From 9fb251dfd6fb40501df32f7d855cefe8a718b69a Mon Sep 17 00:00:00 2001
From: Eugene Yurtsev <eyurtsev@gmail.com>
Date: Mon, 18 Dec 2023 23:07:59 -0500
Subject: [PATCH 1/3] x

---
 .../notebooks/tool_usage/analysis.ipynb       | 389 ++++++++++++++++++
 1 file changed, 389 insertions(+)
 create mode 100644 docs/source/notebooks/tool_usage/analysis.ipynb

diff --git a/docs/source/notebooks/tool_usage/analysis.ipynb b/docs/source/notebooks/tool_usage/analysis.ipynb
new file mode 100644
index 0000000..a189305
--- /dev/null
+++ b/docs/source/notebooks/tool_usage/analysis.ipynb
@@ -0,0 +1,389 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1ba9f105-c48f-4d8c-8253-355ef13156b0",
+   "metadata": {},
+   "source": [
+    "# Analysis\n",
+    "\n",
+    "Let's benchmark against all tool usage tasks. \n",
+    "\n",
+    "Expand the models list to benchmark with different models."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "13a7483b-d08f-49fa-83da-619863171e5b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import datetime\n",
+    "\n",
+    "from langsmith.client import Client\n",
+    "\n",
+    "from langchain_benchmarks import (\n",
+    "    __version__,\n",
+    "    clone_public_dataset,\n",
+    "    model_registry,\n",
+    "    registry,\n",
+    ")\n",
+    "from langchain_benchmarks.rate_limiting import RateLimiter\n",
+    "from langchain_benchmarks.tool_usage.agents import (\n",
+    "    AnthropicToolUserFactory,\n",
+    "    CustomAgentFactory,\n",
+    "    OpenAIAgentFactory,\n",
+    "    OpenAIAssistantFactory,\n",
+    ")\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from langsmith.client import Client"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "925b08db-0442-41d0-8584-bdf40ecf76e6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "client = Client()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "280c9b90-61f1-4d76-8741-500abdd6079c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "claude-2.1-anthropic_tool_user-Multiverse Math-2023-12-18-woof\n",
+      "claude-2.1-anthropic_tool_user-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "claude-2.1-anthropic_tool_user-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "claude-2.1-anthropic_tool_user-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Multiverse Math-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Multiverse Math-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Multiverse Math-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Multiverse Math-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Multiverse Math-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Multiverse Math-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Multiverse Math-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Multiverse Math-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Multiverse Math-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Multiverse Math-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Multiverse Math-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n"
+     ]
+    }
+   ],
+   "source": [
+    "experiment_ids = [\"woof\"]\n",
+    "\n",
+    "\n",
+    "def _endswith(s, suffixes):\n",
+    "    return any(s.endswith(suffix) for suffix in suffixes)\n",
+    "\n",
+    "\n",
+    "client = Client()\n",
+    "projects = [\n",
+    "    project\n",
+    "    for project in client.list_projects()\n",
+    "    if _endswith(project.name, experiment_ids)\n",
+    "]\n",
+    "\n",
+    "print(\"\\n\".join(sorted([project.name for project in projects])))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "7a87b357-0625-41d1-856b-560ecd975a00",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dfs = []\n",
+    "for project in projects:\n",
+    "    # Temporary way to get tag information\n",
+    "    project_info = client.read_project(project_id=project.id)\n",
+    "    \n",
+    "    if project_info.extra is None:\n",
+    "        raise ValueError(project.name)\n",
+    "    try:\n",
+    "        test_results = client.get_test_results(project_name=project.name)\n",
+    "    except Exception:\n",
+    "        continue\n",
+    "\n",
+    "    for k, v in project_info.extra[\"metadata\"].items():\n",
+    "        test_results[k] = v\n",
+    "\n",
+    "    dfs.append(test_results)\n",
+    "\n",
+    "\n",
+    "df = pd.concat(dfs)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9065b7a0-d514-49f7-9d79-67181c41f56d",
+   "metadata": {},
+   "source": [
+    "Compute a standardized \"correct\" column. It uses \"Correct Final State\" for tool usage tasks, and \"correctness (which is based on output) for the other tasks."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b3c0466a-25f4-44d7-bd2a-20da51461994",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "correct = []\n",
+    "\n",
+    "for r in df.to_dict(orient=\"records\"):\n",
+    "    if \"Typewriter\" in r[\"task\"]:\n",
+    "        correct.append(r[\"feedback.Correct Final State\"])\n",
+    "    else:\n",
+    "        correct.append(r[\"feedback.correctness\"])\n",
+    "\n",
+    "df[\"correct\"] = correct\n",
+    "df[\"correct\"].fillna(0, inplace=True)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "270b8ae9-c84b-4ebc-88ab-fa0ac5e28a57",
+   "metadata": {},
+   "source": [
+    "Compute some statistics. We're using estimating standard error of the mean assuming a bernoulli process."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "c59d080c-d3ac-43c3-a527-9961913db2ba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_correct = df.groupby([\"model\", 'arch', \"task\"])[\"correct\"].sum().to_frame(\"num_correct\")\n",
+    "total = df.groupby([\"task\", 'arch', \"model\"]).size().to_frame(\"total\")\n",
+    "stats_df = total.join(num_correct)\n",
+    "stats_df[\"% correct\"] = stats_df[\"num_correct\"] / stats_df[\"total\"]\n",
+    "stats_df[\"error\"] = np.sqrt(\n",
+    "    stats_df[\"% correct\"] * (1 - stats_df[\"% correct\"]) / stats_df[\"total\"]\n",
+    ")\n",
+    "\n",
+    "# stats_df\n",
+    "\n",
+    "models = [\n",
+    "     'mistral-7b-instruct-v0.1',\n",
+    "     'claude-2.1',\n",
+    "     'gpt-3.5-turbo-0613 (functions)',\n",
+    "     'gpt-3.5-turbo-1106 (assistant)',\n",
+    "     'gpt-3.5-turbo-1106 (functions)',\n",
+    "     'gpt-4-0613 (functions)',\n",
+    "     'gpt-4-1106-preview (assistant)',\n",
+    "     'gpt-4-1106-preview (functions)'\n",
+    "]\n",
+    "\n",
+    "tasks = [\n",
+    "    \"Tool Usage - Typewriter (1 tool)\",\n",
+    "    \"Tool Usage - Typewriter (26 tools)\",\n",
+    "    \"Multiverse Math\",\n",
+    "    \"Tool Usage - Relational Data\",\n",
+    "]\n",
+    "\n",
+    "stats_df = stats_df.reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "3704cfb3-79ea-4e7a-bc43-c82a3ae92675",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "names = []\n",
+    "for r in stats_df.to_dict(orient='records'):\n",
+    "    if r['model'].startswith('gpt'):\n",
+    "        if r['arch'] == \"openai_assistant\":\n",
+    "            names.append(f\"{r['model']} (assistant)\")\n",
+    "        else:\n",
+    "            names.append(f\"{r['model']} (functions)\")\n",
+    "    else:\n",
+    "        names.append(r['model'])\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "89d8ae82-a206-4267-9243-33e92628638a",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "stats_df['model'] = names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "0263997a-49ee-47b3-868a-c3461e832970",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# models = stats_df.set_index('task').loc['Tool Usage - Relational Data'].sort_values('% correct')['model'].to_list()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "69df66a1-960c-40a3-abc8-58b503fceda5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABksAAAGbCAYAAABksqcyAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAADy0UlEQVR4nOzdeVhU1f8H8PeA7Isbq4jiBoLJIgSBlvANxQ3X1NREccsFUccNUsQdl0A0UYokrDTNJDNxIxRzwQ1FLREFRZIA94VRQZn5/eGPm9MAMsQq79fzzOPMueec+7kXGGQ+ZxHJZDIZiIiIiIiIiIiIiIiI6imVmg6AiIiIiIiIiIiIiIioJjFZQkRERERERERERERE9RqTJUREREREREREREREVK8xWUJERERERERERERERPUakyVERERERERERERERFSvMVlCRERERERERERERET1GpMlRERERERERERERERUrzFZQkRERERERERERERE9RqTJUREREREREREREREVK8xWUJERERUx7i7u8Pd3b2mw6h38vLy8NFHH6Fp06YQiUQIDw+v6ZCIiIiIiIiokjBZQkRERPQfiESicj0SExNrJDY/P78Sj/300081Fldlcnd3l7vPTZo0wbvvvovo6GhIpdJKPdeMGTNw4MABBAYG4rvvvkOPHj0qtX8iIiIiIiKqOQ1qOgAiIiKiuuy7776Te/3tt98iPj5eodza2ro6w6pXmjdvjpCQEADAnTt38O2332Ls2LG4evUqVqxYUWnnOXToEPr164dZs2ZVWp9ERERERERUOzBZQkRERPQffPLJJ3KvT548ifj4eIVyqjoNGzaUu9+ffvoprKyssH79eixZsgRqamoV7vvly5eQSqVQV1fH7du30ahRo0qI+JXnz59DXV0dKiqc7E1ERERERFTT+JcZERERURWTSCSYOXMmzM3NoaGhASsrK3z++eeQyWRy9V6+fIklS5agTZs20NDQgIWFBT777DMUFBRUS5zXrl3DoEGDYGJiAk1NTTRv3hwff/wxHj16JNT55ptv8L///Q9GRkbQ0NCAjY0NNm7cqNCXVCrFwoUL0axZM2hra8PDwwOXL1+GhYUFRo8eLVf34cOHmD59unB/2rZti5UrV1Z4GS1tbW289957kEgkuHPnTrnPkZmZCZFIhM8//xzh4eHC12HDhg0QiUSQyWSIiIgQlvwqdv36dQwePBhNmjQRzh0XFycXU2JiIkQiEbZt24b58+fDzMwM2traePz4MUaPHg1dXV1kZWWhT58+0NXVhZmZGSIiIgAAly5dwv/+9z/o6OigZcuW2Lp1q1zf9+/fx6xZs9CxY0fo6upCX18fPXv2xIULF0qM4ccff8SyZcvQvHlzaGpq4sMPP0R6errCfTx16hR69eqFxo0bQ0dHB7a2tli7dq1cnStXruCjjz5CkyZNoKmpCScnJ+zevbsCXzUiIiIiIqKaxZklRERERFVIJpOhb9++OHz4MMaOHQt7e3scOHAAs2fPRnZ2NtasWSPUHTduHDZv3oyPPvoIM2fOxKlTpxASEoLU1FT8/PPPVRpnYWEhvLy8UFBQgKlTp8LExATZ2dnYs2cPHj58iIYNGwIANm7ciA4dOqBv375o0KABfv31V0yePBlSqRRTpkwR+gsMDMSqVavg7e0NLy8vXLhwAV5eXnj+/LnceZ8+fYquXbsiOzsbn376KVq0aIETJ04gMDAQOTk5Fd5E/fr161BVVUWjRo2UPsc333yD58+fY8KECdDQ0ECnTp3w3XffYeTIkejWrRt8fHyEunl5eXBzc8PTp0/h7++Ppk2bYvPmzejbty9++uknDBgwQK7vJUuWQF1dHbNmzUJBQQHU1dUBAEVFRejZsyc++OADrFq1Clu2bIGfnx90dHQwb948jBgxAgMHDkRkZCR8fHzg6uqKVq1aCde6a9cuDB48GK1atUJeXh6+/PJLdO3aFZcvX0azZs3kYlixYgVUVFQwa9YsPHr0CKtWrcKIESNw6tQpoU58fDz69OkDU1NTTJs2DSYmJkhNTcWePXswbdo0AMCff/6Jzp07w8zMDAEBAdDR0cGPP/6I/v37Y+fOnQrXTkREREREVKvJiIiIiKjSTJkyRfb6f7F27dolAyBbunSpXL2PPvpIJhKJZOnp6TKZTCZLSUmRAZCNGzdOrt6sWbNkAGSHDh0Syrp27Srr2rXrG2MBIJsyZUqJx3bs2CEDIDt8+LBMJpPJzp8/LwMg27FjR5l9Pn36VKHMy8tL1rp1a+F1bm6urEGDBrL+/fvL1Vu4cKEMgGzUqFFC2ZIlS2Q6Ojqyq1evytUNCAiQqaqqyrKyssqMp2vXrrL27dvL7ty5I7tz544sNTVV5u/vLwMg8/b2VuocN27ckAGQ6evry27fvq1wrpLu5/Tp02UAZEePHhXKnjx5ImvVqpXMwsJCVlRUJJPJZLLDhw/LAMhat26tcA9HjRolAyBbvny5UPbgwQOZlpaWTCQSybZt2yaUX7lyRQZAFhwcLJQ9f/5cOE+xGzduyDQ0NGSLFy8WyopjsLa2lhUUFAjla9eulQGQXbp0SSaTyWQvX76UtWrVStayZUvZgwcP5PqVSqXC8w8//FDWsWNH2fPnz+WOu7m5ydq1a6dw/4iIiIiIiGozLsNFREREVIX27t0LVVVV+Pv7y5XPnDkTMpkM+/btE+oBgFgsVqgHQGFZp8pWPHPkwIEDePr0aan1tLS0hOePHj3C3bt30bVrV1y/fl1YrishIQEvX77E5MmT5dpOnTpVob8dO3bg/fffR+PGjXH37l3h4enpiaKiIvz+++9vjP3KlSswNDSEoaEhrK2t8cUXX6B3796Ijo6u0DkGDRoEQ0PDN54XePV1c3Z2RpcuXYQyXV1dTJgwAZmZmbh8+bJc/VGjRsndw9eNGzdOeN6oUSNYWVlBR0cHQ4YMEcqtrKzQqFEjXL9+XSjT0NAQ9j0pKirCvXv3oKurCysrK5w7d07hPL6+vsKMFgB4//33AUDo8/z587hx4wamT5+usEdL8fJj9+/fx6FDhzBkyBA8efJEuKf37t2Dl5cXrl27huzs7NJvHBERERERUS3DZbiIiIiIqtDNmzfRrFkz6OnpyZVbW1sLx4v/VVFRQdu2beXqmZiYoFGjRkK9ylb84XerVq0gFosRFhaGLVu24P3330ffvn3xySefCIkUADh+/DiCg4ORlJSkkFR59OgRGjZsKMT672tp0qQJGjduLFd27do1XLx4sdTkxO3bt994DRYWFoiKioJIJIKmpibatWsHIyOjCp+jeHmr8rh58yZcXFwUyl//+r7zzjtv7FtTU1MhvoYNG6J58+Zy+6MUlz948EB4LZVKsXbtWmzYsAE3btxAUVGRcKxp06YK52rRooXc6+KvSXGfGRkZACAX97+lp6dDJpMhKCgIQUFBJda5ffs2zMzMSu2DiIiIiIioNmGyhIiIiKgW+fcH4/+FhoYGnj17VuKx4kSHpqamUBYaGorRo0fjl19+wcGDB+Hv74+QkBCcPHkSzZs3R0ZGBj788EO0b98eYWFhMDc3h7q6Ovbu3Ys1a9ZUaEN2qVSKbt26Yc6cOSUet7S0fGMfOjo68PT0rLRzlDbzozKU1reqqqpS5TKZTHi+fPlyBAUFYcyYMViyZAmaNGkCFRUVTJ8+vcSvSXn6fJPifmfNmgUvL68S6/w7WUZERERERFSbMVlCREREVIVatmyJ3377DU+ePJGbXXLlyhXhePG/UqkU165dE2YlAK82EH/48KFQT9lzp6WllXisuPzf/Xbs2BEdO3bE/PnzceLECXTu3BmRkZFYunQpfv31VxQUFGD37t1ysxMOHz6scF7g1eyD12dS3Lt3T25GBAC0adMG+fn5ZSY7/quqPEdp9/jfX9+q9NNPP8HDwwObNm2SK3/48CEMDAyU7q9NmzYAgD/++KPUe9a6dWsAgJqaWpV+7YiIiIiIiKoL9ywhIiIiqkK9evVCUVER1q9fL1e+Zs0aiEQi9OzZU6gHAOHh4XL1wsLCAAC9e/eu0LlPnjyJ5ORkufKHDx9iy5YtsLe3h4mJCQDg8ePHePnypVy9jh07QkVFBQUFBQD+mZHw+gyER48e4ZtvvpFr9+GHH6JBgwbYuHGjXPm/7wEADBkyBElJSThw4IDCsYcPHyrEVBFVeY5evXrh9OnTSEpKEsokEgm++uorWFhYwMbGpsJ9l5eqqqrCrJAdO3ZUeM+QTp06oVWrVggPD8fDhw/ljhWfx8jICO7u7vjyyy+Rk5Oj0MedO3cqdG4iIiIiIqKawpklRERERFXI29sbHh4emDdvHjIzM2FnZ4eDBw/il19+wfTp04VR/HZ2dhg1ahS++uorPHz4EF27dsXp06exefNm9O/fHx4eHkqfOyAgADt27MAHH3yATz/9FO3bt8fff/+NmJgY5OTkyCU5Dh06BD8/PwwePBiWlpZ4+fIlvvvuO6iqqmLQoEEAgO7du0NdXR3e3t749NNPkZ+fj6ioKBgZGcl9YG5sbIxp06YhNDQUffv2RY8ePXDhwgXs27cPBgYGckuNzZ49G7t370afPn0wevRoODo6QiKR4NKlS/jpp5+QmZlZodkRr6vKcwQEBOCHH35Az5494e/vjyZNmmDz5s24ceMGdu7cKWy8XpX69OmDxYsXw9fXF25ubrh06RK2bNkizP5QloqKCjZu3Ahvb2/Y29vD19cXpqamuHLlCv78808h6RQREYEuXbqgY8eOGD9+PFq3bo28vDwkJSXh1q1buHDhQmVeJhERERERUZVisoSIiIioCqmoqGD37t1YsGABtm/fjm+++QYWFhZYvXo1Zs6cKVf366+/RuvWrRETE4Off/4ZJiYmCAwMRHBwcIXObWxsjFOnTmHhwoX48ccfkZeXB319fbi5uWH79u1yG5Pb2dnBy8sLv/76K7Kzs6GtrQ07Ozvs27cP7733HgDAysoKP/30E+bPn49Zs2bBxMQEkyZNgqGhIcaMGSN37pUrV0JbWxtRUVH47bff4OrqioMHD6JLly5y+6Roa2vjyJEjWL58OXbs2IFvv/0W+vr6sLS0xKJFi+Q2l6+oqjyHsbExTpw4gblz5+KLL77A8+fPYWtri19//bVCs4Eq4rPPPoNEIsHWrVuxfft2dOrUCXFxcQgICKhwn15eXjh8+DAWLVqE0NBQSKVStGnTBuPHjxfq2NjY4OzZs1i0aBFiYmJw7949GBkZwcHBAQsWLKiMSyMiIiIiIqo2IpkyOzkSEREREVXQw4cP0bhxYyxduhTz5s2r6XCIiIiIiIiIBNyzhIiIiIgq3bNnzxTKivdjcXd3r95giIiIiIiIiN6Ay3ARERERUaXbvn07YmJi0KtXL+jq6uLYsWP44Ycf0L17d3Tu3LmmwyMiIiIiIiKSw2QJEREREVU6W1tbNGjQAKtWrcLjx4+FTd+XLl1a06ERERERERERKeCeJUREREREREREREREVK9xzxIiIiIiIiIiIiIiIqrXmCwhIiIiIiIiIiIiIqJ6rd7tWSKVSvH3339DT08PIpGopsMhIiIiIiIiIiKiMshkMjx58gTNmjWDigrHfhNR1ah3yZK///4b5ubmNR0GERERERERERERKeGvv/5C8+bNazoMInpL1btkiZ6eHoBXb676+vo1HA0RERERERERERGV5fHjxzA3Nxc+1yMiqgr1LllSvPSWvr4+kyVERERERERERER1BJfUJ6KqxEX+iIiIiIiIiIiIiIioXmOyhIiIiIiIiIiIiIiI6jUmS4iIiIiIiIiIiIiIqF5jsoSIiIiIiIiIiIiIiOo1JkuIiIiIiIiIiIiIiKheY7KEiIiIiIiIiIiIiIjqNSZLiIiIiIiIiIiIiIioXmOyhIiIiIiIiIiIiIiI6jUmS4iIiIiIiIiIiIiIqF5jsoSIiIiIiIiIiIiIiOo1JkuIiIiIiIiIiIiIiKheY7KEiIiIiIiIiIiIiIjqNSZLiKpJREQELCwsoKmpCRcXF5w+fbrUui9evMDixYvRpk0baGpqws7ODvv375ers3DhQohEIrlH+/bta30MRHXV77//Dm9vbzRr1gwikQi7du2q6ZCIiIiIiIiIiKiSMFlCVA22b98OsViM4OBgnDt3DnZ2dvDy8sLt27dLrD9//nx8+eWX+OKLL3D58mVMnDgRAwYMwPnz5+XqdejQATk5OcLj2LFjtToGorpMIpHAzs4OERERNR0KEREREVGtx8F6/+C9ICKqG5gsIaoGYWFhGD9+PHx9fWFjY4PIyEhoa2sjOjq6xPrfffcdPvvsM/Tq1QutW7fGpEmT0KtXL4SGhsrVa9CgAUxMTISHgYFBrY6BqC7r2bMnli5digEDBtR0KEREREREtRoH6/2D94KIqO5gsoSoihUWFiI5ORmenp5CmYqKCjw9PZGUlFRim4KCAmhqasqVaWlpKfzn59q1a2jWrBlat26NESNGICsrq9bGQERERERERPUDB+v9g/eCiKjuYLKEqIrdvXsXRUVFMDY2lis3NjZGbm5uiW28vLwQFhaGa9euQSqVIj4+HrGxscjJyRHquLi4ICYmBvv378fGjRtx48YNvP/++3jy5EmtjIGIiIiIiIjefhys9w/eCyKiuoXJEqJaaO3atWjXrh3at28PdXV1+Pn5wdfXFyoq//zI9uzZE4MHD4atrS28vLywd+9ePHz4ED/++ONbEwMRERERERHVLRys9w/eCyKiuoXJEqIqZmBgAFVVVeTl5cmV5+XlwcTEpMQ2hoaG2LVrFyQSCW7evIkrV65AV1cXrVu3LvU8jRo1gqWlJdLT02tlDEREREREREQl4WC9f/BeEBHVHCZLiKqYuro6HB0dkZCQIJRJpVIkJCTA1dW1zLaampowMzPDy5cvsXPnTvTr16/Uuvn5+cjIyICpqWmtjIGIiIiIiIjefhys9w/eCyKiuoXJEqJqIBaLERUVhc2bNyM1NRWTJk2CRCKBr68vAMDHxweBgYFC/VOnTiE2NhbXr1/H0aNH0aNHD0ilUsyZM0eoM2vWLBw5cgSZmZk4ceIEBgwYAFVVVQwbNqzWxkBUl+Xn5yMlJQUpKSkAgBs3biAlJYVrAxMRERERvYaD9f7Be0FEVLc0qOkAiOqDoUOH4s6dO1iwYAFyc3Nhb2+P/fv3C+uWZmVlyU2pff78OebPn4/r169DV1cXvXr1wnfffYdGjRoJdW7duoVhw4bh3r17MDQ0RJcuXXDy5EkYGhrW2hiI6rKzZ8/Cw8NDeC0WiwEAo0aNQkxMTA1FRURERERU+4jFYowaNQpOTk5wdnZGeHi4wmA9MzMzhISEAHg1WC87Oxv29vbIzs7GwoULSxys5+3tjZYtW+Lvv/9GcHBwnRisx3tBRFSHyOqZR48eyQDIHj16VNOh1Evr16+XtWzZUqahoSFzdnaWnTp1qtS6hYWFskWLFslat24t09DQkNna2sr27dtXjdESVS/+fBBRXcD3KiIiIiqPL774QtaiRQuZurq6zNnZWXby5EnhWNeuXWWjRo0SXicmJsqsra1lGhoasqZNm8pGjhwpy87Olutv6NChMlNTU5m6urrMzMxMNnToUFl6enp1Xc5/wnvx3/HzPCKqDiKZTCar6YRNdXr8+DEaNmyIR48eQV9fv6bDqVe2b98OHx8fREZGwsXFBeHh4dixYwfS0tJgZGSkUH/u3Ln4/vvvERUVhfbt2+PAgQMQi8U4ceIEHBwcauAKiKoOfz6IqC7gexURERHVdREREVi9ejVyc3NhZ2eHL774As7OziXWffHiBUJCQrB582ZkZ2fDysoKK1euRI8ePao5auLneURUHWo0WfL7779j9erVSE5ORk5ODn7++Wf079+/zDaJiYkQi8X4888/YW5ujvnz52P06NHlPiffXGuOi4sL3n33Xaxfvx7Aq3U6zc3NMXXqVAQEBCjUb9asGebNm4cpU6YIZYMGDYKWlha+//77aoubqDrw54OI6gK+VxEREVFdxoEfdRc/zyOi6lCjG7xLJBLY2dkhIiKiXPVv3LiB3r17w8PDAykpKZg+fTrGjRuHAwcOVHGk9F8VFhYiOTkZnp6eQpmKigo8PT2RlJRUYpuCggJoamrKlWlpaeHYsWNVGitRdePPBxHVBXyvIiIiorouLCwM48ePh6+vL2xsbBAZGQltbW1ER0eXWP+7777DZ599hl69eqF169aYNGkSevXqhdDQ0GqOnIiIqkONJkt69uyJpUuXYsCAAeWqHxkZiVatWiE0NBTW1tbw8/PDRx99hDVr1lRxpPRf3b17F0VFRcJm4sWMjY2Rm5tbYhsvLy+EhYXh2rVrkEqliI+PR2xsLHJycqojZKJqw58PIqoL+F5FREREdRkHfhAR0ZvUaLJEWUlJSXK/1IBXf4SX9ksNePWL7fHjx3IPqhvWrl2Ldu3aoX379lBXV4efnx98fX2holKnvm2JqgR/PoioLuB7FREREdUWHPhBRERv0qCmA1BGbm5uib/UHj9+jGfPnkFLS0uhTUhICBYtWlRdIVIpDAwMoKqqiry8PLnyvLw8mJiYlNjG0NAQu3btwvPnz3Hv3j00a9YMAQEBaN26dXWEXGMkEgl0dXUBAPn5+dDR0amXMdQn/PmoWUVhY6u0f1Xxpirtn6i68L2KiIiI6pu1a9di/PjxaN++PUQiEdq0aQNfX99Sl+0iIqK67a0f1hcYGIhHjx4Jj7/++qumQ6qX1NXV4ejoiISEBKFMKpUiISEBrq6uZbbV1NSEmZkZXr58iZ07d6Jfv35VHS5RteLPBxHVBXyvIiIioqogkUggEokgEokgkUiq7Dz/ZeCHRCLBzZs3ceXKFejq6lbZwI/quhdERFSyOpUsMTExKfGXmr6+fomzSgBAQ0MD+vr6cg+qGWKxGFFRUdi8eTNSU1MxadIkSCQS+Pr6AgB8fHwQGBgo1D916hRiY2Nx/fp1HD16FD169IBUKsWcOXNq6hKIqgx/PoioLuB7FREREdVVHPhBRERvUqeW4XJ1dcXevXvlyuLj49/4S41qh6FDh+LOnTtYsGABcnNzYW9vj/379wtLq2VlZcmtYf78+XPMnz8f169fh66uLnr16oXvvvsOjRo1qqErIKo6/PkgorqA71VERERUl4nFYowaNQpOTk5wdnZGeHi4wsAPMzMzhISEAHg18CM7Oxv29vbIzs7GwoULOfCDiOgtJpLJZLKaOnl+fj7S09MBAA4ODggLC4OHhweaNGmCFi1aIDAwENnZ2fj2228BADdu3MA777yDKVOmYMyYMTh06BD8/f0RFxcHLy+vcp3z8ePHaNiwIR49esRZJlQr1Yb9QmpDDETVhXuWEBERERHVnOr++3P9+vVYvXq1MPBj3bp1cHFxAQC4u7vDwsICMTExAIAjR45g0qRJcgM/VqxYgWbNmlVJbPxbvHT8PI+IqkONziw5e/YsPDw8hNdisRgAMGrUKMTExCAnJwdZWVnC8VatWiEuLg4zZszA2rVr0bx5c3z99dflTpQQEREREREREVH95efnBz8/vxKPJSYmyr3u2rUrLl++XA1RERFRbVCje5a4u7tDJpMpPIoz+DExMQq/qNzd3XH+/HkUFBQgIyMDo0ePrva4qW6JiIiAhYUFNDU14eLigtOnT5dZPzw8HFZWVtDS0oK5uTlmzJiB58+fC8cXLlwobLhW/Gjfvn1VXwYRERERERERERERVZE6tcE7kbK2b98OsViM4OBgnDt3DnZ2dvDy8sLt27dLrL9161YEBAQgODgYqamp2LRpE7Zv347PPvtMrl6HDh2Qk5MjPI4dO1Ydl0NERERUa1T2gBQiIiIiIqKaxGQJvdXCwsIwfvx4+Pr6wsbGBpGRkdDW1kZ0dHSJ9U+cOIHOnTtj+PDhsLCwQPfu3TFs2DCFP/4bNGgAExMT4WFgYFAdl0NERERUK1TVgBQiIiIiIqKawmQJvbUKCwuRnJwMT09PoUxFRQWenp5ISkoqsY2bmxuSk5OF5Mj169exd+9e9OrVS67etWvX0KxZM7Ru3RojRoyQ21uHiIiI6G1XVQNSiIiIiIiIagqTJVQrSCQSYf8PiURSKX3evXsXRUVFMDY2lis3NjZGbm5uiW2GDx+OxYsXo0uXLlBTU0ObNm3g7u4uN+rRxcUFMTEx2L9/PzZu3IgbN27g/fffx5MnTyolbqKSVMXPCBFRZeL7VP1RlQNSiIiIiIiIakqDmg6AqDZJTEzE8uXLsWHDBri4uCA9PR3Tpk3DkiVLEBQUBADo2bOnUN/W1hYuLi5o2bIlfvzxR4wdO7amQiciIiKqFmUNSLly5UqJbYYPH467d++iS5cukMlkePnyJSZOnMhluIiIqNaQSCTQ1dUFAOTn50NHR6eGIyIiourGmSX01jIwMICqqiry8vLkyvPy8mBiYlJim6CgIIwcORLjxo1Dx44dMWDAACxfvhwhISGQSqUltmnUqBEsLS2Rnp5e6ddARERE9DZ4fUDKuXPnEBsbi7i4OCxZsqSmQyMiIiIiIgLAZAm9xdTV1eHo6IiEhAShTCqVIiEhAa6uriW2efr0KVRU5H8sVFVVAQAymazENvn5+cjIyICpqWklRU5ERERUe1XXgBQiIiIiIqLqxGQJvdXEYjGioqKwefNmpKamYtKkSZBIJPD19QUA+Pj4IDAwUKjv7e2NjRs3Ytu2bbhx4wbi4+MRFBQEb29vIWkya9YsHDlyBJmZmThx4gQGDBgAVVVVDBs2rEaukYiIiKg6VdeAFCIiIiIiourEPUvorTZ06FDcuXMHCxYsQG5uLuzt7bF//35hje2srCy5P9znz58PkUiE+fPnIzs7G4aGhvD29sayZcuEOrdu3cKwYcNw7949GBoaokuXLjh58iQMDQ2r/fqIiIiIaoJYLMaoUaPg5OQEZ2dnhIeHKwxIMTMzQ0hICIBXA1LCwsLg4OAg7Av37wEpRERERERENYnJEnrr+fn5wc/Pr8RjiYmJcq8bNGiA4OBgBAcHl9rftm3bKhRH7upj5ar3tPCZ8Dwv/AS01bXK1c5kdpc31vkhbXC5+nr+9KXw/Mern0BTu3xvFcOsdpSrHhEREdVtVTEghYjov4qIiMDq1auRm5sLOzs7fPHFF3B2di61fnh4ODZu3IisrCwYGBjgo48+QkhICDQ1NQEAv//+O1avXo3k5GTk5OTg559/Rv/+/avpat4CV+3LV+9p0T/Pr70HaJcziW6ZomxENWbPnj3lqvf8+XPh+b59+4TvxTfp06dPheIiIiJ5TJYQEREREZHSKntAChHRf7F9+3aIxWJERkbCxcUF4eHh8PLyQlpaGoyMjBTqb926FQEBAYiOjoabmxuuXr2K0aNHQyQSISwsDAAgkUhgZ2eHMWPGYODAgdV9SURERFTNmCwhIiIiIiIiojotLCwM48ePF5YDjIyMRFxcHKKjoxEQEKBQ/8SJE+jcuTOGDx8OALCwsMCwYcNw6tQpoU7Pnj3Rs2fP6rkAIiIiqnHc4J2IiIiIiIiI6qzCwkIkJyfD09NTKFNRUYGnpyeSkpJKbOPm5obk5GScPn0aAHD9+nXs3bsXvXr1qpaYiYiIqPbhzBIiIiIiIiIiqrPu3r2LoqIiYd+kYsbGxrhy5UqJbYYPH467d++iS5cukMlkePnyJSZOnIjPPvusOkImIiKiWogzS4iIiIiIiIioXklMTMTy5cuxYcMGnDt3DrGxsYiLi8OSJUtqOjQiIiKqIZxZQvQaiUQCXV1dAEB+fj50dHRqOCIiIiIiIiIqi4GBAVRVVZGXlydXnpeXBxMTkxLbBAUFYeTIkRg3bhwAoGPHjpBIJJgwYQLmzZsHFRWOLSUiIqpv+NufiIiIiIgqjUQigUgkgkgkgkQiqelwiKgeUFdXh6OjIxISEoQyqVSKhIQEuLq6ltjm6dOnCgkRVVVVAIBMJqu6YImIiKjW4swSIiIiIiIiIqrTxGIxRo0aBScnJzg7OyM8PBwSiQS+vr4AAB8fH5iZmSEkJAQA4O3tjbCwMDg4OMDFxQXp6ekICgqCt7e3kDTJz89Henq6cI4bN24gJSUFTZo0QYsWLar/IomIiKhKMVlCRERERERERHXa0KFDcefOHSxYsAC5ubmwt7fH/v37hU3fs7Ky5GaSzJ8/HyKRCPPnz0d2djYMDQ3h7e2NZcuWCXXOnj0LDw8P4bVYLAYAjBo1CjExMdVzYURERFRtmCwhIiIiIiIiojrPz88Pfn5+JR5LTEyUe92gQQMEBwcjODi41P7c3d25JBcREVE9wj1LiIiIiIiIiIiIiIioXmOyhIiIiIiIiIiIiIiI6jUmS4iIiIiIiIiIiIiIqF5TOlnStWtXfPvtt3j27FlVxENEREREREREVCdFRETAwsICmpqacHFxwenTp0ut6+7uDpFIpPDo3bu3XL3U1FT07dsXDRs2hI6ODt59911kZWVV9aVUGx1tVcjS7CBLs4OOtmpNh1OjNDU18euvv+LXX3+FpqZmTYdDRFTvKJ0scXBwwKxZs2BiYoLx48fj5MmTVREXUb2lra6FnFVHkbPqKLTVtWokBk3tBth65SNsvfIRNLUb1EgMREREREREdcn27dshFosRHByMc+fOwc7ODl5eXrh9+3aJ9WNjY5GTkyM8/vjjD6iqqmLw4MFCnYyMDHTp0gXt27dHYmIiLl68iKCgIH6QTkREVAWU/hQ0PDwcn3/+OXbv3o3Nmzfjgw8+QNu2bTFmzBiMHDkSxsbGVREn1VFFYWPLV6/gxT/P101CkYZaudqpijdVKC6iiIgIrF69Grm5ubCzs8MXX3wBZ2fnEuu6u7vjyJEjCuW9evVCXFwcAGD06NHYvHmz3HEvLy/s37+/zDj27NlTrnifP38uPN+3b1+5/zjq06dPueoREZWG71NUm1X273Miov8iLCwM48ePh6+vLwAgMjIScXFxiI6ORkBAgEL9Jk2ayL3etm0btLW15ZIl8+bNQ69evbBq1SqhrE2bNlV0BW+nv49HlKve02cFwvOcpC+hraVRrnbNOk+pUFxERFT7VGjPkgYNGmDgwIH45ZdfcOvWLQwfPhxBQUEwNzdH//79cejQocqOk4io0lTFiC8A6NGjh1y9H374oTouh4iIqF6qqt/nRPT2k0gkwpJXEomkUvosLCxEcnIyPD09hTIVFRV4enoiKSmpXH1s2rQJH3/8MXR0dAAAUqkUcXFxsLS0hJeXF4yMjODi4oJdu3ZVSsxEREQk7z9t8H769GkEBwcjNDQURkZGCAwMhIGBAfr06YNZs2ZVVoxERJXq9RFfNjY2iIyMhLa2NqKjo0us36RJE5iYmAiP+Ph4hRFfAKChoSFXr3HjxtVxOURERPVSVf0+JyKqiLt376KoqEhhtQ1jY2Pk5ua+sf3p06fxxx9/YNy4cULZ7du3kZ+fjxUrVqBHjx44ePAgBgwYgIEDB5Y4U46IiIj+G6WTJbdv30ZoaCjeeecdvP/++7hz5w5++OEHZGZmYtGiRfj6669x8OBBREZGVkW8RET/SVWM+CqWmJgIIyMjWFlZYdKkSbh3716lxk5ERESvVOXvcyKimrBp0yZ07NhRbilBqVQKAOjXrx9mzJgBe3t7BAQEoE+fPvzMhYiIqAoovWdJ8+bN0aZNG4wZMwajR4+GoaGhQh1bW1u8++67lRIgEVFlKmvE15UrV97YvnjE16ZN8vvl9OjRAwMHDkSrVq2QkZGBzz77DD179kRSUhJUVVUr9RqIiIjqu6r6fU5EVFEGBgZQVVVFXl6eXHleXh5MTEzKbCuRSLBt2zYsXrxYoc8GDRrAxsZGrtza2hrHjh2rnMCJiIhIoHSyJCEhAe+//36ZdfT19XH48OEKB0VEVFuVNOILAD7++GPheceOHWFra4s2bdogMTERH374YXWHSURERGUo7fc5EVFFqaurw9HREQkJCejfvz+AVzNDEhIS4OfnV2bbHTt2oKCgAJ988olCn++++y7S0tLkyq9evYqWLVtWavxERERUgWW43pQoISKqzSpjxNfYsWPfeJ7WrVvDwMAA6enp/yleIiIiUlRdv8+JiJQhFosRFRWFzZs3IzU1FZMmTYJEIoGvry8AwMfHB4GBgQrtNm3ahP79+6Np06YKx2bPno3t27cjKioK6enpWL9+PX799VdMnjy5yq+HiIiovinXzBIHBweIRKJydXju3Ln/FBARUVWqihFfJbl16xbu3bsHU1PTygibiIiIXlNdv8+JiJQxdOhQ3LlzBwsWLEBubi7s7e2xf/9+YcnArKwsqKjIj1lNS0vDsWPHcPDgwRL7HDBgACIjIxESEgJ/f39YWVlh586d6NKlS5VfDxERUX1TrmRJ8R8gRERvA7FYjFGjRsHJyQnOzs4IDw9XGPFlZmaGkJAQuXaljfjKz8/HokWLMGjQIJiYmCAjIwNz5sxB27Zt4eXlVW3XRUREVJ9U9u9zIqLK4OfnV2rSNjExUaHMysoKMpmszD7HjBmDMWPGVEZ4REREVIZyJUuCg4OrOg4iompT2SO+VFVVcfHiRWzevBkPHz5Es2bN0L17dyxZsgQaGhrVck1ERET1TVWM4CYiIiIiovpL6Q3eW7dujTNnziiMxHr48CE6deqE69evV1pwRERVpTJHfGlpaeHAgQOVGR4RERGVQ1WM4CYiIiIiovpJ6Q3eMzMzUVRUpFBeUFCAW7duVUpQRERERERERERERERE1aXcyZLdu3dj9+7dAIADBw4Ir3fv3o2ff/4ZS5YsQatWraosUCIiIiIiIiKqfSIiImBhYQFNTU24uLjg9OnTpdZ1d3eHSCRSePTu3VuoExsbi+7du6Np06YQiURISUmphqt4e/DrQUREVDHlXoareJN3kUiEUaNGyR1TU1ODhYUFQkNDKzU4IiIiIiIiIqq9tm/fDrFYjMjISLi4uCA8PBxeXl5IS0uDkZGRQv3Y2FgUFhYKr+/duwc7OzsMHjxYKJNIJOjSpQuGDBmC8ePHV8t1vC349SAiIqq4cs8skUqlkEqlaNGiBW7fvi28lkqlKCgoQFpaGvr06VOVsRLRW6qyRz4REb2N+F5JRES1UVhYGMaPHw9fX1/Y2NggMjIS2traiI6OLrF+kyZNYGJiIjzi4+Ohra0t9+H8yJEjsWDBAnh6elbXZdQIiUQi/I6WSCSV0ie/HkRERBWn9AbvN27cqIo4iKpU2Oaz5apXUPBMeL5uyzloaGiVq514lFOF4qKqGflERPS24XslERHVRoWFhUhOTkZgYKBQpqKiAk9PTyQlJZWrj02bNuHjjz+Gjo5OVYVZb/DrQURE9N8ovcG7v78/1q1bp1C+fv16TJ8+vTJiIqJ6pCpGPlWmqhjtRUSkrNr+XklERPXT3bt3UVRUBGNjY7lyY2Nj5ObmvrH96dOn8ccff2DcuHFVFWK9wq8HERHRf6N0smTnzp3o3LmzQrmbmxt++umnSgmKiOqH4pFPr0/n5sgnIiJ5fK8kUh4HOxDVDZs2bULHjh3h7Oxc06EQ+PUgIiJSOlly7949NGzYUKFcX18fd+/erZSgiKh+4MgnIqI343slERHVVgYGBlBVVUVeXp5ceV5eHkxMTMpsK5FIsG3bNowdO7YqQ6xX+PUgIiL6b5ROlrRt2xb79+9XKN+3bx9at25dKUEREZUHRz4REb0Z3yuJiKiqqKurw9HREQkJCUKZVCpFQkICXF1dy2y7Y8cOFBQU4JNPPqnqMOsNfj2IiEqXmJgIkUiEhw8flruNhYUFwsPDqywmqn2UTpaIxWLMmTMHwcHBOHLkCI4cOYIFCxYgICAAM2bMqIoYiegtxZFPRERvxvdKIiKqzcRiMaKiorB582akpqZi0qRJkEgk8PX1BQD4+PjIbThebNOmTejfvz+aNm2qcOz+/ftISUnB5cuXAQBpaWlISUkp14zK+o5fj4rT1tJA9rH1yD62HtpaGjUdDlG9M3r0aIhEIkycOFHh2JQpUyASiTB69OjqD4zqlQbKNhgzZgwKCgqwbNkyLFmyBMCrLNvGjRvh4+NT6QFS/aCjoYaXoWNqOgyqZq+PfOrfvz+Af0Y++fn5ldm2vo180tTUxK+//lrTYRBRDagr75V8nyIiqp+GDh2KO3fuYMGCBcjNzYW9vT32798vLB+ZlZUFFRX5cZppaWk4duwYDh48WGKfu3fvFj7cB4CPP/4YABAcHIyFCxdWzYW8Jfj1IKK6zNzcHNu2bcOaNWugpaUFAHj+/Dm2bt2KFi1a1HB0VB8oPbMEACZNmoRbt24hLy8Pjx8/xvXr15koIaIKqYqRT0REbxu+VxIRUW3m5+eHmzdvoqCgAKdOnYKLi4twLDExETExMXL1raysIJPJ0K1btxL7Gz16NGQymcKDH8yXD78eRFRXderUCebm5oiNjRXKYmNj0aJFCzg4OAhlBQUF8Pf3h5GRETQ1NdGlSxecOXNGrq+9e/fC0tISWlpa8PDwQGZmpsL5jh07hvfffx9aWlowNzeHv78/JBJJlV0f1X4VSpa8fPkSv/32G2JjYyGTyQAAf//9N/Lz8ys1OCJ6+w0dOhSff/45FixYAHt7e6SkpCiMfMrJyZFrUzzyicvKEFF9wfdKIiIiIiKqD8aMGYNvvvlGeB0dHS03uw0A5syZg507d2Lz5s04d+4c2rZtCy8vL9y/fx8A8Ndff2HgwIHw9vZGSkoKxo0bh4CAALk+MjIy0KNHDwwaNAgXL17E9u3bcezYsTfO3qe3m9LLcN28eRM9evRAVlYWCgoK0K1bN+jp6WHlypUoKChAZGRkVcRJRG8xPz+/Un8ZJSYmKpQVj3wiIqpP+F5JRERERERvu08++QSBgYG4efMmAOD48ePYtm2b8DePRCLBxo0bERMTg549ewIAoqKiEB8fj02bNmH27NnYuHEj2rRpg9DQUACv/ja6dOkSVq5cKZwnJCQEI0aMwPTp0wEA7dq1w7p169C1a1ds3LgRmpqa1XfRVGsonSyZNm0anJyccOHCBbklHQYMGIDx48dXanBEREREREREREREVD8YGhqid+/eiImJgUwmQ+/evWFgYCAcz8jIwIsXL9C5c2ehTE1NDc7OzkhNTQUApKamyi1BCACurq5yry9cuICLFy9iy5YtQplMJoNUKsWNGzdgbW1dFZdHtZzSyZKjR4/ixIkTUFdXlyu3sLBAdnZ2pQVGRERERERERERERPXLmDFjhFn1ERERVXKO/Px8fPrpp/D391c4xs3k6y+l9yyRSqUoKipSKL916xb09PSUDiAiIgIWFhbQ1NSEi4sLTp8+XWb98PBwWFlZCRvvzJgxA8+fP1f6vERERERERERERERUu/To0QOFhYV48eIFvLy85I61adMG6urqOH78uFD24sULnDlzBjY2NgAAa2trhc+YT548Kfe6U6dOuHz5Mtq2bavw+PckAao/lJ5Z0r17d4SHh+Orr74CAIhEIuTn5yM4OBi9evVSqq/t27dDLBYjMjISLi4uCA8Ph5eXF9LS0mBkZKRQf+vWrQgICEB0dDTc3Nxw9epVjB49GiKRCGFhYcpeChERERERERFVI4lEAl1dXQCvRvXq6OhUWt9hm8+Wq15BwTPh+bot56ChoVWuduJRThWKqzaryq8HEVFFqaqqCktqqaqqyh3T0dHBpEmTMHv2bDRp0gQtWrTAqlWr8PTpU4wdOxYAMHHiRISGhmL27NkYN24ckpOTERMTI9fP3Llz8d5778HPzw/jxo2Djo4OLl++jPj4eKxfv75arpNqH6Vnlnz++ec4fvw4bGxs8Pz5cwwfPlxYguv1TXLKIywsDOPHj4evry9sbGwQGRkJbW1tREdHl1j/xIkT6Ny5s3DO7t27Y9iwYW+cjUJERERERFRVlJ0t//DhQ0yZMgWmpqbQ0NCApaUl9u7dW+djICIiIqos+vr60NfXL/HYihUrMGjQIIwcORKdOnVCeno6Dhw4gMaNGwN4tYzWzp07sWvXLtjZ2SEyMhLLly+X68PW1hZHjhzB1atX8f7778PBwQELFixAs2bNqvzaqPZSemaJubk5Lly4gO3bt+PChQvIz8/H2LFjMWLECGhplW80BgAUFhYiOTkZgYGBQpmKigo8PT2RlJRUYhs3Nzd8//33OH36NJydnXH9+nXs3bsXI0eOLPU8BQUFKCgoEF4/fvy43DESUc3iKCciojfjeyVRzVJ2tnxhYSG6desGIyMj/PTTTzAzM8PNmzfRqFGjOh0DERER0X/x75kf/7Zr1y7huaamJtatW4d169aVWr9Pnz7o06ePXJmvr6/c63fffRcHDx4stY/MzMwyY6K3j1LJkhcvXqB9+/bYs2cPRowYgREjRlT4xHfv3kVRURGMjY3lyo2NjXHlypUS2wwfPhx3795Fly5dIJPJ8PLlS0ycOBGfffZZqecJCQnBokWLKhwnERERERFxeZvSvD5bHgAiIyMRFxeH6OhoBAQEKNSPjo7G/fv3ceLECaipqQEALCws6nwMRERERER1nVLLcKmpqdXoZuqJiYlYvnw5NmzYgHPnziE2NhZxcXFYsmRJqW0CAwPx6NEj4fHXX39VY8RERERERPS2Kp4t7+npKZS9abb87t274erqiilTpsDY2BjvvPMOli9fjqKiojobAxERERHR20DpZbimTJmClStX4uuvv0aDBko3FxgYGEBVVRV5eXly5Xl5eTAxMSmxTVBQEEaOHIlx48YBADp27AiJRIIJEyZg3rx5UFFRzP1oaGhAQ0OjwnESERERERGVpCKz5a9fv45Dhw5hxIgR2Lt3L9LT0zF58mS8ePECwcHBdTIGIiIiIqK3gdLZjjNnziAhIQEHDx5Ex44dFdbFjo2NLVc/6urqcHR0REJCAvr37w8AkEqlSEhIgJ+fX4ltnj59qpAQUVVVBQDIZDIlr4SIiIiIiKh6SaVSGBkZ4auvvoKqqiocHR2RnZ2N1atXV1uiojbEQERERERU2yidLGnUqBEGDRpUKScXi8UYNWoUnJyc4OzsjPDwcEgkEmGtXR8fH5iZmSEkJAQA4O3tjbCwMDg4OMDFxQXp6ekICgqCt7e3kDQhIiIiIiKqDhWZLW9qago1NTW5v1+sra2Rm5uLwsJCqKur17kYiIiIiIjeBkolS16+fAkPDw9079691P94K2Po0KG4c+cOFixYgNzcXNjb22P//v3CFPKsrCy5mSTz58+HSCTC/PnzkZ2dDUNDQ3h7e2PZsmX/ORYiIiIiIiJlVGS2fOfOnbF161ZIpVLhb52rV6/C1NS0QkmK2hADEREREdHbQKkN3hs0aICJEyeioKCg0gLw8/PDzZs3UVBQgFOnTsHFxUU4lpiYiJiYGLnzBwcHIz09Hc+ePUNWVhYiIiLQqFGjSouHiIiIiIiovMRiMaKiorB582akpqZi0qRJCrPlAwMDhfqTJk3C/fv3MW3aNFy9ehVxcXFYvnw5pkyZUqdjICIiIiKq65RehsvZ2Rnnz59Hy5YtqyIeIiIiIiKiOkPZ2fLm5uY4cOAAZsyYAVtbW5iZmWHatGmYO3dunY6BiIiIiKiuUzpZMnnyZMycORO3bt2Co6Ojwgbvtra2lRYcERERERFRbefn51fqkleJiYkKZa6urjh58uRbFwMRERERUV2m1DJcAPDxxx/jxo0b8Pf3R+fOnWFvbw8HBwfhX6K6TENDC6ExZxAacwYaGlo1HQ4RERERERERERESExMhEonw8OHDaj93TExMpWyDYGFhgfDwcKXaZGZmQiQSISUl5T+fn+hNlJ5ZcuPGjaqIg4iIiIiIiIiIiKhSfHp0a7We78v3h1dp/25ubsjJyUHDhg3fWDcxMREeHh548OBBte317O7ujiNHjiiU9+rVC3FxcRXu19zcHDk5OTAwMPgv4QliYmIwffr0aks6ubu7w97eXukkUUkSExMhFovx559/wtzcHPPnz8fo0aNLrf/8+XNMnDgRycnJSE1NRZ8+fbBr167/HMfbTOlkCfcqISIiIiIiIiIiIqo+6urqMDExqdQ+CwsLoa6uXil9xcbGorCwUHh979492NnZYfDgwf+pX1VV1Uq/7vKozHtTGW7cuIHevXtj4sSJ2LJlCxISEjBu3DiYmprCy8urxDZFRUXQ0tKCv78/du7cWc0R101KL8MFABkZGZg6dSo8PT3h6ekJf39/ZGRkVHZsREREVIMiIiJgYWEBTU1NuLi44PTp02XWf/jwIaZMmQJTU1NoaGjA0tISe/furaZoiYiIiGqH3NXHyvXICz8htMkLP1HudkT0dnB3d8fUqVMxffp0NG7cGMbGxoiKioJEIoGvry/09PTQtm1b7Nu3D4DiMlw3b96Et7c3GjduDB0dHXTo0AF79+5FZmYmPDw8AACNGzeGSCQSZh+4u7vDz88P06dPh4GBgfAhe1hYGDp27AgdHR2Ym5tj8uTJyM/PV+p6mjRpAhMTE+ERHx8PbW1thWTJkydPMGzYMOjo6MDMzAwRERFl9vvvZbiK70NCQgKcnJygra0NNzc3pKWlCW0uXLgADw8P6OnpQV9fH46Ojjh79iwSExPh6+uLR48eQSQSQSQSYeHChQBeLRG2ZMkS+Pj4QF9fHxMmTChx6bOUlBSIRCJkZmYKZcePH4e7uzu0tbXRuHFjeHl54cGDBxg9ejSOHDmCtWvXCud7vV2xr776Cs2aNYNUKpUr79evH8aMGQMAiIyMRKtWrRAaGgpra2v4+fnho48+wpo1a0q9dzo6Oti4cSPGjx9fIwmnukjpZMmBAwdgY2OD06dPw9bWFra2tjh16hQ6dOiA+Pj4qoiRiIiIqtn27dshFosRHByMc+fOwc7ODl5eXrh9+3aJ9QsLC9GtWzdkZmbip59+QlpaGqKiomBmZlbNkRMREREREdUNmzdvhoGBAU6fPo2pU6di0qRJGDx4MNzc3HDu3Dl0794dI0eOxNOnTxXaTpkyBQUFBfj9999x6dIlrFy5Erq6ujA3NxdmEaSlpSEnJwdr166VO6e6ujqOHz+OyMhIAICKigrWrVuHP//8E5s3b8ahQ4cwZ86c/3RtmzZtwscffwwdHR258tWrV8POzg7nz59HQEAApk2bVqHPlOfNm4fQ0FCcPXsWDRo0EJIKADBixAg0b94cZ86cQXJyMgICAqCmpgY3NzeEh4dDX18fOTk5yMnJwaxZs4R2n3/+uRBbUFBQueJISUnBhx9+CBsbGyQlJeHYsWPw9vZGUVER1q5dC1dXV4wfP144n7m5uUIfgwcPxr1793D48GGh7P79+9i/fz9GjBgBAEhKSoKnp6dcOy8vLyQlJSl136hsSi/DFRAQgBkzZmDFihUK5XPnzkW3bt0qLTgiIiKqGWFhYRg/fjx8fX0BvBrFEhcXh+joaAQEBCjUj46Oxv3793HixAmoqakBeDUyh4ioPpNIJNDV1QUA5OfnK3xYUF9iICIiopLZ2dlh/vz5AIDAwECsWLECBgYGGD9+PABgwYIF2LhxIy5evKjQNisrC4MGDULHjh0BAK1btxaONWnSBABgZGSksGdJu3btsGrVKrmy6dOnC88tLCywdOlSTJw4ERs2bKjQdZ0+fRp//PEHNm3apHCsc+fOwt+UlpaWOH78ONasWaP0Z8rLli1D165dAbz6XLp37954/vw5NDU1kZWVhdmzZ6N9+/YAXl1zsYYNG0IkEpU40+J///sfZs6cKbz+66+/3hjHqlWr4OTkJHevOnToIDxXV1eHtrZ2mTM7GjdujJ49e2Lr1q348MMPAQA//fQTDAwMhFlCubm5MDY2lmtnbGyMx48f49mzZ9DS0npjrPRmSs8sSU1NxdixYxXKx4wZg8uXL1dKUERERFRzCgsLkZycLDdqRUVFBZ6enqWOWtm9ezdcXV0xZcoUGBsb45133sHy5ctRVFRUXWETERERERHVKba2tsJzVVVVNG3aVEh+ABA+HC9phr+/vz+WLl2Kzp07Izg4uMSESkkcHR0Vyn777Td8+OGHMDMzg56eHkaOHIl79+6VOKMlKysLurq6wmP58uUKdTZt2oSOHTvC2dlZ4Zirq6vC69TUVADAxIkT5fouy+v3ztTUFMA/90ksFmPcuHHw9PTEihUryr19hJOTU7nqva54ZokyOnToIFxjz549AbyaDbNz504UFBQAALZs2YKPP/4YKioV2kWDKkjpmSWGhoZISUmRy8gBr74xjIyMKi0wIqKq9PfxstfELPb0WYHwPCfpS2hraZSrXbPOUyoUF1FtcPfuXRQVFZU4auXKlSsltrl+/ToOHTqEESNGYO/evUhPT8fkyZPx4sULBAcHV0fYREREREREdUrxrPxiIpFIrkwkEgGAwl4WADBu3Dh4eXkhLi4OBw8eREhICEJDQzF16tQyz/nvWaaZmZno06cPJk2ahGXLlqFJkyY4duwYxo4di8LCQmhra8vVb9asmbB/CPDPLJZiEokE27Ztw+LFi8uMoySLFy+WWxarLGXdp4ULF2L48OGIi4vDvn37EBwcjG3btmHAgAFl9vnve1OcqJDJZELZixcv5OpUZEbH3r17hX6K23t7e0MmkyEuLg7vvvsujh49KrcfiYmJCfLy8uT6ycvLg76+PmeVVCKlkyXjx4/HhAkTcP36dbi5uQF4tYnNypUrIRaLKz1AIiIiqv2kUimMjIzw1VdfQVVVFY6OjsjOzsbq1auZLCEiIiIiIqoC5ubmmDhxIiZOnIjAwEBERUVh6tSpUFdXB4ByzfRPTk6GVCpFaGiokBz48ccfS63foEEDtG3bttTjO3bsQEFBAT755JMSj588eVLhtbW1NYBXy4ZV1mB8S0tLWFpaYsaMGRg2bBi++eYbDBgwAOrq6uVeAcHQ0BAAkJOTg8aNGwOAXKIIeDXDJSEhAYsWLSqxj5LO17JlS4V6mpqaGDhwILZs2YL09HRYWVmhU6dOwnFXV1fs3btXrk18fLzCTB36b5SexxMUFIQFCxbgiy++QNeuXdG1a1esX78eCxcuFNbYIyIiorrLwMAAqqqqJY5aKW2dVVNTU1haWkJVVVUos7a2Rm5uLgoLC6s0XiIiIiIiovpm+vTpOHDgAG7cuIFz587h8OHDQtKhZcuWEIlE2LNnD+7cuYP8/PxS+2nbti1evHiBL774AtevX8d3330nbPxeEZs2bUL//v3RtGnTEo8fP34cq1atwtWrVxEREYEdO3Zg2rRpFT7fvz179gx+fn5ITEzEzZs3cfz4cZw5c0a4NxYWFsjPz0dCQgLu3r1b4lJjxdq2bQtzc3MsXLgQ165dQ1xcHEJDQ+XqBAYG4syZM5g8eTIuXryIK1euYOPGjbh7965wvlOnTiEzMxN3794tcZZQsREjRgh7hRZv7F5s4sSJuH79OubMmYMrV65gw4YN+PHHHzFjxgyhzvr16xWWBLt8+TJSUlJw//59PHr0CCkpKQoJH/qH0skSkUiEGTNm4NatW3j06BEePXqEW7duYdq0acKUJyIiIqq71NXV4ejoiISEBKFMKpUiISGh1FErnTt3Rnp6utx//K5evQpTU1NhVBMRERERERFVjqKiIkyZMgXW1tbo0aMHLC0thU3GzczMsGjRIgQEBMDY2Bh+fn6l9mNnZ4ewsDCsXLkS77zzDrZs2YKQkJAKxZSWliYs4VWamTNn4uzZs3BwcMDSpUsRFhYGLy+vCp2vJKqqqrh37x58fHxgaWmJIUOGoGfPnsLMDzc3N0ycOBFDhw6FoaGhwmb3r1NTU8MPP/yAK1euwNbWFitXrsTSpUvl6lhaWuLgwYO4cOECnJ2d4erqil9++QUNGrxa0GnWrFlQVVWFjY0NDA0NkZWVVer5/ve//6FJkyZIS0vD8OHD5Y61atUKcXFxiI+Ph52dHUJDQ/H111/L3bu7d+8q7M/Sq1cvODg44Ndff0ViYiIcHBzg4OBQvptZD5V7Ga5nz54hPj4eHh4e0NPTAwDh38ePHyMxMRFeXl7Q0Cjfev5ERERUe4nFYowaNQpOTk5wdnZGeHg4JBIJfH19AQA+Pj4wMzMT/hM9adIkrF+/HtOmTcPUqVNx7do1LF++HP7+/jV5GUREREREVE99+f7wN1eqQYmJiQplmZmZCmWv75fx+vMvvviizP6DgoIQFBT0xnMCwIwZM+RmKADAyJEjheejR4/G6NGjyzwfAFhZWcnF+G8lXd+bWFhYyPXp7u6ucA57e3u5sh9++KHMPjdu3IiNGzeWK7bOnTvj4sWLcmX/Pn/Xrl1x/PjxEttbWloiKSmpzHiKqaio4O+//y71uLu7O86fP1/q8YULF2LhwoVyZRW55/VZuZMlX331FXbv3o2+ffsqHNPX18e6devw119/YcoUbmpMRERU1w0dOhR37tzBggULkJubC3t7e+zfv1/Y9D0rK0tYzxZ4tVbugQMHMGPGDNja2sLMzAzTpk3D3Llza+oSiIiIiIiIiIjKrdzJki1btihkI183ffp0LF68mMkSIiKit4Sfn1+p07VLGpHk6uqqsFkfEREREREREVFdUO49S65duwY7O7tSj9va2uLatWuVEhQREREREREREREREVF1KffMkpcvX+LOnTto0aJFicfv3LmDly9fVlpgRERERERERESVTUNDC6ExZ2o6DCIiIqplyj2zpEOHDvjtt99KPX7w4EF06NChUoIiIiIiIiIiIiIiIiKqLuVOlowZMwZLlizBnj17FI79+uuvWLZsGcaMGVOpwREREREREREREREREVW1ci/DNWHCBPz+++/o27cv2rdvDysrKwDAlStXcPXqVQwZMgQTJkyoskCJiIiIiIiIiIiIiIiqQrmTJQDw/fffo2/fvti6dSuuXr0KmUwGKysrLFq0CEOGDKmqGImIiKgWkUgk0NXVBQDk5+dDR0enhiMiqj4RERFYvXo1cnNzYWdnhy+++ALOzs4l1o2JiYGvr69cmYaGBp4/f/7WxEFEVKwobGz56hW8+Of5ukko0lArVztV8aYKxVVf/ZA2uFz1nj/9Z+/ZH69+Ak3t8n1MNMxqR4XiIiIiqs2USpYAwJAhQ5gYISIiIqJ6Z/v27RCLxYiMjISLiwvCw8Ph5eWFtLQ0GBkZldhGX18faWlpwmuRSPTWxEFERERERPQ2KfeeJURERERE9VlYWBjGjx8PX19f2NjYIDIyEtra2oiOji61jUgkgomJifAwNjZ+a+IgIiIioqqRmZkJkUiElJSUKj+XhYUFwsPDq/w8RHWB0jNLiIj+s6v25av3tOif59feA7RVy9fOMkXZiIiIap2/j0eUq97TZwXC85ykL6GtpVGuds06T6lQXPVVYWEhkpOTERgYKJSpqKjA09MTSUlJpbbLz89Hy5YtIZVK0alTJyxfvhwdOnSo83HUlNzVx8pV72nhM+F5XvgJaKtrlaudyewuFYqLiIiIap/yLg9YWerzcoFRUVH49ttv8ccffwAAHB0dsXz58lKXiQWAnJwczJw5E2fPnkV6ejr8/f2ZtKEax5klRERERERvcPfuXRQVFSnMyDA2NkZubm6JbaysrBAdHY1ffvkF33//PaRSKdzc3HDr1q06HwcRERERUbHExEQMGzYMhw8fRlJSEszNzdG9e3dkZ2eX2qagoACGhoaYP38+7OzsqjFaotIxWUJEREREVAVcXV3h4+MDe3t7dO3aFbGxsTA0NMSXX35ZL+MgIiIiInlSqRSrVq1C27ZtoaGhgRYtWmDZsmUK9YqKijB27Fi0atUKWlpasLKywtq1a+XquLu7Y/r06XJl/fv3x+jRo4XXt2/fhre3N7S0tNCqVSts2bJF4VwPHz7EuHHjYGhoCH19ffzvf//DhQsXyryOLVu2YPLkybC3t0f79u3x9ddfQyqVIiEhodQ2FhYWWLt2LXx8fNCwYcMy+yeqLlyGi4iIiIjoDQwMDKCqqoq8vDy58ry8PJiYmJSrDzU1NTg4OCA9Pb3Ox0FERERE/11gYCCioqKwZs0adOnSBTk5Obhy5YpCPalUiubNm2PHjh1o2rQpTpw4gQkTJsDU1BRDhgwp9/lGjx6Nv//+G4cPH4aamhr8/f1x+/ZtuTqDBw+GlpYW9u3bh4YNG+LLL7/Ehx9+iKtXr6JJkyblOs/Tp0/x4sWLctcnqi3KlSwZOHBguTuMjY2tcDBERERERLWRuro6HB0dkZCQgP79+wOAMFrOz8+vXH0UFRXh0qVL6NWrV52Pg4iIiIj+mydPnmDt2rVYv349Ro0aBQBo06YNunTpgszMTLm6ampqWLRokfC6VatWSEpKwo8//ljuZMnVq1exb98+nD59Gu+++y4AYNOmTbC2thbqHDt2DKdPn8bt27ehofFqL8TPP/8cu3btwk8//YQJEyaU61xz585Fs2bN4OnpWa76RLVFuZIlr0+Fkslk+Pnnn9GwYUM4OTkBAJKTk/Hw4UOlkipERERERHWJWCzGqFGj4OTkBGdnZ4SHh0MikcDX1xcA4OPjAzMzM4SEhAAAFi9ejPfeew9t27bFw4cPsXr1aty8eRPjxo17K+IgIiIioopLTU1FQUEBPvzww3LVj4iIQHR0NLKysvDs2TMUFhbC3t5eqfM1aNAAjo6OQln79u3RqFEj4fWFCxeQn5+Ppk2byrV99uwZMjIykJWVBRsbG6H8s88+w2effSZXd8WKFdi2bRsSExOhqalZ7viIaoNyJUu++eYb4fncuXMxZMgQREZGQlVVFcCr0WmTJ0+Gvr5+1URJRERERFTDhg4dijt37mDBggXIzc2Fvb099u/fL2y2npWVBRWVf7YEfPDgAcaPH4/c3Fw0btwYjo6OOHHihNwfmHU5DiIiIiKqOC0trXLX3bZtG2bNmoXQ0FC4urpCT08Pq1evxqlTp4Q6KioqkMlkcu1evHihVEz5+fkwNTVFYmKiwrFGjRqhUaNGSElJEcr+vczW559/jhUrVuC3336Dra2tUucmqg2U3rMkOjoax44dExIlAKCqqgqxWAw3NzesXr26UgMkIiIiIqot/Pz8Sl3u6t9/VK5ZswZr1qx5q+MgIiIioopp164dtLS0kJCQ8MYZv8ePH4ebmxsmT54slGVkZMjVMTQ0RE5OjvC6qKgIf/zxBzw8PAC8mkXy8uVLJCcnC8twpaWl4eHDh0KbTp06ITc3Fw0aNICFhUWJsbRt27bE8lWrVmHZsmU4cOCAsBoRUV2j8uYq8l6+fFniRkNXrlyBVCqtlKCIiIiIiIiIiIiI3laampqYO3cu5syZg2+//RYZGRk4efIkNm3apFC3Xbt2OHv2LA4cOICrV68iKCgIZ86ckavzv//9D3FxcYiLi8OVK1cwadIkuUSIlZUVevTogU8//RSnTp1CcnIyxo0bJzfDxdPTE66urujfvz8OHjyIzMxMnDhxAvPmzcPZs2dLvZaVK1ciKCgI0dHRsLCwQG5uLnJzc5Gfny/UCQwMhI+Pj1y7lJQUpKSkID8/H3fu3EFKSgouX76s7K0kqjRKzyzx9fXF2LFjkZGRAWdnZwDAqVOnsGLFCmGdZCIiIiIiqp80NLQQGnPmzRWJiIiI6rmgoCA0aNAACxYswN9//w1TU1NMnDhRod6nn36K8+fPY+jQoRCJRBg2bBgmT56Mffv2CXXGjBmDCxcuwMfHBw0aNMCMGTOEWSXFvvnmG4wbNw5du3aFsbExli5diqCgIOG4SCTC3r17MW/ePPj6+uLOnTswMTHBBx98ICz5WpKNGzeisLAQH330kVx5cHAwFi5cCADIyclBVlaW3HEHBwfheXJyMrZu3YqWLVsqbHBPVF2UTpZ8/vnnMDExQWhoqDC1y9TUFLNnz8bMmTMrPUAiIiIiIiIiIiIiZaiKFWdo1DYqKiqYN28e5s2bp3Ds9f1HNDQ08M0338jtKw0AISEhwnM1NTVs2LABGzZsKPV8JiYm2LNnj1zZyJEj5V7r6elh3bp1WLduXbmvozzJjZiYGIWyf++xQlTTlE6WqKioYM6cOZgzZw4eP34MANzYnYiIiIiIiIhICdrqWshZdbSmwyAiIqL/p/SeJcCrfUt+++03/PDDDxCJRACAv//+W24dOiIiIqq4iIgIWFhYQFNTEy4uLjh9+nSpdWNiYiASieQempqa1RgtEREREREREVHdpvTMkps3b6JHjx7IyspCQUEBunXrBj09PaxcuRIFBQWIjIysijiJiIjqje3bt0MsFiMyMhIuLi4IDw+Hl5cX0tLSYGRkVGIbfX19pKWlCa+LBzMQEREREREREdGbKT2zZNq0aXBycsKDBw+gpaUllA8YMAAJCQmVGhwREVF9FBYWhvHjx8PX1xc2NjaIjIyEtrY2oqOjS20jEolgYmIiPMrafI+IKp9EIhFmdkkkknofBxERERERUV2j9MySo0eP4sSJE1BXV5crt7CwQHZ2dqUFRkRUG2hraSD72PqaDoPqkcLCQiQnJyMwMFAoU1FRgaenJ5KSkkptl5+fj5YtW0IqlaJTp05Yvnw5OnToUB0hExERERERERHVeUrPLJFKpSgqKlIov3XrFvT09ColKCIiovrq7t27KCoqUpgZYmxsjNzc3BLbWFlZITo6Gr/88gu+//57SKVSuLm54datW9URMhERERERERFRnad0sqR79+4IDw8XXotEIuTn5yM4OBi9evWqzNiIiIioHFxdXeHj4wN7e3t07doVsbGxMDQ0xJdfflnToRERERERERER1QlKL8P1+eefo0ePHrCxscHz588xfPhwXLt2DQYGBvjhhx+qIkYiIqJ6w8DAAKqqqsjLy5Mrz8vLg4mJSbn6UFNTg4ODA9LT06siRCIiIiIiIiKit47SM0vMzc1x4cIFzJs3DzNmzICDgwNWrFiB8+fPw8jIqCpiJCIiqjfU1dXh6OiIhIQEoUwqlSIhIQGurq7l6qOoqAiXLl2CqalpVYVJRERERERERPRWUSpZ8uLFC7Rp0wbXrl3DiBEjsGrVKmzYsAHjxo2DlpZWVcVIRERUr4jFYkRFRWHz5s1ITU3FpEmTIJFI4OvrCwDw8fGR2wB+8eLFOHjwIK5fv45z587hk08+wc2bNzFu3LiaugQiIiIiIiKiSmFhYSG3LUR9cu/ePRgZGSEzM1MoO378ODp27Ag1NTX079+/xmIDgNGjR1drDPv374e9vT2kUmmV9K/UMlxqamp4/vx5lQRCRERErwwdOhR37tzBggULkJubC3t7e+zfv1/Y9D0rKwsqKv+Md3jw4AHGjx+P3NxcNG7cGI6Ojjhx4gRsbGxq6hKIiIiIiIhqVNjms9V6PvEop2o9XzGRSISff/75jR9Yx8bGYvny5UhPT8eLFy/Qrl07zJw5EyNHjiy1TWJiIjw8PBTKc3Jyylwm2sLCAtOnT8f06dPLexk15uLFi5gyZQrOnDkDQ0NDTJ06FXPmzJGr8/DhQ8ybNw+xsbG4f/8+WrZsifDwcGH/7t9//x2rV69GcnIycnJySvx6LFy4ENu2bcNff/0lrCixbNkyuLi4lBnfsmXL0K9fP1hYWAhlYrEY9vb22LdvH3R1dSvlPrxJZmYmWrVqhfPnz8Pe3l4oX7t2LWQyWbXEAAA9evRAUFAQtmzZUub3bkUpvWfJlClTsHLlSnz99ddo0EDp5kRERFQOfn5+8PPzK/FYYmKi3Os1a9ZgzZo11RAVERERERER1UVNmjTBvHnz0L59e6irq2PPnj3w9fWFkZERvLy8ymyblpYGfX194XV1bcVQWFgIdXX1Kuv/8ePH6N69Ozw9PREZGYlLly5hzJgxaNSoESZMmCDE0K1bNxgZGeGnn36CmZkZbt68iUaNGgn9SCQS2NnZYcyYMRg4cGCJ57K0tMT69evRunVrPHv2DGvWrEH37t2Rnp4OQ0PDEts8ffoUmzZtwoEDB+TKMzIyMHHiRDRv3rxybsR/0LBhw2o/5+jRo7Fu3boqSZYovWfJmTNnEBsbixYtWsDLywsDBw6UexARERERERERERFR6Z48eYIRI0ZAR0cHpqamWLNmDdzd3eVmY1hYWGDJkiUYNmwYdHR0YGZmhoiICLnjADBgwACIRCK52Qf/5u7ujgEDBsDa2hpt2rTBtGnTYGtri2PHjr0xViMjI5iYmAiP11c6KOk8N2/exIwZMyASiSASiQC8mlnx+owEAAgPD5eLuXhJp2XLlqFZs2awsrKSu1+l3Qfg1QoM/fr1g66uLvT19TFkyBDk5eWVeV1btmxBYWEhoqOj0aFDB3z88cfw9/dHWFiYUCc6Ohr379/Hrl270LlzZ1hYWKBr166ws7MT6vTs2RNLly7FgAEDSj3X8OHD4enpidatW6NDhw4ICwvD48ePcfHixVLb7N27FxoaGnjvvfcAvJrdIRKJcO/ePYwZMwYikQgxMTGIiYmRS94AwK5du4R7D/xz/7/77jtYWFigYcOG+Pjjj/HkyROhjlQqxapVq9C2bVtoaGigRYsWWLZsGQCgVatWAAAHBweIRCK4u7sDUFyGq6CgAP7+/jAyMoKmpia6dOmCM2fOCMcTExMhEomQkJAAJycnaGtrw83NDWlpaUKdCxcuwMPDA3p6etDX14ejoyPOnv1nppi3tzfOnj2LjIyMUu9dRSmdLGnUqBEGDRoELy8vNGvWDA0bNpR7EBEREREREREREVHpxGIxjh8/jt27dyM+Ph5Hjx7FuXPnFOqtXr0adnZ2OH/+PAICAjBt2jTEx8cDgPAh9DfffIOcnBy5D6XLIpPJkJCQgLS0NHzwwQdvrG9vbw9TU1N069YNx48fL7NubGwsmjdvjsWLFyMnJwc5OTnliqlYcVzx8fHYs2ePUF7WfZBKpejXrx/u37+PI0eOID4+HtevX8fQoUPLPFdSUhI++OADudkrXl5eSEtLw4MHDwAAu3fvhqurK6ZMmQJjY2O88847WL58OYqKipS6rtcVFhbiq6++QsOGDeWSLv929OhRODo6Cq/Nzc2Rk5MDfX19hIeHIycn543X+LqMjAzs2rULe/bswZ49e3DkyBGsWLFCOB4YGIgVK1YgKCgIly9fxtatW4XlwE+fPg0A+O2335CTk4PY2NgSzzFnzhzs3LkTmzdvxrlz59C2bVt4eXnh/v37cvXmzZuH0NBQnD17Fg0aNMCYMWOEYyNGjEDz5s1x5swZJCcnIyAgAGpqasLxFi1awNjYGEePHi33tZeX0utoffPNN5UeBBEREREREREREVF98OTJE2zevBlbt27Fhx9+CODVZ67NmjVTqNu5c2cEBAQAeLWU0/Hjx7FmzRp069ZNWL6pUaNGZe4hUuzRo0cwMzNDQUEBVFVVsWHDBnTr1q3U+qampoiMjISTkxMKCgrw9ddfw93dHadOnUKnTp1KbNOkSROoqqpCT0+vXDH9m46ODr7++muF5bfKug8JCQm4dOkSbty4AXNzcwDAt99+iw4dOuDMmTN49913SzxXbm6uMGOiWHFyoHhP0OvXr+PQoUMYMWIE9u7di/T0dEyePBkvXrxAcHCwUte2Z88efPzxx3j69ClMTU0RHx8PAwODUuvfvHlT7ntCVVUVJiYmEIlEaNiwodL3VyqVIiYmBnp6egCAkSNHIiEhAcuWLcOTJ0+wdu1arF+/HqNGjQIAtGnTBl26dAEA4XutadOmpZ5XIpFg48aNiImJQc+ePQEAUVFRiI+Px6ZNmzB79myh7rJly9C1a1cAQEBAAHr37o3nz59DU1MTWVlZmD17Ntq3bw8AaNeuncK5mjVrhps3byp1/eWh9MwSAHj58iV+++03fPnll8JUnb///hv5+fmVGhwRERERERERERHR2+T69et48eIFnJ2dhbKGDRvKLTtVzNXVVeF1ampqqX1nZWVBV1dXeCxfvlw4pqenh5SUFJw5cwbLli2DWCxW2BPzdVZWVvj000/h6OgINzc3REdHw83NTdgzc8uWLXLnqoyR/h07dixxn5Ky7kNqairMzc2FRAkA2NjYoFGjRkKdDh06CHEWf5BfHlKpFEZGRvjqq6/g6OiIoUOHYt68eYiMjFT62jw8PJCSkoITJ06gR48eGDJkCG7fvl1q/WfPnkFTU1Pp85TGwsJCSJQAr5JhxedPTU1FQUGBkLyriIyMDLx48QKdO3cWytTU1ODs7KzwPWtraysXBwAhFrFYjHHjxsHT0xMrVqwocbktLS0tPH36tMKxlkbpmSU3b95Ejx49kJWVhYKCAnTr1g16enpYuXIlCgoKKvSNQkRERERERERERET/TbNmzZCSkiK8btKkifBcRUUFbdu2BfBqaa3U1FSEhIQI+0+Uh7Ozs7DPSd++feHi4iIcMzMzK7WdiooKZDKZXNmLFy8U6uno6JQ7FmXs3btXOJ+WlhYAwMTERGFfk+LXxbMnTE1NoaamBlVVVaGOtbU1cnNzld6AXkdHB23btkXbtm3x3nvvoV27dti0aRMCAwNLrG9gYCAsB1aW8t7b15eyAgCRSASpVArgn3tSXV6PpXhvleJYFi5ciOHDhyMuLg779u1DcHAwtm3bJrcnzP3794XZLpVJ6Zkl06ZNg5OTEx48eCB3EwcMGICEhASlA4iIiICFhQU0NTXh4uIirH9WmocPH2LKlCkwNTWFhoYGLC0tsXfvXqXPS0REVBdJJBJhkzyJRFLT4RAREREpRUdDDS9Dx+Bl6BjoaKi9uQFVKU3tBth65SNsvfIRNLWVHk9LRBXUunVrqKmpye0x8ujRI1y9elWh7smTJxVeW1tbC6/V1NTk9s9o0KCB8IF827Zt5ZIl/yaVSlFQUKBU7CkpKcJMAD09PblzFX9WrK6urrCnh6GhIXJzc+U+1H89qfMmZd0Ha2tr/PXXX/jrr7+E45cvX8bDhw9hY2MDAGjZsqUQZ3FSx9XVFb///rtcYiE+Ph5WVlZo3LgxgFfLf6Wnpwsf5APA1atXYWpqqlSipCRvuv8ODg64fPnyG/sxNDTEkydP5D4jUObeAq+WutLS0ir18/3iay1rr5Y2bdpAXV1dbl+bFy9e4MyZM8LXobwsLS0xY8YMHDx4EAMHDpTbGuT58+fIyMiAg4ODUn2Wh9LJkqNHj2L+/PkK3wwWFhbIzs5Wqq/t27dDLBYjODgY586dg52dHby8vEqdflRYWIhu3bohMzMTP/30E9LS0hAVFVVm1pKIiIiIiIiqh7KD4Ypt27YNIpEI/fv3fytiICIiKouenh5GjRqF2bNn4/Dhw/jzzz8xduxYqKioCKPsix0/fhyrVq3C1atXERERgR07dmDatGnCcQsLCyQkJCA3N7fMWQghISHCxuepqakIDQ3Fd999h08++USoExgYCB8fH+F1eHg4fvnlF6Snp+OPP/7A9OnTcejQIUyZMqXM67OwsMDvv/+O7Oxs3L17FwDg7u6OO3fuYNWqVcjIyEBERAT27dtX7ntW1n3w9PREx44dMWLECJw7dw6nT5+Gj48PunbtCicnp1L7HD58ONTV1TF27Fj8+eef2L59O9auXQuxWCzUmTRpEu7fv49p06bh6tWriIuLw/Lly+XuQX5+PlJSUoQExY0bN5CSkoKsrCwArwY9fvbZZzh58iRu3ryJ5ORkjBkzBtnZ2Rg8eHCp8Xl5eeHPP/984+wSFxcXaGtr47PPPkNGRga2bt2KmJiYN91SOZqampg7dy7mzJmDb7/9FhkZGTh58iQ2bdoEADAyMoKWlhb279+PvLw8PHr0SKEPHR0dTJo0CbNnz8b+/ftx+fJljB8/Hk+fPsXYsWPLFcezZ8/g5+eHxMRE3Lx5E8ePH8eZM2fkEoQnT56EhoaGwtJslUHpZIlUKi0xg3Tr1i25Nc/KIywsDOPHj4evry9sbGwQGRkJbW1tREdHl1g/Ojoa9+/fx65du9C5c2dYWFiga9eusLOzU/YyiIiIiIiIqBIpOxiuWGZmJmbNmoX333//rYiBiIioPMLCwuDq6oo+ffrA09MTnTt3hrW1tcIeFTNnzsTZs2fh4OCApUuXIiwsDF5eXsLx0NBQxMfHw9zcvMyR9hKJBJMnT0aHDh3QuXNn7Ny5E99//z3GjRsn1MnJyRE+4AdeDVyfOXMmOnbsiK5du+LChQv47bff3rivxeLFi5GZmYk2bdoISyVZW1tjw4YNiIiIgJ2dHU6fPo1Zs2aV+36VdR9EIhF++eUXNG7cGB988AE8PT3RunVrbN++vcw+GzZsiIMHD+LGjRtwdHTEzJkzsWDBAkyYMEGoY25ujgMHDuDMmTOwtbWFv78/pk2bJmw2D0CIq/j+i8ViODg4YMGCBQBebcx+5coVDBo0CJaWlvD29sa9e/dw9OhRdOjQodT4OnbsiE6dOuHHH38s8zqaNGmC77//Hnv37kXHjh3xww8/YOHChWW2KUlQUJBwD6ytrTF06FDh/1ANGjTAunXr8OWXX6JZs2bo169fiX2sWLECgwYNwsiRI9GpUyekp6fjwIEDwkydN1FVVcW9e/fg4+MDS0tLDBkyBD179sSiRYuEOj/88ANGjBgBbW1tpa/xTUSyfy9o9gZDhw5Fw4YN8dVXX0FPTw8XL16EoaEh+vXrhxYtWshNiSlLYWEhtLW18dNPP8mN3Bk1ahQePnyIX375RaFNr1690KRJE2hra+OXX36BoaEhhg8fjrlz58qtG/e6goICuelMjx8/hrm5OR49egR9fX1lLp0qoCisfFnDilIVbypXvbDNZ6s0DvGo0rPUxXJXH6vSGExmd3ljnR/SSs9WV4ZhVjvKV/GqfbmqSZ4WQdfhDwBA/vl3oKNd8s+5AsuUN1b5+3hE+fqqoGadyx5lUWzPnj1VGkefPn2qtP+3QW15nyoviUQCXV1dAK9Gr1TVeq61PYb6oLzvU0+fFaBdt5kAgGvxodDW0ihXO75PVa7a8nNRlXHUpf9PPS18hjbzuwMAMpYehLZ6+dZgLs//p5RRG74vqjMGFxcXvPvuu1i/fj2AVwPtzM3NMXXqVLkPFF5XVFSEDz74AGPGjMHRo0fx8OFD7Nq1q07HUF/Vhv9T1Yb3KYB/+wnK+XdfhZXj7z6gdvztx/9P/XePHz9Gw4YN3+rP8yQSCczMzBAaGiqMwrewsMD06dMxffr0mg2OakxcXBxmz56NP/74AyoqSs97eOvcvXsXVlZWOHv2LFq1alXp/Su9IGVoaCi8vLxgY2OD58+fY/jw4bh27RoMDAzwww8/lLufu3fvoqioCMbGxnLlxsbGuHLlSoltrl+/jkOHDmHEiBHYu3cv0tPTMXnyZLx48QLBwcEltgkJCZHLPBEREVHJlPkQslhe+Ika+xCSiKimlPdDyOdPXwrPf7z6Sbn3A6jUDyGfvrYqwLX3gEocfPK6wsJCJCcny21QqqKiAk9PTyQlJZXabvHixTAyMsLYsWNx9OhRpc5ZG2MgIiIqr/Pnz+PKlStwdnbGo0ePsHjxYgAodcQ+1U+9e/fGtWvXkJ2dDXNz85oOp8ZlZmZiw4YNVZIoASqQLGnevDkuXLiAbdu24eLFi8jPz8fYsWMxYsQIuQ3fq4JUKoWRkRG++uorqKqqwtHREdnZ2Vi9enWpyZLAwEC5deaKZ5YQUe2no60KWRqX2SMiKou2lgayj62v6TCIqJ6ryGC4Y8eOYdOmTUpvQFqbYyAiIlLG559/jrS0NKirq8PR0RFHjx6FgYFBTYdFtQxnFv3DycmpzH1o/iulkyXAqzXKXt/8pyIMDAygqqqKvLw8ufK8vDyYmJiU2MbU1BRqampyS25ZW1sjNzcXhYWFCpvOA4CGhgY0NMq3HAURERERERFVvSdPnmDkyJGIioqqsQ+FakMMRERUfzk4OCA5ObnMOpmZmdUTDBEBqECypEWLFnB3d0fXrl3h4eGB1q1bV+jExRnThIQEYc8SqVSKhIQE+Pn5ldimc+fO2Lp1K6RSqbBG29WrV2FqalpiooSIiIiIiIiqnrKD4TIyMpCZmQlvb2+hTCqVAng1OC8tLQ1t2rSpczEQERERUd2l9K4wy5cvh6amJlauXIm2bdvC3Nwcn3zyCaKionDt2jWl+hKLxYiKisLmzZuRmpqKSZMmQSKRwNfXFwDg4+Mjt97spEmTcP/+fUybNg1Xr15FXFwcli9fjilTyrdBKREREREREVW+1wfDFSseDOfq6qpQv3379rh06RJSUlKER9++feHh4YGUlJQKLZ1cG2IgIiIiorpL6Zkln3zyibAEV05ODo4cOYI9e/Zg8uTJkEqlKCoqekMP/xg6dCju3LmDBQsWIDc3F/b29ti/f7+wxmxWVpYwgwQAzM3NceDAAcyYMQO2trYwMzPDtGnTMHfuXGUvg4iIiIiIiCqRWCzGqFGj4OTkBGdnZ4SHhysMhjMzM0NISAg0NTXxzjvvyLVv1KgRACiU17UYiIiIiKhuqtCeJU+fPsWxY8eQmJiIw4cP4/z583jnnXfg7u6udF9+fn6lLruVmJioUObq6oqTJ08qfR4iIiIiIiKqOsoOhntbYyAiIiKiuknpZImbmxvOnz8Pa2truLu7IyAgAB988AEaN25cFfERERERERFRHaHsYLjXxcTEvDUxEBEREVHdo/SQmitXrkBHRwft27dH+/btYW1tzUQJERERERERERERERHVWUonS+7du4dDhw7hvffew4EDB9C5c2eYmZlh+PDhiIqKqooYiYiIiIiIiIiIiKgesrCwQHh4eE2HUSMKCwvRtm1bnDhxosrPlZiYCJFIhIcPH1b5uSrivffew86dO6v0HEovwyUSiWBrawtbW1tMnToVycnJWL9+PbZs2YLt27dj/PjxVREnERERERERERERUbnkrj5Wreczmd2lWs9XTCQS4eeff0b//v3LrBcbG4vly5cjPT0dL168QLt27TBz5kyMHDmy1DaJiYnw8PBQKM/JyYGJiUmp7SwsLDB9+nRMnz69vJdRI54/f46JEyciOTkZqamp6NOnD3bt2iVXJycnBzNnzsTZs2eRnp4Of3//EhM3O3bsQFBQEDIzM9GuXTusXLkSvXr1kquTmpqKuXPn4siRI3j58iVsbGywc+dOtGjRotQYIyMj0apVK7i5uVXGJZfJzc0NOTk5aNiw4RvrFn9vPHjwAI0aNarUOGJiYjB9+nSFpM38+fMxY8YMDBgwoMr2oFO613PnziEsLAx9+/ZF06ZN4erqiosXL2Lq1KmIjY2tihiJiIiIiIiIiIiIqIKaNGmCefPmISkpCRcvXoSvry98fX1x4MCBN7ZNS0tDTk6O8DAyMqqGiF/NqqhKRUVF0NLSgr+/Pzw9PUusU1BQAENDQ8yfPx92dnYl1jlx4gSGDRuGsWPH4vz58+jfvz/69++PP/74Q6iTkZGBLl26oH379khMTMTFixcRFBQETU3NUuOTyWRYv349xo4d+98utJzU1dVhYmICkUhULedTVs+ePfHkyRPs27evys6hdLLE2dkZW7duhaWlJTZv3oy7d+8KCZR+/fpVRYxERERENSoiIgIWFhbQ1NSEi4sLTp8+Xa5227Ztg0gkeuMoLyIiIiIiql+ePHmCESNGQEdHB6amplizZg3c3d3lZmNYWFhgyZIlGDZsGHR0dGBmZoaIiAi54wAwYMAAiEQi4XVJ3N3dMWDAAFhbW6NNmzaYNm0abG1tcezYm2fgGBkZwcTERHiUNarf3d0dN2/exIwZMyASiYQP3hcuXAh7e3u5uuHh4XIxjx49Gv3798eyZcvQrFkzWFlZyd2v0u4DAGRlZaFfv37Q1dWFvr4+hgwZgry8vDKvS0dHBxs3bsT48eNLnSljYWGBtWvXwsfHp9QZF2vXrkWPHj0we/ZsWFtbY8mSJejUqRPWr18v1Jk3bx569eqFVatWwcHBAW3atEHfvn3LTDwlJycjIyMDvXv3liufO3cuLC0toa2tjdatWyMoKAgvXrwQjl+4cAEeHh7Q09ODvr4+HB0dcfbsWQDAzZs34e3tjcaNG0NHRwcdOnTA3r17ASguw1Va3czMTGHGUePGjSESiTB69GgAwP79+9GlSxc0atQITZs2RZ8+fZCRkSHElpmZCZFIhNjYWHh4eEBbWxt2dnZISkoSYvD19cWjR4+E75+FCxcCAFRVVdGrVy9s27at1Hv2XymdLLl//z7Onj2Lzz//HN7e3uWalkNERERUV23fvh1isRjBwcE4d+4c7Ozs4OXlhdu3b5fZLjMzE7NmzcL7779fTZESEREREVFdIRaLcfz4cezevRvx8fE4evQozp07p1Bv9erVsLOzw/nz5xEQEIBp06YhPj4eAHDmzBkAwDfffIOcnBzh9ZvIZDIkJCQgLS0NH3zwwRvr29vbw9TUFN26dcPx48fLrBsbG4vmzZtj8eLFwkwUZRTHFR8fjz179gjlZd0HqVSKfv364f79+zhy5Aji4+Nx/fp1DB06VKlzV1RSUpLCzBQvLy8hASCVShEXFwdLS0t4eXnByMgILi4uCkt+/dvRo0dhaWkJPT09uXI9PT3ExMTg8uXLWLt2LaKiorBmzRrh+IgRI9C8eXOcOXMGycnJCAgIgJqaGgBgypQpKCgowO+//45Lly5h5cqV0NXVLfH8pdU1NzcX9g4pnnW0du1aAIBEIoFYLMbZs2eRkJAAFRUVDBgwAFKpVK7vefPmYdasWUhJSYGlpSWGDRuGly9fws3NDeHh4dDX1xe+f2bNmiW0c3Z2xtGjR8u8b/+F0nuWPHr0CI8fP0bz5s0BAKdPn8bWrVthY2ODCRMmVHqARERERDUpLCwM48ePh6+vL4BXa8bGxcUhOjoaAQEBJbYpKirCiBEjsGjRIhw9erTWbpBH9LbSVtdCzqqq+yOKlCeRSIQ/xPPz86Gjo1MvYyAiIgJezZLYvHkztm7dig8//BDAq4RHs2bNFOp27txZ+LvD0tISx48fx5o1a9CtWzcYGhoCABo1alTmHiLFHj16BDMzMxQUFEBVVRUbNmxAt27dSq1vamqKyMhIODk5oaCgAF9//TXc3d1x6tQpdOrUqcQ2TZo0gaqqKvT09MoV07/p6Ojg66+/hrq6ulx5WfchISEBly5dwo0bN2Bubg4A+Pbbb9GhQwecOXMG7777rtJxKCM3NxfGxsZyZcbGxsjNzQUA3L59G/n5+VixYgWWLl2KlStXYv/+/Rg4cCAOHz6Mrl27ltjvzZs3S/yemD9/vvDcwsICs2bNwrZt2zBnzhwAr2bZzJ49G+3btwcAtGvXTqiflZWFQYMGoWPHjgCA1q1bl3pdZdVt0qQJgFezjl7fs2TQoEFyfURHR8PQ0BCXL1/GO++8I5TPmjVLmDGzaNEidOjQAenp6Wjfvj0aNmwIkUhU4vdPs2bN8Ndff0EqlVbJviVK9zh8+HAcPnwYwKtvhG7duuH06dOYN28eFi9eXOkBEhEREdWUwsJCJCcny40SUlFRgaenpzBKqCSLFy+GkZFRta0tS0REREREdcf169fx4sULODs7C2UNGzaUW3aqmKurq8Lr1NTUUvvOysqCrq6u8Fi+fLlwTE9PDykpKThz5gyWLVsGsViMxMTEUvuysrLCp59+CkdHR7i5uSE6Ohpubm7CLIYtW7bInasyRvx37NhRIVEClH0fUlNTYW5uLiRKAMDGxgaNGjUS6nTo0EGIs2fPnv85TmUUz6ro168fZsyYAXt7ewQEBKBPnz6IjIwstd2zZ89K3NNk+/bt6Ny5M0xMTKCrq4v58+cjKytLOC4WizFu3Dh4enpixYoVcstg+fv7Y+nSpejcuTOCg4Nx8eLFUs+vTN1i165dw7Bhw9C6dWvo6+sLy6y9Hh8A2NraCs9NTU0B4I2rNwCAlpYWpFIpCgoK3li3IpROlvzxxx/CD/KPP/6Id955BydOnMCWLVsQExNT2fERERER1Zi7d++iqKiozFFC/3bs2DFs2rQJUVFR1REiERERERGRoFmzZkhJSREeEydOFI6pqKigbdu2sLe3x8yZM/HRRx8hJCREqf6dnZ2Rnp4OAOjbt6/cuZycnEptp6KiAplMJlf2+j4bxapq5ufevXuFOL/++utK7dvExERhf5S8vDxhZoSBgQEaNGgAGxsbuTrW1tYKSYTXGRgY4MGDB3JlSUlJGDFiBHr16oU9e/bg/PnzmDdvHgoLC4U6CxcuxJ9//onevXvj0KFDsLGxwc8//wwAGDduHK5fv46RI0fi0qVLcHJywhdffFHi+ZWpW8zb2xv3799HVFQUTp06hVOnTgGAXHwAhGXBAAj72vx7qa6S3L9/Hzo6OtDS0npj3YpQOlny4sULaGhoAAB+++039O3bFwDQvn17pdegIyIiInqbPHnyBCNHjkRUVBQMDAxqOhwiIiIiIqqFWrduDTU1Nbk9Rh49eoSrV68q1D158qTCa2tra+G1mpoaioqKhNcNGjRA27ZthUfxckklqcgI/ZSUFGEmgJ6enty5ij/AVldXl4sJAAwNDZGbmyuXMElJSSn3ecu6D9bW1vjrr7/w119/CccvX76Mhw8fCgmKli1bCnGamZmV/4LLwdXVFQkJCXJl8fHxwmwYdXV1vPvuu0hLS5Orc/XqVbRs2bLUfh0cHHDlyhW5e3bixAm0bNkS8+bNg5OTE9q1a4ebN28qtLW0tMSMGTNw8OBBDBw4EN98841wzNzcHBMnTkRsbCxmzpxZ5kC/0uoWz/55/et87949pKWlYf78+fjwww9hbW2tkOwpj5K+f4r98ccfcHBwULrP8lJ6z5IOHTogMjISvXv3Rnx8PJYsWQIA+Pvvv9G0adNKD5CIiIiophgYGEBVVbXMUUKvy8jIQGZmJry9vYWy4tExDRo0QFpaGtq0aVO1QRMRERERUa2mp6eHUaNGYfbs2WjSpAmMjIwQHBwMFRUVYZR9sePHj2PVqlXo378/4uPjsWPHDsTFxQnHLSwskJCQgM6dO0NDQwONGzcu8ZwhISFwcnJCmzZtUFBQgL179+K7777Dxo0bhTqBgYHIzs7Gt99+CwAIDw9Hq1at0KFDBzx//hxff/01Dh06hIMHD5Z5fRYWFvj999/x8ccfQ0NDAwYGBnB3d8edO3ewatUqfPTRR9i/fz/27dsHfX39ct2zsu6Dp6cnOnbsiBEjRiA8PBwvX77E5MmT0bVr1zJnuwCvkiqFhYW4f/8+njx5IiRw7O3thTrFZfn5+bhz5w5SUlKgrq4uJGKmTZuGrl27IjQ0FL1798a2bdtw9uxZfPXVV0Ifs2fPxtChQ/HBBx/Aw8MD+/fvx6+//lrmMmgeHh7Iz8/Hn3/+Kez30a5dO2RlZWHbtm149913ERcXJ8waAV4t3TV79mx89NFHaNWqFW7duoUzZ84Ie4lMnz4dPXv2hKWlJR48eIDDhw/LJd9eV1bdli1bQiQSYc+ePejVqxe0tLTQuHFjNG3aFF999RVMTU2RlZVV6j6fZbGwsEB+fj4SEhJgZ2cHbW1taGtrA3i16X337t2V7rO8lE6WrFy5EgMGDMDq1asxatQo2NnZAQB2794tt84eERERUV2nrq4OR0dHJCQkoH///gBeJT8SEhLg5+enUL99+/a4dOmSXNn8+fPx5MkTrF27Vm4NXSIiIiIiqjoms7vUdAhlCgsLw8SJE9GnTx/o6+tjzpw5+OuvvxT2qJg5cybOnj2LRYsWQV9fH2FhYfDy8hKOh4aGQiwWIyoqCmZmZsjMzCzxfBKJBJMnT8atW7egpaWF9u3b4/vvv8fQoUOFOjk5OXLLQhUWFmLmzJnIzs6GtrY2bG1t8dtvv8HDw6PMa1u8eDE+/fRTITEjk8lgbW2NDRs2YPny5ViyZAkGDRqEWbNmySUUylLWfRCJRPjll18wdepUfPDBB1BRUUGPHj3euGQUAPTq1UtuZkbxrIXXZ3O8PpMhOTkZW7duRcuWLYV77ebmhq1bt2L+/Pn47LPP0K5dO+zatUtuQ/MBAwYgMjISISEh8Pf3h5WVFXbu3IkuXUr/Pm3atCkGDBiALVu2CMul9e3bFzNmzICfnx8KCgrQu3dvBAUFYeHChQAAVVVV3Lt3Dz4+PsjLy4OBgQEGDhyIRYsWAXg1E2TKlCm4desW9PX10aNHD2EPmn8rq66ZmRkWLVqEgIAA+Pr6wsfHBzExMdi2bRv8/f3xzjvvwMrKCuvWrYO7u/sbvw6vc3Nzw8SJEzF06FDcu3cPwcHBWLhwIbKzs3HixAl8//33SvWnDKWTJe7u7rh79y4eP34sl6mcMGGCkOEhIiIieluIxWKMGjUKTk5OcHZ2Rnh4OCQSCXx9fQEAPj4+MDMzQ0hICDQ1NeX+QwwAjRo1AgCFciIiIiIiqr/09PSwZcsW4bVEIsGiRYswYcIEuXr6+vr48ccfS+3H29tbbmZ7aZYuXYqlS5eWWeff+1HPmTMHc+bMeWPf//bee+/hwoULCuUTJ06U20MFAD777LNSz1+stATQ61q0aIFffvlFqTjL2/e/91opyeDBgzF48OAy64wZMwZjxowpb2gAgHnz5qFbt26YN28edHV1AQCrVq3CqlWr5OpNnz4dwKsBfz/88EOp/ZWVQHJ3d5e71jclm4KCghAUFCRX5unpicuXL8uVvd6nhYWFwv1s1KiRQtnGjRvlZj0BwLp16zB69Gg0b968zLj+C6WTJcCrDNW/p3QV72xPRERE9DYZOnQo7ty5gwULFiA3Nxf29vbYv3+/sOl7VlYWVFSU3gaOiIiIiIjqsfPnz+PKlStwdnbGo0ePsHjxYgBAv379ajgyqk1sbW2xcuVK3LhxAx07dqzpcGqUkZERxGJxlZ5D6WRJXl4eZs2ahYSEBNy+fVsh61Pa5itEREREdZWfn1+Jy24BKHONWaD00VFERERERFS/ff7550hLSxOW/z169CgMDAxqOiyqZUaPHl3TIdQKM2fOrPJzKJ0sGT16NLKyshAUFARTU1OFTYeIiIiIiIiIiIiIqHQODg5ITk4us055logiosqjdLLk2LFjOHr0KOzt7asgHCIiIiIiIiIiIiIiouql9ALb5ubm5drUhoiIiIiIiIiIiIiIqC5QOlkSHh6OgIAATgMjIiIiIiIiIiIiIqK3gtLLcA0dOhRPnz5FmzZtoK2tDTU1Nbnj9+/fr7TgiIiIiIiIiIiIiIiIqprSyZLw8PAqCIOIiIio7pFIJNDV1QUA5OfnQ0dHp4YjIiIiIiIiIqKKUDpZMmrUqFKPcVYJERERERERERERERHVNUrvWVKSgwcPYsiQITAzM6uM7oiIiIiIiIiIiIiIYGFhUW9XOyosLETbtm1x4sQJoezKlSt47733oKmpCXt7+5oLDsDChQurNYbLly+jefPmkEgkVdK/0jNLit28eRPR0dHYvHkzHjx4gJ49e+Lbb7+tzNiIiIjqjbDNZ8tVr6DgmfB83ZZz0NDQKlc78SinCsVFVN99enRrueq9ePZceD71+HaoaWmWq92X7w8vV72isLHlq1fw4p/n6yahSEOtjNr/UBVvKlc9IiIiorrih7TB1Xq+YVY7qvV8xUQiEX7++Wf079+/zHqxsbFYvnw50tPT8eLFC7Rr1w4zZ87EyJEjS22TmJgIDw8PhfKcnByYmJiU2s7CwgLTp0/H9OnTy3sZNeL58+eYOHEikpOTkZqaij59+mDXrl1ydXJycjBz5kycPXsW6enp8Pf3LzFxs2PHDgQFBSEzMxPt2rXDypUr0atXL7k6qampmDt3Lo4cOYKXL1/CxsYGO3fuRIsWLUqNMTIyEq1atYKbm5tQFhwcDB0dHaSlpQnLQleHkr7XZs2ahalTp1ZbDDY2NnjvvfcQFhaGoKCgSu9fqZklhYWF2LZtGzw9PdG+fXucO3cOt27dwrFjx7Bt2zYMHly9b0JEREREREREREREVLYmTZpg3rx5SEpKwsWLF+Hr6wtfX18cOHDgjW3T0tKQk5MjPIyMjKoh4lefRVeloqIiaGlpwd/fH56eniXWKSgogKGhIebPnw87O7sS65w4cQLDhg3D2LFjcf78efTv3x/9+/fHH3/8IdTJ+L/27jwup/T/H/jrbt8loUVkKdKk1ZI+lBFlLbs0VPY9LfYl1ShLiyzDDMY2yBhmxmAy6SsqzdjK2tgTpuxMC0Xdvz/8OuN2d+eOyPJ6Ph73Q+c617nO+xx1Peq8z3VdV67gf//7H1q0aIHk5GScPn0ac+fOhZqa7JesxGIxVqxYgREjJF+cKm+rUaNGqFOnzhtcefXR0tJ67zH4+flh1apVeP78ebW3LXeyZNKkSTAyMkJcXBz69OmDmzdv4rfffoNIJIKiomK1B0ZERERERERERET0KcrPz4e3tzc0NTVhaGiI2NhYuLi4SIzGMDU1RXh4OLy8vKCpqQljY2OsXLlSYj8A9OnTByKRSNiuiIuLC/r06QMLCws0bdoU/v7+aNWqFVJTU18ba7169WBgYCB8FBRkP1J2cXHB9evXERAQAJFIBJFIBKDi6ZqWLl0qEbOvry88PT2xYMECGBkZoXnz5hL3S9Z9AICcnBx4eHhAS0sLOjo6GDhwIG7fvl3pdWlqamLVqlUYNWqUzJEypqamiIuLw7Bhw1CrVq0K68TFxcHd3R1Tp06FhYUFwsPDYWdnhxUrVgh1Zs+eje7du2Px4sWwtbVF06ZN0bt370oTTydOnMCVK1fQo0cPoUwkEuHEiRMICwuDSCTC/PnzkZycDJFIhEePHgn1MjMzIRKJkJ2dDQDYsGEDdHV1sX//flhYWEBLSwvu7u7Izc2VOOf3338PS0tLqKqqwtDQEBMnThTuAyD9vfbq/2tZWRnCwsLQoEEDqKqqwsbGBgkJCcL+7OxsiEQi7Nq1C506dYKGhgasra2Rnp4u1Ll+/Tp69eqF2rVrQ1NTE5aWlti3b5+wv0uXLnjw4AEOHTok8969KbmTJatWrcKYMWPwxx9/YMKECTWetSIiIqKaoaGijtzFKchdnAINFfmmASMiIiIiIqL/BAYGIi0tDbt370ZiYiJSUlJw8uRJqXpLliyBtbU1MjIyMGPGDPj7+yMxMREAcOzYMQDA+vXrkZubK2y/jlgsRlJSEi5cuICOHTu+tr6NjQ0MDQ3RpUsXpKWlVVp3165daNCgAcLCwoSRKFVRHldiYiL27NkjlFd2H8rKyuDh4SE8QE9MTMTVq1cxaNCgKp37TaWnp0uNTHFzcxMSAGVlZdi7dy/Mzc3h5uaGevXqoW3btlJTfr0qJSUF5ubm0NbWFspyc3NhaWmJoKAg5ObmIjg4WO44i4qKEBUVhc2bN+Pw4cPIycmROH7VqlWYMGECRo8ejTNnzmD37t1o1qwZAPm/1+Li4hAdHY2oqCicPn0abm5u6N27Ny5duiRRb/bs2QgODkZmZibMzc3h5eUljBSZMGECiouLcfjwYZw5cwaLFi2SmG5MRUUFNjY2SElJkfva5SX3miWbN2/G999/D0NDQ/To0QNDhw5Ft27dqj0gIiIiIiIiIiIiok9Vfn4+Nm7ciK1bt6Jz584AXjyENjIykqrr5OSEGTNmAADMzc2RlpaG2NhYdOnSBXXr1gUA6OrqVrqGSLnHjx/D2NgYxcXFUFRUxDfffIMuXbrIrG9oaIjVq1fDwcEBxcXFWLt2LVxcXPDXX3/Bzs6uwmP09PSgqKgIbW1tuWJ6laamJtauXQsVFRWJ8sruQ1JSEs6cOYNr167BxMQEALBp0yZYWlri2LFjaN26dZXjqIq8vDzUr19foqx+/frIy8sDANy5cwcFBQVYuHAhvv76ayxatAgJCQno27cvDh48CGdn5wrbvX79utT3hIGBAZSUlKClpVXl+/vs2TOsXr0aTZs2BQBMnDgRYWFhwv6vv/4aQUFB8Pf3F8rK752832tRUVGYPn06Bg8eDABYtGgRDh48iKVLl0qMBgoODhZGzISGhsLS0hKXL19GixYtkJOTg379+sHKygoA0KRJE6nzGBkZ4fr161W6fnnIPbLEy8sLiYmJOHPmDFq0aIEJEybAwMAAZWVlOH/+fLUHRkRERERERERERPSpuXr1Kp49e4Y2bdoIZbVq1ZKYdqqco6Oj1HZWVpbMtnNycqClpSV8IiIihH3a2trIzMzEsWPHsGDBAgQGBiI5OVlmW82bN8eYMWNgb2+P9u3b4/vvv0f79u0RGxsLANiyZYvEuarjTX8rKyupRAlQ+X3IysqCiYmJkCgBXiwErqurK9SxtLQU4nzfAwDKysoAAB4eHggICICNjQ1mzJiBnj17YvXq1TKPe/LkSaVrmlSVhoaGkCgBXiTD7ty5A+BFQueff/4Rkndv4t9//8U///wDJycniXInJyep79lWrVpJxFEeAwBMnjwZX3/9NZycnBASEoLTp09LnUtdXR1FRUVvHKssVVrgHQAaN26M0NBQZGdn44cffkC/fv3w1VdfoUGDBpg8eXK1B0hEREREREREREREr2dkZITMzEzhM3bsWGGfgoICmjVrBhsbGwQFBaF///6IjIysUvtt2rTB5cuXAQC9e/eWOJeDg4PM4xQUFCAWiyXKnj17JlVPU1OzSvHIa9++fUKca9eurda2DQwMpNZHuX37tjACQ19fH0pKSmjZsqVEHQsLC+Tk5MhsV19fHw8fPnzt+cvXkHn5/lZ0b5WVlSW2RSKRcIy6+vudYvvlWMrXtSlPKo0cORJXr17F0KFDcebMGTg4OGD58uUSxz948EAY7VKdqpwsKScSieDm5oYff/wR//zzD4KDg9/JoipEREREREREREREn4omTZpAWVlZYt2Hx48f4+LFi1J1//zzT6ltCwsLYVtZWRmlpaXCtpKSEpo1ayZ89PT0ZMZRVlaG4uLiKsWemZkpjATQ1taWOFf5A3cVFRWJmIAX0zjl5eVJPNDPzMyU+7yV3QcLCwvcuHEDN27cEPafP38ejx49EhIUjRo1EuI0NjaW/4Ll4OjoiKSkJImyxMREYTSMiooKWrdujQsXLkjUuXjxIho1aiSzXVtbW/z9999SSaZXlScNXl4fpir3Fnjxf2lqaip1HS979XvtVTo6OjAyMpJa1yYtLU0qUfQ6JiYmGDt2LHbt2oWgoCCsWbNGYv/Zs2dha2tbpTblIfeaJZXR09PDlClTMGXKlOpojoiIiIiIiIiIiOiTpK2tDR8fH0ydOhV6enqoV68eQkJCoKCgILxlXy4tLQ2LFy+Gp6cnEhMTsWPHDuzdu1fYX/6A28nJCaqqqqhdu3aF54yMjISDgwOaNm2K4uJi7Nu3D5s3b8aqVauEOjNnzsStW7ewadMmAMDSpUvRuHFjWFpa4unTp1i7di3+7//+D3/88Uel12dqaorDhw9j8ODBUFVVhb6+PlxcXHD37l0sXrwY/fv3R0JCAn7//Xfo6OjIdc8quw+urq6wsrKCt7c3li5diufPn2P8+PFwdnaudLQL8CKpUlJSggcPHiA/P19IMtjY2Ah1yssKCgpw9+5dZGZmQkVFRUgA+Pv7w9nZGdHR0ejRowfi4+Nx/PhxfPfdd0IbU6dOxaBBg9CxY0d06tQJCQkJ+O233yqdBq1Tp04oKCjAuXPn8MUXX8is16xZM5iYmGD+/PlYsGABLl68iOjo6EqvuyLz58/H2LFjUa9ePXTr1g35+flIS0vDpEmTAMj3vTZ16lSEhISgadOmsLGxwfr165GZmYktW7bIHceUKVPQrVs3mJub4+HDhzh48KBEgjA7Oxu3bt2Cq6trla/xdaolWUJERERERERERET0ofBqvqOmQ6hUTEwMxo4di549e0JHRwfTpk3DjRs3pNaoCAoKwvHjxxEaGgodHR3ExMTAzc1N2B8dHY3AwECsWbMGxsbGyM7OrvB8hYWFGD9+PG7evAl1dXW0aNECP/zwAwYNGiTUyc3NlZgWqqSkBEFBQbh16xY0NDTQqlUrHDhwAJ06dar02sLCwjBmzBghMSMWi2FhYYFvvvkGERERCA8PR79+/RAcHCyRUKhMZfdBJBLh119/xaRJk9CxY0coKCjA3d1dauqminTv3l1iofDy0Qovj+Z4eQTDiRMnsHXrVjRq1Ei41+3bt8fWrVsxZ84czJo1C2ZmZvjll18kEhx9+vTB6tWrERkZicmTJ6N58+bYuXMn/ve//8mMrU6dOujTpw+2bNlS6XRpysrK2LZtG8aNG4dWrVqhdevW+PrrrzFgwIDXXv/LfHx88PTpU8TGxiI4OBj6+vro37+/sF+e77XJkyfj8ePHCAoKwp07d9CyZUvs3r0bZmZmcsdRWlqKCRMm4ObNm9DR0YG7u7uwTg4AbNu2DV27dq10VM6bYrKEiIiIiIiIiIiI6D3S1taWeNu+sLAQoaGhGD16tEQ9HR0d/PjjjzLb6dWrF3r16vXa83399df4+uuvK62zYcMGie1p06Zh2rRpr237Ve3atcOpU6ekyseOHSuxhgoAzJo1S+b5y8lKAL2sYcOG+PXXX6sUp7xtv24aLAAYMGDAa5MTw4cPx/Dhw+UNDQAwe/ZsdOnSBbNnz4aWlhaAiqfYcnJykloI/eW4fX194evrK7Hf09NT6trGjBmDMWPGVBhLRd9r8+fPx/z584VtBQUFhISEICQkpMI2TE1Npc6pq6srUVZZkqukpASrV6/G1q1bZdZ5G2+8ZgkRERERERERERERVV1GRga2bduGK1eu4OTJk/D29gYAeHh41HBk9CFp1aoVFi1ahGvXrtV0KB+EnJwczJo1C05OTu+kfY4sISIiIiIiIiIiInrPoqKicOHCBaioqMDe3h4pKSnQ19ev6bDoA/PqiJDPWbNmzdCsWbN31n6VkyUJCQnQ0tIS5lNbuXIl1qxZg5YtW2LlypUyFxEiIiIiIiIiIiIiohfrYJw4caLSOvJMEUVE1afK03BNnToV//77LwDgzJkzCAoKQvfu3XHt2jUEBgZWe4BERERERERERERERETvUpVHlly7dg0tW7YEAOzcuRM9e/ZEREQETp48ie7du1d7gERERERERERERERERO9SlUeWqKiooKioCABw4MABdO3aFQCgp6cnjDghIiIiIiIiIiIiIiL6WFR5ZMn//vc/BAYGwsnJCUePHsX27dsBABcvXkSDBg2qPUAiIiIiIqKPkZqGErb+3b9GY9DUUIT4gnWNxkBERERE9DGo8siSFStWQElJCT/99BNWrVoFY2NjAMDvv/8Od3f3ag+QiIiIiIiIiIiIiIjoXaryyJKGDRtiz549UuWxsbHVEhAREREREREREREREdH7VOWRJQBQVlaGixcvIjU1FYcPH5b4EBERERERERERERG9D0OHDkVERISwXVRUhH79+kFHRwcikQiPHj2qsdiSk5PfawwlJSUwNTXF8ePH38v5PjVVHlny559/YsiQIbh+/TrEYrHEPpFIhNLS0moLjoiIiIiIiIiIiKjKLtq83/OZZ77f8/1/IpEIP//8Mzw9PeU+Jj4+Hl5eXvDw8MAvv/xSad2nT58iKCgI8fHxKC4uhpubG7755hvUr19fot6GDRsQExODixcvQkdHBwMGDMDKlSuFNsaOHYsTJ04gKysLPXv2lDpvamoqpk+fjr///htFRUVo1KgRxowZg4CAgErjO3XqFPbt24dVq1YJZRs3bkRKSgqOHDkCfX191KpVS+578zZcXFxgY2ODpUuXCmXt27dHbm7ue4tBRUUFwcHBmD59OpKSkt7LOT8lVU6WjB07Fg4ODti7dy8MDQ0hEoneRVxEREREREREREREVI2ys7MRHByMDh06yFU/ICAAe/fuxY4dO1CrVi1MnDgRffv2RVpamlAnJiYG0dHRWLJkCdq2bYvCwkJkZ2cL+0tLS6Guro7Jkydj586dFZ5HU1MTEydORKtWraCpqYnU1FSMGTMGmpqaGD16tMz4li9fjgEDBkBLS0sou3LlCiwsLPDFF1/IdY3vkoqKCgwMDN7rOb29vREUFIRz587B0tLyvZ77Y1flabguXbqEiIgIWFhYQFdXF7Vq1ZL4EBEREREREREREZFs+fn58Pb2hqamJgwNDREbGwsXFxdMmTJFqGNqaorw8HB4eXlBU1MTxsbGwmiN8v0A0KdPH4hEImFbltLSUnh7eyM0NBRNmjR5bYyPHz/GunXrEBMTgy+//BL29vZYv349jhw5gj///BMA8PDhQ8yZMwebNm3CkCFD0LRpU7Rq1Qq9e/cW2tHU1MSqVaswatQomYkDW1tbeHl5wdLSEqampvjqq6/g5uaGlJSUSq/np59+Qq9evYQyFxcXREdH4/DhwxCJRHBxcQHwYgTOq6NZdHV1sWHDBgAvkkgikQi7du1Cp06doKGhAWtra6Snp0sck5aWBhcXF2hoaKB27dpwc3PDw4cP4evri0OHDiEuLg4ikQgikQjZ2dkVTsO1c+dOWFpaQlVVFaampoiOjpY4h6mpKSIiIjB8+HBoa2ujYcOG+O6774T9JSUlmDhxIgwNDaGmpoZGjRohMjJS2F+7dm04OTkhPj5e5r2jilU5WdK2bVtcvnz5XcRCRERERERERERE9MkLDAxEWloadu/ejcTERKSkpODkyZNS9ZYsWQJra2tkZGRgxowZ8Pf3R2JiIgDg2LFjAID169cjNzdX2JYlLCwM9erVw4gRI+SK8cSJE3j27BlcXV2FshYtWqBhw4ZCEiExMRFlZWW4desWLCws0KBBAwwcOBA3btyQ6xyyZGRk4MiRI3B2dpZZ5/Tp03j8+DEcHByEsl27dmHUqFFwdHREbm4udu3aVaXzzp49G8HBwcjMzIS5uTm8vLzw/PlzAEBmZiY6d+6Mli1bIj09HampqejVqxdKS0sRFxcHR0dHjBo1Crm5ucjNzYWJiYlU+ydOnMDAgQMxePBgnDlzBvPnz8fcuXOFpE256OhoODg4ICMjA+PHj8e4ceNw4cIFAMCyZcuwe/du/Pjjj7hw4QK2bNkilShr06ZNpYkmqliVp+GaNGkSgoKCkJeXBysrKygrK0vsb9WqVbUFR0RERERERERERPQpyc/Px8aNG7F161Z07twZwIuEh5GRkVRdJycnzJgxAwBgbm6OtLQ0xMbGokuXLqhbty6AFyMkXjfVU2pqKtatW4fMzEy548zLy4OKigp0dXUlyuvXr4+8vDwAwNWrV1FWVoaIiAjExcWhVq1amDNnDrp06YLTp09DRUVF7vMBQIMGDXD37l08f/4c8+fPx8iRI2XWvX79OhQVFVGvXj2hTE9PDxoaGm88/VVwcDB69OgBAAgNDYWlpSUuX76MFi1aYPHixXBwcMA333wj1H95misVFRVoaGhUet6YmBh07twZc+fOBfDi//T8+fNYsmQJfH19hXrdu3fH+PHjAQDTp09HbGwsDh48iObNmyMnJwdmZmb43//+B5FIhEaNGkmdx8jICNevX6/y9X/uqjyypF+/fsjKysLw4cPRunVr2NjYwNbWVviXiIiIiIiIiIiIiCp29epVPHv2DG3atBHKatWqhebNm0vVdXR0lNrOysqS2XZOTg60tLSET0REBPLz8zF06FCsWbMG+vr6FR4XEREhcVxOTo5c11JWVoZnz55h2bJlcHNzQ7t27bBt2zZcunQJBw8elKuNl6WkpOD48eNYvXo1li5dim3btsms++TJE6iqqlbrmtovDwQwNDQEANy5cwfAfyNL3kZWVhacnJwkypycnHDp0iWUlpZWGIdIJIKBgYEQh6+vLzIzM9G8eXNMnjwZf/zxh9R51NXVUVRU9Faxfo6qPLLk2rVr7yIOIiIiIiIiIiIiInoLRkZGEqNH9PT0cOXKFWRnZ0us7VFWVgYAUFJSwoULFzB27FgMHDhQoh0DAwOUlJTg0aNHEqNLbt++LYyeKE8otGzZUthft25d6Ovry51weVnjxo0BAFZWVrh9+zbmz58PLy+vCuvq6+ujqKgIJSUlrx3BIhKJIBaLJcqePXsmVe/lWZTKkzDl90pdXV3+C3lLr87mJBKJhDjs7Oxw7do1/P777zhw4AAGDhwIV1dX/PTTT0L9Bw8eCCOPSH5VHlnSqFGjSj9vYuXKlTA1NYWamhratm2Lo0ePynVcfHw8RCIRPD093+i8RERERERERERERO9TkyZNoKysLLHGyOPHj3Hx4kWpuuULqb+8bWFhIWwrKytLjEhQUlJCs2bNhI+enh5atGiBM2fOIDMzU/j07t0bnTp1QmZmJkxMTKCnpydxnJKSEuzt7aGsrIykpCSh/QsXLiAnJ0cY8VI+SqJ8PQ3gxYP6e/fuvfGz4nJlZWUoLi6Wud/GxgYAcP78+de2VbduXeTm5grbly5dqvLIi1atWknci1epqKhI/F9UxMLCAmlpaRJlaWlpMDc3h6Kiotyx6OjoYNCgQVizZg22b9+OnTt34sGDB8L+s2fPchaoN1DlkSUAcOXKFSxdulQY8tWyZUv4+/ujadOmVW5r+/btCAwMxOrVq9G2bVssXboUbm5uuHDhgsR8c6/Kzs5GcHAwOnTo8CaXQERERERERERERPTeaWtrw8fHB1OnToWenh7q1auHkJAQKCgoSE0plZaWhsWLF8PT0xOJiYnYsWMH9u7dK+w3NTVFUlISnJycoKqqitq1a0udT01NDV988YVEWflIkVfLX1arVi2MGDECgYGB0NPTg46ODiZNmgRHR0e0a9cOwIs1Nzw8PODv74/vvvsOOjo6mDlzJlq0aIFOnToJbZ0/fx4lJSV48OAB8vPzhdEv5QmPlStXomHDhmjRogUA4PDhw4iKisLkyZNlxle3bl3Y2dkhNTVVaEeWL7/8EitWrICjoyNKS0sxffp0qdEbrzNz5kxYWVlh/PjxGDt2LFRUVHDw4EEMGDAA+vr6MDU1xV9//YXs7GxoaWlBT09Pqo2goCC0bt0a4eHhGDRoENLT07FixQqJdVBeJyYmBoaGhrC1tYWCggJ27NgBAwMDidE/KSkpCA8Pr9L10RskS/bv34/evXvDxsZGyBympaXB0tISv/32G7p06VKl9mJiYjBq1Cj4+fkBAFavXo29e/fi+++/FxYvelVpaSm8vb0RGhqKlJQUPHr0qKqXQURERERERERERJ8q88yajqBSMTExGDt2LHr27AkdHR1MmzYNN27cgJqamkS9oKAgHD9+HKGhodDR0UFMTAzc3NyE/dHR0QgMDMSaNWtgbGyM7Ozsao0zNjYWCgoK6NevH4qLi+Hm5ib1YH/Tpk0ICAhAjx49oKCgAGdnZyQkJEgkI7p37y6x4Hj5qIfyqbHKysowc+ZMXLt2DUpKSmjatCkWLVqEMWPGVBrfyJEjsWnTJkycOLHSetHR0fDz80OHDh1gZGSEuLg4nDhxokr3wtzcHH/88QdmzZqFNm3aQF1dHW3bthWmCQsODoaPjw9atmyJJ0+eVLichZ2dHX788UfMmzcP4eHhMDQ0RFhYmMTi7q+jra2NxYsX49KlS1BUVETr1q2xb98+KCi8mEQqPT0djx8/Rv/+/at0ffQGyZIZM2YgICAACxculCqfPn16lZIlJSUlOHHiBGbOnCmUKSgowNXVFenp6TKPCwsLQ7169TBixAikpKRUeo7i4mKJ4Vr//vuv3PERERERERERERERVTdtbW1s2bJF2C4sLERoaChGjx4tUU9HRwc//vijzHZ69eolsRaJvDZs2CBXPTU1NaxcuRIrV66UWUdHRwfr1q3DunXrZNZ5XRJn0qRJmDRpklwxvczX1xeRkZFIT08XpgZbunSpVD0jIyPs379fouzlF/BNTU2l1jTR1dWVKnN2dpaaRqucubm51DPtitrt168f+vXrJ/OaKrpXL69DM2rUKIwaNUrm8UuXLsXUqVPf6xorn4oqJ0uysrIq/AEdPnx4hd+Ilbl37x5KS0tRv359ifL69evj77//rvCY1NRUrFu3TuIbpDKRkZEIDQ2tUlxERERUM1auXIklS5YgLy8P1tbWWL58Odq0aVNh3TVr1mDTpk04e/YsAMDe3h4RERES9X19fbFx40aJ49zc3JCQkFB5IBdt5Au46KX5aC+1AzTknGP2A3/LjYhIXv+kyX5w8rKiJ/+9wJab/i001FXlOs7IacJr6+zZs0eutp4+fSp8/fvvv0u9uStLz5495apHRERUFRkZGfj777/Rpk0bPH78GGFhYQAADw+PGo7s46Kuro5Nmzbh3r17NR3KB6GkpARWVlYICAio6VA+SlVe4L1u3boVJioyMzMrXWOkOuTn52Po0KFYs2YN9PX15Tpm5syZePz4sfC5cePGO42RiIiI3kz5OmYhISE4efIkrK2t4ebmhjt37lRYPzk5GV5eXjh48CDS09NhYmKCrl274tatWxL13N3dkZubK3y2bdv2Pi6HiIiIiIioUlFRUbC2toarqysKCwuRkpIi9zNP+o+Li8sbja75FKmoqGDOnDkcVfKGqjyyZNSoURg9ejSuXr2K9u3bA3ixZsmiRYsQGBhYpbb09fWhqKiI27dvS5Tfvn0bBgYGUvWvXLmC7OxsiW/+srKyFxeipIQLFy5ILTKvqqoKVVX53loiIiKimlPVdcxeHrIOAGvXrsXOnTuRlJSEYcOGCeWqqqoV/l5BRERERERUU2xtbV+7ZkZ1rz9CRJWrcrJk7ty50NbWRnR0tLDWiJGREebPn4/JkydXqS0VFRXY29sjKSkJnp6eAF4kP5KSkipclKdFixY4c+aMRNmcOXOQn5+PuLg4mJiYVPVyiIiIPiqqquqI3nCspsOodm+6jtnLioqK8OzZM+jp6UmUJycno169eqhduza+/PJLfP3116hTp061xk9EREREREREH7cqJ0tEIhECAgIQEBCA/Px8AC8WJHpTgYGB8PHxgYODA9q0aYOlS5eisLBQeKt02LBhMDY2RmRkJNTU1PDFF19IHK+rqwsAUuVERET08XiTdcxeNX36dBgZGcHV1VUoc3d3R9++fdG4cWNcuXIFs2bNQrdu3ZCeng5FRTnXFyEiIiIiIiKiT16VkyUve5skSblBgwbh7t27mDdvHvLy8mBjY4OEhAThYUlOTg4UFKq8tAoRERF9RhYuXIj4+HgkJydLLNg7ePBg4WsrKyu0atUKTZs2RXJyMjp37lwToRIRERERERHRB0iuZImdnR2SkpJQu3Zt2NraQiQSyax78uTJKgcxceLECqfdAl5MnVGZDRs2VPl8RERE9GGp6jpmL4uKisLChQtx4MABtGrVqtK6TZo0gb6+Pi5fvsxkCREREREREREJ5EqWeHh4CIuke3h4VJosISIiIqqqqq5jVm7x4sVYsGAB9u/fDwcHh9ee5+bNm7h//z4MDQ2rK3QiIiIiIiIi+gTIlSwJCQkRvp4/f/67ioWIiIg+Y1VZxwwAFi1ahHnz5mHr1q0wNTVFXl4eAEBLSwtaWlooKChAaGgo+vXrBwMDA1y5cgXTpk1Ds2bN4ObmVmPXSUREREREREQfniovBtKkSRPcv39fqvzRo0do0qRJtQRFREREn59BgwYhKioK8+bNg42NDTIzM6XWMcvNzRXqr1q1CiUlJejfvz8MDQ2FT1RUFABAUVERp0+fRu/evWFubo4RI0bA3t4eKSkpwohZIiIiIiIiojfh6+srzIzwPnXs2BFbt2595+fJzs6GSCRCZmbmOz/Xmxg8eDCio6Ortc0qL/CenZ2N0tJSqfLi4mLcvHmzWoIiIiKiz1NV1jHLzs6utC11dXXs37+/miIjIiIiIqKPyT9pK9/r+YycJrzX85UTiUT4+eefq/TQPj4+Hl5eXvDw8MAvv/xSad3vvvsOW7duxcmTJ5Gfn4+HDx9CV1dXos6CBQuwd+9eZGZmQkVFBY8ePZJqJycnB+PGjcPBgwehpaUFHx8fREZGQknpv8fTxcXFCAsLww8//IC8vDwYGhpi3rx5GD58uNzX9j7FxcVBLBa/13Pu3r0bt2/fxuDBg9/5uUxMTJCbmwt9ff3X1s3Ozkbjxo2RkZEBGxubao0jOTkZnTp1kvremzNnDjp27IiRI0eiVq1a1XIuuZMlu3fvFr7ev3+/RAClpaVISkpC48aNqyUoIiIiIiIiIiIiIqpe2dnZCA4ORocOHeSqX1RUBHd3d7i7u2PmzJkV1ikpKcGAAQPg6OiIdevWSe0vLS1Fjx49YGBggCNHjiA3NxfDhg2DsrIyIiIihHoDBw7E7du3sW7dOjRr1gy5ubkoKyt7swutRElJCVRUVN66nep6QF8Vy5Ytg5+fHxQUqjxhVJUpKirCwMDgnZ/nTX3xxRdo2rQpfvjhB0yYUD3JSrnvqqenJzw9PSESieDj4yNse3p6YvDgwUhMTKz2YS9EREREREREREREn5r8/Hx4e3tDU1MThoaGiI2NhYuLC6ZMmSLUMTU1RXh4OLy8vKCpqQljY2OsXLlSYj8A9OnTByKRSNiWpbS0FN7e3ggNDZV7OYUpU6ZgxowZaNeuncw6oaGhCAgIgJWVVYX7//jjD5w/fx4//PADbGxs0K1bN4SHh2PlypUoKSkBACQkJODQoUPYt28fXF1dYWpqCkdHRzg5OVUan4uLizBDQa1ataCvr4+5c+dKjPgov4/Dhg2Djo4ORo8eDQBITU1Fhw4doK6uDhMTE0yePBmFhYUAgFmzZqFt27ZS57O2tkZYWBgA6Wm4ysrKEBkZicaNG0NdXR3W1tb46aefhP0ODg7CtNHAi+ftysrKKCgoAADcvHkTIpEIly9frvBa7969i//7v/9Dr169JMpjYmJgZWUFTU1NmJiYYPz48UKbAHD9+nX06tULtWvXhqamJiwtLbFv3z4AwMOHD+Ht7Y26detCXV0dZmZmWL9+PQDpabgqq1s+iMLW1hYikQguLi4AgGPHjqFLly7Q19dHrVq14OzsjJMnT0rELxKJsHbtWvTp0wcaGhowMzMTBm5kZ2ejU6dOAIDatWtDJBLB19dXOLZXr16Ij4+v8H69CbmTJWVlZSgrK0PDhg1x584dYbusrAzFxcW4cOECevbsWW2BEREREREREREREX2KAgMDkZaWht27dyMxMREpKSlSD5EBYMmSJbC2tkZGRgZmzJgBf39/JCYmAnjxIBoA1q9fj9zcXGFblrCwMNSrVw8jRoyo/guqRHp6OqysrIT1KAHAzc0N//77L86dOwfgxaxGDg4OWLx4MYyNjWFubo7g4GA8efLkte1v3LgRSkpKOHr0KOLi4hATE4O1a9dK1ImKihLu49y5c3HlyhW4u7ujX79+OH36NLZv347U1FRhWmhvb28cPXoUV65cEdo4d+4cTp8+jSFDhlQYR2RkJDZt2oTVq1fj3LlzCAgIwFdffYVDhw4BAJydnYXppcViMVJSUqCrq4vU1FQAwKFDh2BsbIxmzZpV2H5qaio0NDRgYWEhUa6goIBly5bh3Llz2LhxI/7v//4P06ZNE/ZPmDABxcXFOHz4MM6cOYNFixZBS0sLADB37lycP38ev//+O7KysrBq1SqZ025VVvfo0aMAgAMHDiA3Nxe7du0C8CIp6OPjg9TUVPz5558wMzND9+7dkZ+fL9F2aGgoBg4ciNOnT6N79+7w9vbGgwcPYGJigp07dwIALly4gNzcXMTFxQnHtWnTBkePHkVxcXGFMVdVldcsuXbtmlTZo0ePpOaqIyIiIiIiIiIiIiJJ+fn52LhxI7Zu3YrOnTsDeJHwMDIykqrr5OSEGTNmAADMzc2RlpaG2NhYdOnSBXXr1gUA6Orqvna6pNTUVKxbt65GFuvOy8uTSJQAELbz8vIAAFevXkVqairU1NTw888/4969exg/fjzu378vjF6QxcTEBLGxsRCJRGjevDnOnDmD2NhYjBo1Sqjz5ZdfIigoSNgeOXIkvL29hZE8ZmZmWLZsGZydnbFq1SpYWlrC2toaW7duxdy5cwEAW7ZsQdu2bStMZhQXFyMiIgIHDhyAo6MjAKBJkyZITU3Ft99+C2dnZ7i4uGDdunUoLS3F2bNnoaKigkGDBiE5ORnu7u5ITk6Gs7OzzOu8fv066tevLzUF16ujkb7++muMHTsW33zzDYAX68X069dPGPnz8qiinJwc2NrawsHBQThelsrqln8v1qlTR+J78csvv5Ro47vvvoOuri4OHTokMfDC19cXXl5eAICIiAgsW7YMR48ehbu7O/T09AAA9erVk8pBGBkZoaSkBHl5eWjUqJHM2OVV5cnNFi1ahO3btwvbAwYMgJ6eHoyNjXHq1Km3DoiIiIiIiIiIiIjoU3X16lU8e/YMbdq0Ecpq1aqF5s2bS9Utf/D+8nZWVpbMtnNycqClpSV8IiIikJ+fj6FDh2LNmjUyRw1ERERIHJeTk/OGV/dmysrKIBKJsGXLFrRp0wbdu3dHTEwMNm7ciCdPniAlJUUivi1btgjHtmvXDiKRSNh2dHTEpUuXUFpaKpSVP+Avd+rUKWzYsEGiTTc3N5SVlQmDBby9vbF161YAL0aCbNu2Dd7e3hXGf/nyZRQVFaFLly4SbW7atEkYndKhQwfk5+cjIyMDhw4dEhIo5aNNDh06JExfVZEnT55ATU1NqvzAgQPo3LkzjI2Noa2tjaFDh+L+/fsoKioCAEyePBlff/01nJycEBISgtOnTwvHjhs3DvHx8bCxscG0adNw5MgRmeevSt1yt2/fxqhRo2BmZoZatWpBR0cHBQUFUt9frVq1Er7W1NSEjo4O7ty589r21dXVAUC41rdV5ZElq1evFr4ZExMTceDAASQkJODHH3/E1KlT8ccff1RLYERERESVKSwsFIYOFxQUQFNTs4YjIiIiIiIiqllGRkYSo0f09PRw5coVZGdnS6x1Ub5wupKSEi5cuICxY8di4MCBEu1UFwMDA2GapnK3b98W9gGAoaEhjI2NJRZNt7CwgFgsxs2bN+Hg4CBxXa+OVHmdV/9eLCgowJgxYzB58mSpug0bNgQAeHl5Yfr06Th58iSePHmCGzduYNCgQRW2X75GyN69e2FsbCyxT1VVFcCLEUDW1tZITk5Geno6unTpgo4dO2LQoEG4ePEiLl26VOnIEn19fTx8+FCiLDs7Gz179sS4ceOwYMEC6OnpITU1FSNGjEBJSQk0NDQwcuRIuLm5Ye/evfjjjz8QGRmJ6OhoTJo0Cd26dcP169exb98+JCYmonPnzpgwYYLE2irlqlK3nI+PD+7fv4+4uDg0atQIqqqqcHR0FNaqKaesrCyxLRKJhO/Ryjx48ADAfyNb3laVkyV5eXkwMTEBAOzZswcDBw5E165dYWpqWuGiN0RERERERERERET0QpMmTaCsrIxjx44JD+YfP36MixcvomPHjhJ1//zzT6ntl9esUFZWlhhBoaSkJDVNlIaGBs6cOSNRNmfOHOTn5yMuLg4mJiZQUVERpjuqbo6OjliwYAHu3LmDevXqAXjxEr6Ojg5atmwJ4MV0Yzt27EBBQYHwUtzFixehoKCABg0aQF1dXeZaHn/99ZfEdvnaGIqKijJjsrOzw/nz52W2CQANGjSAs7MztmzZgidPnqBLly5C/K9q2bIlVFVVkZOTU2nCw9nZGQcPHsTRo0eF5IaFhQUWLFgAQ0NDmJubyzzW1tYWeXl5ePjwIWrXrg0AOHHiBMrKyhAdHS1Mz/Xjjz9KHWtiYoKxY8di7NixmDlzJtasWYNJkyYBeJFo8PHxgY+PDzp06ICpU6fKTIDIqquiogIAEt+LAJCWloZvvvkG3bt3BwDcuHED9+7dk3mNFZHVNgCcPXsWDRo0kDliqqqqnCypXbs2bty4ARMTEyQkJODrr78G8GIoUkUBExERERF96pTV1TD68JbXV3zHNFWV8Tx6eE2HQURERESV0NbWho+PD6ZOnQo9PT3Uq1cPISEhUFBQkJhOCnjxsHnx4sXw9PREYmIiduzYgb179wr7TU1NkZSUBCcnJ6iqqgoP0V+mpqaGL774QqKsfO2HV8tflZeXh7y8PFy+fBkAcObMGWhra6Nhw4ZCciUnJwcPHjxATk4OSktLhREgzZo1g5aWFrp27YqWLVti6NChWLx4MfLy8jBnzhxMmDBBGHUxZMgQhIeHw8/PD6Ghobh37x6mTp2K4cOHC1MtyZKTk4PAwECMGTMGJ0+exPLlyxEdHV3pMdOnT0e7du0wceJEjBw5Epqamjh//jwSExOxYsUKoZ63tzdCQkJQUlKC2NhYme1pa2sjODgYAQEBKCsrw//+9z88fvwYaWlp0NHRgY+PDwDAxcUFy5cvR926ddGiRQuhbMWKFRgwYEClMdva2kJfXx9paWnCeh/NmjXDs2fPsHz5cvTq1QtpaWlYvXq1xHFTpkxBt27dYG5ujocPH+LgwYNCwm3evHmwt7eHpaUliouLsWfPHqkF5MtVVrdevXpQV1dHQkICGjRoADU1NdSqVQtmZmbYvHkzHBwc8O+//2Lq1Kmv/f98VaNGjSASibBnzx50794d6urqQkItJSUFXbt2rVJ7lalysqRv374YMmQIzMzMcP/+fXTr1g0AkJGRUWkmjoiIiIiIiIiIiOh9MHKaUNMhVComJgZjx45Fz549oaOjg2nTpuHGjRtSa1IEBQXh+PHjCA0NhY6ODmJiYuDm5ibsj46ORmBgINasWQNjY2NkZ2dXa5yrV69GaGiosF0+8mX9+vXw9fUF8OIh+saNG4U6tra2AICDBw/CxcUFioqK2LNnD8aNGwdHR0doamrCx8cHYWFhwjFaWlpITEzEpEmT4ODggDp16mDgwIHCi/qVGTZsGJ48eYI2bdpAUVER/v7+GD16dKXHtGrVCocOHcLs2bPRoUMHiMViNG3aVGqarf79+2PixIlQVFSEp6dnpW2Gh4ejbt26iIyMxNWrV6Grqws7OzvMmjVLqNOhQweUlZVJjD5xcXFBXFxcpeuVAICioiL8/PywZcsWIVlibW2NmJgYLFq0CDNnzkTHjh0RGRmJYcOGCceVlpZiwoQJuHnzJnR0dODu7i4kflRUVDBz5kxkZ2dDXV0dHTp0QHx8fIXnr6yukpISli1bhrCwMMybNw8dOnRAcnIy1q1bh9GjR8POzg4mJiaIiIhAcHBwpdf5KmNjY4SGhmLGjBnw8/PDsGHDsGHDBjx9+hS//PILEhISqtReZaqcLImNjYWpqSlu3LiBxYsXC1mc3NxcjB8/vtoCIyIiIiIiIiIiIvoUaWtrSyxSXlhYiNDQUKmH/Do6OhVOq1SuV69eEmuRyGvDhg1y1Zs/fz7mz5//2rZe116jRo2wb9++Suu0aNECiYmJcsX1MmVlZSxduhSrVq2qcL+sBFLr1q1fu/62rq4unj59WuG+V69ZJBLB398f/v7+MtvT09OTWovD09MTYrG40jjKBQQEwNLSEtevX0ejRo2EsoCAAIl6Q4cOFb5evny5zPbmzJmDOXPmVLjP1NRUIq7K6gLAyJEjMXLkSIkyW1tbHDt2TKKsf//+EtsVXfujR48ktufOnYu5c+dKlK1fvx5t2rRBu3btZMZUVVVOligrK1eY/Xn1P4SIiIiIiIiIiIiIpGVkZODvv/9GmzZt8PjxY2GUhYeHRw1HRh8yAwMDrFu3Djk5OUKy5HOlrKxcaSLoTSi8yUGbN2/G//73PxgZGeH69esAgKVLl+LXX3+t1uCIiIiIiIiISLaVK1fC1NQUampqaNu2LY4ePSqz7rlz59CvXz+YmppCJBJh6dKlUnXy8/MxZcoUNGrUCOrq6mjfvr3UG6FERFQ9oqKiYG1tDVdXVxQWFiIlJaXaFqqmT5enpyc6dOhQ02HUuJEjR6J58+bV2maVkyWrVq1CYGAgunXrhkePHgmLuuvq6lb4ixYRERERERERVb/t27cjMDAQISEhOHnyJKytreHm5oY7d+5UWL+oqAhNmjTBwoULYWBgUGGdkSNHIjExEZs3b8aZM2fQtWtXuLq64tatW+/yUoiIPju2trY4ceIECgoK8ODBAyQmJsLKykqiTnZ2NqZMmVIzAX4kkpOT+Uyaqk2VkyXLly/HmjVrMHv2bCgqKgrlDg4OOHPmTLUGR0REREREREQVi4mJwahRo+Dn54eWLVti9erV0NDQwPfff19h/datW2PJkiUYPHgwVFVVpfY/efIEO3fuxOLFi9GxY0c0a9YM8+fPR7NmzWTOA09ERET0qahysuTatWuwtbWVKldVVUVhYWG1BEVEREREREREspWUlODEiRNwdXUVyhQUFODq6or09PQ3avP58+coLS2FmpqaRLm6ujpSU1PfKl4iIiKiD12VkyWNGzdGZmamVHlCQgIsLCyqIyYiIiIiIiIiqsS9e/dQWlqK+vXrS5TXr18feXl5b9SmtrY2HB0dER4ejn/++QelpaX44YcfkJ6ejtzc3OoIm4iIiOiDpVTVAwIDAzFhwgQ8ffoUYrEYR48exbZt2xAZGYm1a9e+ixiJiIiIiIiI6D3YvHkzhg8fDmNjYygqKsLOzg5eXl44ceJETYdGRERE9E5VOVkycuRIqKurY86cOSgqKsKQIUNgZGSEuLg4DB48+F3ESEREREREREQv0dfXh6KiIm7fvi1Rfvv2bZmLt8ujadOmOHToEAoLC/Hvv//C0NAQgwYNQpMmTd42ZCIiIqIPWpWn4QIAb29vXLp0CQUFBcjLy8PNmzcxYsSI6o6NiIiIiIiIiCqgoqICe3t7JCUlCWVlZWVISkqCo6PjW7evqakJQ0NDPHz4EPv374eHh8dbt0lERET0IXujZEk5DQ0N1KtXr7piISIiIiIiIiI5BQYGYs2aNdi4cSOysrIwbtw4FBYWws/PDwAwbNgwzJw5U6hfUlKCzMxMZGZmoqSkBLdu3UJmZiYuX74s1Nm/fz8SEhJw7do1JCYmolOnTmjRooXQJhEREb3g6+sLT0/P937ejh07YuvWrcJ2Xl4eunTpAk1NTejq6r73eF62YcOG9xrDvXv3UK9ePdy8ebNa2qvyNFyNGzeGSCSSuf/q1atvFRARERERERERvd6gQYNw9+5dzJs3D3l5ebCxsUFCQoKw6HtOTg4UFP57R/Kff/6Bra2tsB0VFYWoqCg4OzsjOTkZAPD48WPMnDkTN2/ehJ6eHvr164cFCxZAWVn5vV4bEdHb2rNnz3s9X8+ePd/r+cqJRCL8/PPPVXpoHx8fDy8vL3h4eOCXX36ptO53332HrVu34uTJk8jPz8fDhw+lHoYvWLAAe/fuRWZmJlRUVPDo0SOpdnJycjBu3DgcPHgQWlpa8PHxQWRkJJSU/ns8XVxcjLCwMPzwww/Iy8uDoaEh5s2bh+HDh8t9be9TXFwcxGLxez3n7t27cfv2bYnlMGJjY5Gbm4vMzEzUqlXrvcViamqKKVOmYMqUKULZoEGD0L179/cWg76+PoYNG4aQkBCsW7furdurcrLk5YsHgGfPniEjIwMJCQmYOnXqWwdERERERERERPKZOHEiJk6cWOG+8gRIOVNT09c+1Bk4cCAGDhxYXeEREdEHJjs7G8HBwejQoYNc9YuKiuDu7g53d3eJ0YovKykpwYABA+Do6FjhA+vS0lL06NEDBgYGOHLkCHJzczFs2DAoKysjIiJCqDdw4EDcvn0b69atQ7NmzZCbm4uysrI3u9BKlJSUQEVF5a3beZ+JiXLLli2Dn5+fxMsQV65cgb29PczMzN57PK9SV1eHurr6ez2nn58f7O3tsWTJEujp6b1VW1Wehsvf31/iExwcjC1btiAsLAwXLlx4q2CIiIiIiIiIiIiIPnX5+fnw9vYW1oiKjY2Fi4uLxIvqpqamCA8Ph5eXFzQ1NWFsbIyVK1dK7AeAPn36QCQSCduylJaWwtvbG6GhoWjSpIlccU6ZMgUzZsxAu3btZNYJDQ1FQEAArKysKtz/xx9/4Pz58/jhhx9gY2ODbt26ITw8HCtXrkRJSQkAICEhAYcOHcK+ffvg6uoKU1NTODo6wsnJqdL4XFxchBcHatWqBX19fcydO1fi5YDy+zhs2DDo6Ohg9OjRAIDU1FR06NAB6urqMDExweTJk1FYWAgAmDVrFtq2bSt1Pmtra4SFhQGQnoarrKwMkZGRaNy4MdTV1WFtbY2ffvpJ2O/g4ICoqChh29PTE8rKyigoKAAA3Lx5EyKRSGJ6zJfdvXsX//d//4devXpJXNvOnTuxadMmiEQi+Pr6Ijs7GyKRCJmZmUK9R48eQSQSCS9SJCcnQyQSISkpCQ4ODtDQ0ED79u2lnu//9ttvaN26NdTU1KCvr48+ffoI9/369esICAiASCQSZqKqaBquVatWoWnTplBRUUHz5s2xefNmif0ikQhr165Fnz59oKGhATMzM+zevVvY//DhQ3h7e6Nu3bpQV1eHmZkZ1q9fL+y3tLSEkZERfv755wrvW1W81ZolL+vWrRt27txZXc0RERERffA0NRQhvmAN8QVraGoo1nQ4RERERET0kQgMDERaWhp2796NxMREpKSk4OTJk1L1lixZAmtra2RkZGDGjBnw9/dHYmIiAODYsWMAgPXr1yM3N1fYliUsLAz16tXDiBEjqv+CKpGeng4rKythmkgAcHNzw7///otz584BeDG9lIODAxYvXgxjY2OYm5sjODgYT548eW37GzduhJKSEo4ePYq4uDjExMRg7dq1EnWioqKE+zh37lxcuXIF7u7u6NevH06fPo3t27cjNTVVGK3p7e2No0eP4sqVK0Ib586dw+nTpzFkyJAK44iMjMSmTZuwevVqnDt3DgEBAfjqq69w6NAhAJCY9lIsFiMlJQW6urpITU0FABw6dAjGxsZo1qxZhe2npqZCQ0MDFhYWQtmxY8fg7u6OgQMHIjc3F3Fxca+9Xy+bPXs2oqOjcfz4cSgpKUlMebZ371706dMH3bt3R0ZGBpKSktCmTRsAwK5du9CgQQOEhYUhNzcXubm5Fbb/888/w9/fH0FBQTh79izGjBkDPz8/HDx4UKJeaGgoBg4ciNOnT6N79+7w9vbGgwcPAABz587F+fPn8fvvvyMrKwurVq2Cvr6+xPFt2rRBSkpKla69IlWehkuWn3766a2HuRARERERERERERF9yvLz87Fx40Zs3boVnTt3BvAi4WFkZCRV18nJCTNmzAAAmJubIy0tDbGxsejSpQvq1q0LANDV1YWBgUGl50xNTcW6deskRhu8L3l5eRKJEgDCdl5eHoAX62CnpqZCTU0NP//8M+7du4fx48fj/v37EqMIKmJiYoLY2FiIRCI0b94cZ86cQWxsLEaNGiXU+fLLLxEUFCRsjxw5Et7e3sJIHjMzMyxbtgzOzs5YtWoVLC0tYW1tja1bt2Lu3LkAgC1btqBt27YVJjOKi4sRERGBAwcOwNHREQDQpEkTpKam4ttvv4WzszNcXFywbt06lJaW4uzZs1BRUcGgQYOQnJwMd3d3JCcnw9nZWeZ1Xr9+HfXr15eYgqtu3bpQVVWFurq68D3w8OHDSu/XyxYsWCCcc8aMGejRoweePn0KNTU1LFiwAIMHD0ZoaKhQ39raGgCgp6cHRUVFaGtrV/q9FxUVBV9fX4wfPx7AiyThn3/+iaioKHTq1Emo5+vrCy8vLwBAREQEli1bhqNHj8Ld3R05OTmwtbWFg4MDAFQ4gsrIyAgZGRlyX7csVR5ZYmtrCzs7O+Fja2sLQ0NDzJo1C7NmzXrrgIiIiIiIiIiIiIg+VVevXsWzZ8+Et/SBF+tfNG/eXKpu+YP3l7ezsrJktp2TkwMtLS3hExERgfz8fAwdOhRr1qyReiO/XEREhMRxOTk5b3h1b6asrAwikQhbtmxBmzZt0L17d8TExGDjxo148uQJUlJSJOLbsmWLcGy7du2EaaCAF/fo0qVLKC0tFcrKH7SXO3XqFDZs2CDRppubG8rKynDt2jUAL0aXbN26FcCLkSDbtm2Dt7d3hfFfvnwZRUVF6NKli0SbmzZtEkandOjQAfn5+cjIyMChQ4eEBEr5aJNDhw7BxcVF5j168uQJ1NTU5L+pcmjVqpXwtaGhIQDgzp07AIDMzEwhmfemsrKypKZSc3JykvoefjkOTU1N6OjoCHGMGzcO8fHxsLGxwbRp03DkyBGp86irq6OoqOitYgXeYGTJy/OwAYCCggLq1q0LFxcXtGjR4q0DIiIiIiIiIiIiIqKqMzIykhg9oqenhytXriA7O1tirYvyhdOVlJRw4cIFjB07FgMHDpRop7oYGBjg6NGjEmW3b98W9gEvHtQbGxtLLJpuYWEBsViMmzdvwsHBQeK6Xh2p8jqampoS2wUFBRgzZgwmT54sVbdhw4YAAC8vL0yfPh0nT57EkydPcOPGDQwaNKjC9svXHdm7dy+MjY0l9qmqqgJ4MQLI2toaycnJSE9PR5cuXdCxY0cMGjQIFy9exKVLlyodWaKvry/XqJHykScvr9vy7NmzCusqKysLX5cnnMq/N97nQu0vx1EeS3kc3bp1w/Xr17Fv3z4kJiaic+fOmDBhgsT6Lw8ePBBGWr2NKidLQkJC3vqkRERERERERERERJ+jJk2aQFlZGceOHRMezD9+/BgXL15Ex44dJer++eefUtsvr1mhrKwsMYJCSUlJapooDQ0NnDlzRqJszpw5yM/PR1xcHExMTKCiovLOllhwdHTEggULcOfOHdSrVw8AkJiYCB0dHbRs2RLAi9EGO3bsQEFBAbS0tAAAFy9ehIKCAho0aAB1dXWZa3n89ddfEtt//vknzMzMoKgoe11JOzs7nD9/XmabANCgQQM4Oztjy5YtePLkCbp06SLE/6qWLVtCVVUVOTk5lSY8nJ2dcfDgQRw9ehQLFiyAnp4eLCwssGDBAhgaGsLc3Fzmsba2tsjLy8PDhw9Ru3ZtmfXKkwa5ubmwtbUFgDeafq1Vq1ZISkqCn59fhftVVFQkvvcqYmFhgbS0NPj4+AhlaWlpwv+7vOrWrQsfHx/4+PigQ4cOmDp1qkSy5OzZs5WOypFXlZMlt27dws6dO3Hx4kVhBfuBAwdW+h9ERERERERERDWnsLBQePhUUFAg9YYtERG9P9ra2vDx8cHUqVOhp6eHevXqISQkBAoKChLTSQEvHiwvXrwYnp6eSExMxI4dO7B3715hv6mpKZKSkuDk5ARVVdUKn9Gqqanhiy++kCjT1dUFAKnyV+Xl5SEvLw+XL18GAJw5cwba2tpo2LChkFzJycnBgwcPkJOTg9LSUuHBfLNmzaClpYWuXbuiZcuWGDp0KBYvXoy8vDzMmTMHEyZMEEZdDBkyBOHh4fDz80NoaCju3buHqVOnYvjw4a8d4ZCTk4PAwECMGTMGJ0+exPLlyxEdHV3pMdOnT0e7du0wceJEjBw5Epqamjh//jwSExOxYsUKoZ63tzdCQkJQUlKC2NhYme1pa2sjODgYAQEBKCsrw//+9z88fvwYaWlp0NHREZIFLi4uWL58OerWrSvM0uTi4oIVK1ZgwIABlcZsa2sLfX19pKWloWfPnjLrqauro127dli4cCEaN26MO3fuYM6cOZW2XZGQkBB07twZTZs2xeDBg/H8+XPs27cP06dPB/Die+/w4cMYPHgwVFVVK5ziberUqRg4cCBsbW3h6uqK3377Dbt27cKBAwfkjmPevHmwt7eHpaUliouLsWfPHomEYVFREU6cOIGIiIgqX+OrqpQs+eabbxAYGIiSkhLo6OgAAP79918EBgZi7dq18PLyglgsRmZmppC1IiIiIiIiIiIiInqfKnuY/CGIiYnB2LFj0bNnT+jo6GDatGm4ceOG1JoUQUFBOH78OEJDQ6Gjo4OYmBi4ubkJ+6OjoxEYGIg1a9bA2NgY2dnZ1Rrn6tWrJRb4Lh/5sn79evj6+gJ48TB748aNQp3y58IHDx6Ei4sLFBUVsWfPHowbNw6Ojo7Q1NSEj48PwsLChGO0tLSQmJiISZMmwcHBAXXq1MHAgQPx9ddfvzbGYcOG4cmTJ2jTpg0UFRXh7++P0aNHV3pMq1atcOjQIcyePRsdOnSAWCxG06ZNpabZ6t+/PyZOnAhFRUWp5SleFR4ejrp16yIyMhJXr16Frq4u7OzsJNb57tChA8rKyiRGn7i4uCAuLu61IyMUFRXh5+eHLVu2vPb7+/vvv8eIESNgb2+P5s2bY/HixejatWulx7zKxcUFO3bsQHh4OBYuXAgdHR2JkU9hYWEYM2YMmjZtiuLiYolpv8p5enoiLi4OUVFR8Pf3R+PGjbF+/foqjQJRUVHBzJkzkZ2dDXV1dXTo0AHx8fHC/l9//RUNGzZEhw4dqnR9FZE7WbJ3715MnjwZU6ZMQVBQkLDgS25uLpYsWQIfHx+YmJjgm2++QYsWLZgsISIiIiIiIiIiIqqAtra2xCLlhYWFCA0NlXrIr6Ojgx9//FFmO7169ZJYi0ReGzZskKve/PnzMX/+/Ne29br2GjVqhH379lVap0WLFkhMTJQrrpcpKytj6dKlWLVqVYX7ZSWQWrdujT/++KPStnV1dfH06dMK9716zSKRCP7+/vD395fZnp6enrAWRzlPT88KEw0VCQgIgKWlJa5fv45GjRoBAH755RepehYWFlILob98DhcXF6lz2tjYSJX17dsXffv2rTCWdu3a4dSpUxJlvr6+QhKt3Lhx4zBu3DiZ11TRtT969Ej4es6cOZWOjImLi8O8efNk7q8KuZMlS5YswYwZM6SyeYaGhoiJiYGGhga6dOkCAwMDREZGVktwRERERERERERERJ+ajIwM/P3332jTpg0eP34sjLLw8PCo4cjoQ2ZgYIB169YhJydHSJZ8zu7du4e+ffvCy8urWtpTkLfiyZMnMXToUJn7hw4diuLiYhw6dIj/UURERERERERERESViIqKgrW1NVxdXVFYWIiUlJQK130gepmnp2e1TDn1KdDX18e0adOk1vp5U3KPLCktLYWysrLM/crKylBXV0fDhg2rJTAiIiIiIiIiIiKiT5GtrS1OnDhRaZ3qXn/kU5ScnFzTIdAnRO6RJZaWlvj1119l7v/ll19gaWlZLUERERERERERERERERG9L3KPLJkwYQLGjRsHVVVVjB49GkpKLw59/vw5vv32W8yZMwfffPPNOwuUiIiIiIiIiIiIiIjoXZA7WeLj44MzZ85g4sSJmDlzJpo2bQqxWIyrV6+ioKAAkydPllrpnoiIiKiqtl0YIFe9p0XPha9/vPgV1DTk+7XGq/mON4qLiIiIiIiIiD5dcidLgBeLDvXv3x/btm3DpUuXAAAdO3aEl5cX2rVr904CJCIiIiIioo+bhroqbqWuqNEY1NTU8Ntvv9VoDERERET04apSsgQA2rVrx8QIERERERERERERERF9MuRe4J2IiIiIiIiIiIiIiOhTxGQJERERERERERERERF91pgsISIiIiIiIiIiIiKizxqTJURERERERERERERE9Fmr8gLvL7t37x7++usvlJaWonXr1jA0NKyuuIiIiIiIiIiIiIiIiN6LN06W7Ny5EyNGjIC5uTmePXuGCxcuYOXKlfDz86vO+IiIiIiIiIiIiIiIiN4puafhKigokNgODQ3F0aNHcfToUWRkZGDHjh2YPXt2tQdIRERERERERERERET0LsmdLLG3t8evv/4qbCspKeHOnTvC9u3bt6GiolK90REREREREREREREREb1jck/DtX//fkyYMAEbNmzAypUrERcXh0GDBqG0tBTPnz+HgoICNmzY8A5DJSIiIiIiIiIiIiIiqn5yjywxNTXF3r17MXDgQDg7OyMzMxOXL19GYmIiDhw4gJycHHTv3v2Ngli5ciVMTU2hpqaGtm3b4ujRozLrrlmzBh06dEDt2rVRu3ZtuLq6VlqfiIiIiIiIiIiIiIioMnInS8p5eXnh2LFjOHXqFFxcXFBWVgYbGxuoqam9UQDbt29HYGAgQkJCcPLkSVhbW8PNzU1iiq+XJScnw8vLCwcPHkR6ejpMTEzQtWtX3Lp1643OT0REREREREREREREn7cqJUv27duH6OhoHD9+HGvXrsXixYvh7e2NqVOn4smTJ28UQExMDEaNGgU/Pz+0bNkSq1evhoaGBr7//vsK62/ZsgXjx4+HjY0NWrRogbVr16KsrAxJSUkV1i8uLsa///4r8SEiIiIiIiIiIiIiIiond7IkKCgIfn5+OHbsGMaMGYPw8HA4Ozvj5MmTUFNTg62tLX7//fcqnbykpAQnTpyAq6vrfwEpKMDV1RXp6elytVFUVIRnz55BT0+vwv2RkZGoVauW8DExMalSjERERERERERERERE9GmTO1myYcMG7Nu3D/Hx8Th27Bg2b94MAFBRUUF4eDh27dqFiIiIKp383r17KC0tRf369SXK69evj7y8PLnamD59OoyMjCQSLi+bOXMmHj9+LHxu3LhRpRiJiIiIiIiIiIiIiOjTpiRvRU1NTVy7dg329va4ceOG1BolLVu2REpKSrUHWJmFCxciPj4eycnJMtdMUVVVhaqq6nuNi4iIiIiIiIiIiIiIPh5yJ0siIyMxbNgwTJ48GUVFRdi4ceNbn1xfXx+Kioq4ffu2RPnt27dhYGBQ6bFRUVFYuHAhDhw4gFatWr11LERERERERERERERE9HmSO1ni7e0Nd3d3XL16FWZmZtDV1X3rk6uoqMDe3h5JSUnw9PQEAGGx9okTJ8o8bvHixViwYAH2798PBweHt46DiIiIiIiI6GM0JmWrXPWePXkqfD0pbTuU1SueneFV33YY8kZxEREREX1s5E6WAECdOnVQp06dag0gMDAQPj4+cHBwQJs2bbB06VIUFhbCz88PADBs2DAYGxsjMjISALBo0SLMmzcPW7duhampqbC2iZaWFrS0tKo1NiIiIiIiIiIiIiIi+vRVKVnyLgwaNAh3797FvHnzkJeXBxsbGyQkJAiLvufk5EBB4b916FetWoWSkhL0799fop2QkBDMnz//fYZORERERERERERERESfgBpPlgDAxIkTZU67lZycLLGdnZ397gMiIiIiIiIiIiIiIqLPhsLrqxAREREREREREREREX26mCwhIiIiIiIiIiIiIqLPGpMlRERERERERERERET0WWOyhIiIiIiIiIiIiIiIPmtMlhARERERERERERER0WeNyRIiIiIiIiIiIiIiIvqsMVlCRERERERERERERESfNaWaDoCIiIjoTahpKGHr3/1rOgwiIiIiIiIi+gRwZMknauXKlTA1NYWamhratm2Lo0ePVlp/x44daNGiBdTU1GBlZYV9+/ZJ7Pf19YVIJJL4uLu7v8tLIKLPAPsqIiIiIiIiIiL6EDBZ8gnavn07AgMDERISgpMnT8La2hpubm64c+dOhfWPHDkCLy8vjBgxAhkZGfD09ISnpyfOnj0rUc/d3R25ubnCZ9u2be/jcojoE8W+ioiIiIiIiIiIPhRMlnyCYmJiMGrUKPj5+aFly5ZYvXo1NDQ08P3331dYPy4uDu7u7pg6dSosLCwQHh4OOzs7rFixQqKeqqoqDAwMhE/t2rXfx+UQ0SeKfRUREREREREREX0omCz5xJSUlODEiRNwdXUVyhQUFODq6or09PQKj0lPT5eoDwBubm5S9ZOTk1GvXj00b94c48aNw/3796v/Aojos8C+ioiIiIiIiIiIPiRMlnxi7t27h9LSUtSvX1+ivH79+sjLy6vwmLy8vNfWd3d3x6ZNm5CUlIRFixbh0KFD6NatG0pLS6v/Iojok8e+ioiIiIiIiIiIPiRKNR0AfRwGDx4sfG1lZYVWrVqhadOmSE5ORufOnWswMiKi/7CvIiIiIiIiIiKiN8GRJZ8YfX19KCoq4vbt2xLlt2/fhoGBQYXHGBgYVKk+ADRp0gT6+vq4fPny2wdNRJ8d9lVERERERERERPQhYbLkE6OiogJ7e3skJSUJZWVlZUhKSoKjo2OFxzg6OkrUB4DExESZ9QHg5s2buH//PgwNDasncCL6rLCvIiIiIiIiIiKiDwmTJZ+gwMBArFmzBhs3bkRWVhbGjRuHwsJC+Pn5AQCGDRuGmTNnCvX9/f2RkJCA6Oho/P3335g/fz6OHz+OiRMnAgAKCgowdepU/Pnnn8jOzkZSUhI8PDzQrFkzuLm51cg1EtHHj30VERERERERERF9KLhmySdo0KBBuHv3LubNm4e8vDzY2NggISFBWBg5JycHCgr/5cnat2+PrVu3Ys6cOZg1axbMzMzwyy+/4IsvvgAAKCoq4vTp09i4cSMePXoEIyMjdO3aFeHh4VBVVa2RaySijx/7KiIiIiIiIiIi+lAwWfKJmjhxovC29auSk5OlygYMGIABAwZUWF9dXR379++vzvCIiACwryIiIiIiIiIiog8Dp+EiIiIiIiIiIiIiIqLPGpMlRERERERERERERET0WWOyhIiIiIiIiIiIiIiIPmtMlhARERERERERERER0WeNC7wTERERERERfeKU1dUw+vCWmg6DiIiI6IPFkSWEwsJCiEQiiEQiFBYW1nQ4RERS2E8REREREREREdG7xGQJERERERERERERERF91pgsISIiIiIiIiIiIiKizxqTJURERERERERERERE9FljsoSIiIiIiIiIiIiIiD5rTJYQEREREREREREREdFnjckSIiIiIiIiIiIiIiL6rDFZQkREREREREREREREnzUmS4iIiIiIiIiIiIiI6LPGZAkREREREREREREREX3WmCwhIiIiIiIiIiIiIqLPGpMlRERERERERERERET0WWOyhIiIiIiIiIiIiIiIPmtMlhARERERERERERER0WeNyRIiIiIiIiIiIiIiIvqsMVlCRERERERERERERESfNaWaDoDenTEpW+Wq9+zJU+HrSWnboayuJtdx33YY8kZxERGVYz9FREREREREREQfAo4sISIiIiIiIiIiIiKizxqTJURERERERERERERE9FljsoSIiIiIiIiIiIiIiD5rTJYQEREREREREREREdFnjckSIiIiIiIiIiIiIiL6rDFZQkREREREREREREREnzUmS4iIiIiIiIiIiIiI6LPGZAkREREREREREREREX3WmCwhIiIiIiIiIiIiIqLPGpMlRERERERERERERET0WfsgkiUrV66Eqakp1NTU0LZtWxw9erTS+jt27ECLFi2gpqYGKysr7Nu37z1FSkREREREREREREREn5oaT5Zs374dgYGBCAkJwcmTJ2FtbQ03NzfcuXOnwvpHjhyBl5cXRowYgYyMDHh6esLT0xNnz559z5ETEREREREREREREdGnoMaTJTExMRg1ahT8/PzQsmVLrF69GhoaGvj+++8rrB8XFwd3d3dMnToVFhYWCA8Ph52dHVasWPGeIyciIiIiIiIiIiIiok+BUk2evKSkBCdOnMDMmTOFMgUFBbi6uiI9Pb3CY9LT0xEYGChR5ubmhl9++aXC+sXFxSguLha2Hz9+DAD4999/3zL6D19JYZFc9Z49+e/+lBQ+gbisTK7j5LmHpU9L5GrrTSnK+f/49EnBO41DnnuR/7TwncagIUcMRQXP3mkMcv9cFZS+0zggz/9H4ZN3HIJ896KoSL6f03cdR01hP/Uf9lP/+SD6KvZTAvZTH8b1fwh9Ffup/7Cf+s+H0Fexn/owrp/91H8+hL6K/dR/2E99GsqvUSwW13AkRPQpE4lrsJf5559/YGxsjCNHjsDR0VEonzZtGg4dOoS//vpL6hgVFRVs3LgRXl5eQtk333yD0NBQ3L59W6r+/PnzERoa+m4ugIiIiIiIiIiIiN6LGzduoEGDBjUdBhF9omp0ZMn7MHPmTImRKGVlZXjw4AHq1KkDkUhUg5ERSfv3339hYmKCGzduQEdHp6bDISKSwn6KiD4G7KuI6EPHfoqoasRiMfLz82FkZFTToRDRJ6xGkyX6+vpQVFSUGhFy+/ZtGBgYVHiMgYFBleqrqqpCVVVVokxXV/fNgyZ6D3R0dPgLMxF90NhPEdHHgH0VEX3o2E8Rya9WrVo1HQIRfeJqdIF3FRUV2NvbIykpSSgrKytDUlKSxLRcL3N0dJSoDwCJiYky6xMREREREREREREREVWmxqfhCgwMhI+PDxwcHNCmTRssXboUhYWF8PPzAwAMGzYMxsbGiIyMBAD4+/vD2dkZ0dHR6NGjB+Lj43H8+HF89913NXkZRERERERERERERET0karxZMmgQYNw9+5dzJs3D3l5ebCxsUFCQgLq168PAMjJyYGCwn8DYNq3b4+tW7dizpw5mDVrFszMzPDLL7/giy++qKlLIKo2qqqqCAkJkZo6jojoQ8F+iog+BuyriOhDx36KiIjowyMSi8Ximg6CiIiIiIiIiIiIiIioptTomiVEREREREREREREREQ1jckSIiIiIiIiIiIiIiL6rDFZQkREREREREREREREnzUmS4iIiIiIiIiIiIiI6LPGZAnRO+Lr6wtPT8/3es6SkhI0a9YMR44cea/nldeGDRugq6srbK9evRq9evWquYCIPgPsi95MVe7bjBkzMGnSpHcbENFHRCQS4Zdffqm0Tk30TR+T7OxsiEQiZGZm1nQoRJ+U5ORkiEQiPHr06INop6rmz58PGxub93pOIiKizwmTJfTBEYlElX7mz59f0yHKJS4uDhs2bBC2XVxcMGXKlHd6ztWrV6Nx48Zo3769ULZgwQK0b98eGhoaEomKypiammLp0qXvJsiXDB8+HCdPnkRKSso7PxdRVbEvenOv9kXZ2dkYMWIEGjduDHV1dTRt2hQhISEoKSmROE4sFiMqKgrm5uZQVVWFsbExFixYIPM8H8rDxODgYGzcuBFXr16t0TiI3oSvry9EIhHGjh0rtW/ChAkQiUTw9fV94/Zl/Zy+2jd9LMqvR1FREbdu3ZLYl5ubCyUlJYhEImRnZ8vdJhNHRPIp769EIhGUlZXRuHFjTJs2DU+fPn2n563od6f27dsjNzcXtWrVeqfnrqryPqr8o62tDUtLS0yYMAGXLl2qcnvv6+9CIiKiDwWTJfTByc3NFT5Lly6Fjo6ORFlwcHBNh1ip0tJSlJWVoVatWnInJ6ri1YeL5cRiMVasWIERI0ZI1R8wYADGjRtX7bG8LRUVFQwZMgTLli2r6VCIpLAvqlxV+qK///4bZWVl+Pbbb3Hu3DnExsZi9erVmDVrlsSx/v7+WLt2LaKiovD3339j9+7daNOmTbXHXt309fXh5uaGVatW1XQoRG/ExMQE8fHxePLkiVD29OlTbN26FQ0bNnwn53xXfdPLnj179s7aNjY2xqZNmyTKNm7cCGNj43d2TiIC3N3dkZubi6tXryI2NhbffvstQkJC3nscKioqMDAwgEgkeu/nlseBAweQm5uLU6dOISIiAllZWbC2tkZSUlJNh0ZERPRBY7KEPjgGBgbCp1atWhCJRDAwMIC2tjbMzc2RkJAgUf+XX36BpqYm8vPzhTdp4uPj0b59e6ipqeGLL77AoUOHJI45e/YsunXrBi0tLdSvXx9Dhw7FvXv3AAB79uyBrq4uSktLAQCZmZkQiUSYMWOGcPzIkSPx1VdfAfhvaqndu3ejZcuWUFVVRU5OjsRbgr6+vjh06BDi4uKEt3zK3zisLBbgxZtMEydOxJQpU4QHchU5ceIErly5gh49ekiUh4aGIiAgAFZWVnLdfxcXF1y/fh0BAQFCrOV27twJS0tLqKqqwtTUFNHR0RLHPnz4EMOGDUPt2rWhoaGBbt26vfYNpl69emH37t0SD2iIPgTsi6qvL3J3d8f69evRtWtXNGnSBL1790ZwcDB27dol1MnKysKqVavw66+/onfv3mjcuDHs7e3RpUsXmf9HjRs3BgDY2tpCJBLBxcUFAFBWVoawsDA0aNAAqqqqsLGxkfr/OnPmDL788kuoq6ujTp06GD16NAoKCmSe66effoKVlZVQ39XVFYWFhcL+Xr16IT4+XubxRB8yOzs7mJiYSPxM7tq1Cw0bNoStra1E3YreMraxsZE52k7Wz+nLfdN3330HIyMjlJWVSRzr4eGB4cOHC9u//vor7OzsoKamhiZNmiA0NBTPnz8X9otEIqxatQq9e/eGpqYmFixYgIcPH8Lb2xt169aFuro6zMzMsH79euGYGzduYODAgdDV1YWenh48PDzkGhXi4+Mj0Q4ArF+/Hj4+PhJlpaWlEiPrmjdvjri4OGH//PnzsXHjRvz6669Cv5ycnCzsv3r1Kjp16gQNDQ1YW1sjPT39tbERfcpUVVVhYGAAExMTeHp6wtXVFYmJicL+srIyREZGCj9z1tbW+Omnn2S2d//+fXh5ecHY2BgaGhqwsrLCtm3bhP2yfneqaBqu1/2tZGpqioiICAwfPhza2tpo2LAhvvvuO4k606dPh7m5OTQ0NNCkSRPMnTv3jRK/derUgYGBAZo0aQIPDw8cOHAAbdu2xYgRI4TfLa9cuQIPDw/Ur18fWlpaaN26NQ4cOCC0IevvwtfdMyIioo8ZkyX00dDU1MTgwYMr/MO0f//+0NbWFsqmTp2KoKAgZGRkwNHREb169cL9+/cBAI8ePcKXX34JW1tbHD9+HAkJCbh9+zYGDhwIAOjQoQPy8/ORkZEBADh06BD09fUl/nA9dOiQ8Mc+ABQVFWHRokVYu3Ytzp07h3r16knEGBcXB0dHR4waNUp4K93ExOS1sZTbuHEjVFRUkJaWhtWrV1d4f1JSUmBubi5xH97Erl270KBBA4SFhQmxAi8egA4cOBCDBw/GmTNnMH/+fMydO1diCg1fX18cP34cu3fvRnp6OsRiMbp3717pL/gODg54/vw5/vrrr7eKm+h9YV9UPX3R48ePoaenJ2z/9ttvaNKkCfbs2YPGjRvD1NQUI0eOxIMHD2S2cfToUQD/vT1Z/qA3Li4O0dHRiIqKwunTp+Hm5obevXsLydvCwkK4ubmhdu3aOHbsGHbs2IEDBw5g4sSJFZ4nNzcXXl5eGD58OLKyspCcnIy+fftCLBYLddq0aYObN29Waeodog/J8OHDJfq177//Hn5+fm/drqyf05cNGDAA9+/fx8GDB4WyBw8eICEhAd7e3gBe9C3Dhg2Dv78/zp8/j2+//RYbNmyQmqpv/vz56NOnD86cOYPhw4dj7ty5OH/+PH7//XchKauvrw/gxcgTNzc3aGtrIyUlBWlpadDS0oK7u7vM0XPlevfujYcPHyI1NRUAkJqaiocPH0qtxVZWVoYGDRpgx44dOH/+PObNm4dZs2bhxx9/BPBiGr+BAwcKb8vn5uZKTKc6e/ZsBAcHIzMzE+bm5vDy8pJIEBF9zs6ePYsjR45ARUVFKIuMjMSmTZuwevVqnDt3DgEBAfjqq6+kXlgp9/TpU9jb22Pv3r04e/YsRo8ejaFDhwp9l6zfnV4lz99KABAdHQ0HBwdkZGRg/PjxGDduHC5cuCDs19bWxoYNG3D+/HnExcVhzZo1iI2Nfet7paCgAH9/f1y/fh0nTpwAABQUFKB79+5ISkpCRkYG3N3d0atXL+Tk5ACQ/Xfh6+4ZERHRR01M9AFbv369uFatWsL2X3/9JVZUVBT/888/YrFYLL59+7ZYSUlJnJycLBaLxeJr166JAYgXLlwoHPPs2TNxgwYNxIsWLRKLxWJxeHi4uGvXrhLnuXHjhhiA+MKFC2KxWCy2s7MTL1myRCwWi8Wenp7iBQsWiFVUVMT5+fnimzdvigGIL168KMQIQJyZmSnRpo+Pj9jDw0PYdnZ2Fvv7+0vUkScWZ2dnsa2t7Wvvlb+/v/jLL7+Uuf/Ve1mZRo0aiWNjYyXKhgwZIu7SpYtE2dSpU8UtW7YUi8Vi8cWLF8UAxGlpacL+e/fuidXV1cU//vhjpTHUrl1bvGHDBrliI6oJ7Iuqry8Si8XiS5cuiXV0dMTfffedUDZmzBixqqqquG3btuLDhw+LDx48KLaxsRF36tRJZjvl9zkjI0Oi3MjISLxgwQKJstatW4vHjx8vFovF4u+++05cu3ZtcUFBgbB/7969YgUFBXFeXp5YLJa8bydOnBADEGdnZ8uM5fHjx2IAwvcA0cei/Hv9zp07YlVVVXF2drY4OztbrKamJr57967Yw8ND7OPjI9Sv6HcEa2trcUhIiLANQPzzzz+LxWLZP6ev9k0eHh7i4cOHC9vffvut2MjISFxaWioWi8Xizp07iyMiIiTa2Lx5s9jQ0FDivFOmTJGo06tXL7Gfn1+F175582Zx8+bNxWVlZUJZcXGxWF1dXbx///4Kj3n5eqZMmSK07efnJw4ICBBnZGSIAYivXbtW4fFisVg8YcIEcb9+/WTei5fPs3btWqHs3LlzYgDirKwsmW0Tfcp8fHzEioqKYk1NTbGqqqoYgFhBQUH8008/icVisfjp06diDQ0N8ZEjRySOGzFihNjLy0ssFovFBw8eFAMQP3z4UOZ5evToIQ4KChK2K/rd6dV2Xve3klj8ov/86quvhO2ysjJxvXr1xKtWrZIZy5IlS8T29vbCdkhIiNja2lpmfVl9rlgsFmdlZYkBiLdv3y7zeEtLS/Hy5cslYn61z6/Iq/eMiIjoY8WRJfRRadOmDSwtLbFx40YAwA8//IBGjRqhY8eOEvUcHR2Fr5WUlODg4ICsrCwAwKlTp3Dw4EFoaWkJnxYtWgB4MRQZAJydnZGcnAyxWIyUlBT07dsXFhYWSE1NxaFDh2BkZAQzMzPhHCoqKmjVqlWVr0eeWADA3t7+tW09efIEampqVY5BXllZWXBycpIoc3JywqVLl1BaWoqsrCwoKSmhbdu2wv46deqgefPmwr2XRV1dHUVFRe8kbqJ3gX2RbK/ri27dugV3d3cMGDAAo0aNEsrLyspQXFyMTZs2oUOHDnBxccG6detw8OBBiTcuX+fff//FP//8U2F/VX7vy+ft1tTUlNhfVlZW4bmsra3RuXNnWFlZYcCAAVizZg0ePnwoUUddXR0A2JfRR6tu3bro0aMHNmzYgPXr16NHjx7CCIz3wdvbGzt37kRxcTEAYMuWLRg8eDAUFF78uXLq1CmEhYVJ9FPlb3q//HPn4OAg0e64ceMQHx8PGxsbTJs2DUeOHBH2nTp1CpcvX4a2trbQpp6eHp4+fSrR98kyfPhw7NixA3l5edixY4fElGEvW7lyJezt7VG3bl1oaWnhu+++E97cfp2X+3RDQ0MAwJ07d+Q6luhT1KlTJ2RmZuKvv/6Cj48P/Pz80K9fPwDA5cuXUVRUhC5dukj0FZs2bZL5M11aWorw8HBYWVlBT08PWlpa2L9/v9w/o+Ve97dSuZd/psuneH35Z3r79u1wcnKCgYEBtLS0MGfOnCrHIov4/4+ILZ9Oq6CgAMHBwbCwsICuri60tLSQlZX12vNV1z0jIiL6ECnVdABEVTVy5EisXLkSM2bMwPr16+Hn51elhfUKCgrQq1cvLFq0SGpf+R+hLi4u+P7773Hq1CkoKyujRYsWcHFxQXJyMh4+fAhnZ2eJ49TV1d9ocT95YgEg8UBPFn19fZw5c6bKMXwIHjx4gLp169Z0GERVwr6oYpX1Rf/88w86deqE9u3bS83RbWhoCCUlJZibmwtlFhYWAICcnBw0b95crmt5FxQVFZGYmIgjR47gjz/+wPLlyzF79mz89ddfwnoM5dOFsS+jj9nw4cOF6ehWrlxZYR0FBQWJKeiA6llIvVevXhCLxdi7dy9at26NlJQUialnCgoKEBoair59+0od+3KC9tV+qlu3brh+/Tr27duHxMREdO7cGRMmTEBUVBQKCgpgb2+PLVu2SLUpz8+ylZUVWrRoAS8vL1hYWOCLL75AZmamRJ34+HgEBwcjOjoajo6O0NbWxpIlS+SeflRZWVn4urx/f3VtF6LPiaamJpo1awbgxXSB1tbWWLduHUaMGCGsPbZ3714YGxtLHKeqqlphe0uWLEFcXByWLl0KKysraGpqYsqUKa+diu9NvfwzDbz4uS7/mU5PT4e3tzdCQ0Ph5uaGWrVqIT4+XmrtkzdV/tJI+e8uwcHBSExMRFRUFJo1awZ1dXX079//tdf+vu8ZERHR+8SRJfTR+eqrr3D9+nUsW7YM58+fl1pIEwD+/PNP4evnz5/jxIkTwkM3Ozs7nDt3DqampmjWrJnEp/wP7PK1AmJjY4WHkeUPKJOTkyXWCJCXioqKxFtF8sYiL1tbW/z9999SDzDeREWxWlhYIC0tTaIsLS0N5ubmUFRUhIWFhdTaI/fv38eFCxfQsmVLmee6cuUKnj59KrWALNGHjn1RxWT1Rbdu3YKLiwvs7e2xfv164W3xck5OTnj+/LnEm58XL14EADRq1EjmtQCQuB4dHR0YGRlV2F+V90UWFhY4deqUxALtaWlpUFBQkJmUEYlEcHJyQmhoKDIyMqCiooKff/5Z2H/27FkoKyvD0tKy4htD9BEoX6ujfC2PitStW1eYtx54MZrr2rVrMtus6Oe0Impqaujbty+2bNmCbdu2oXnz5rCzsxP229nZ4cKFC1J9VLNmzaT6k4pi9vHxwQ8//IClS5cKyVo7OztcunQJ9erVk2qzVq1albZZbvjw4UhOTpY5qiQtLQ3t27fH+PHjYWtri2bNmkm94V5Rv0xEr6egoIBZs2Zhzpw5ePLkCVq2bAlVVVXk5ORI/UxXtM4I8OJn1MPDA1999RWsra3RpEkT4fePcvL8jL7ubyV5HDlyBI0aNcLs2bPh4OAAMzMzXL9+Xa5jX6esrAzLli1D48aNhb+70tLS4Ovriz59+sDKygoGBgZSa69VdO3y3DMiIqKPFZMl9NGpXbs2+vbti6lTp6Jr165o0KCBVJ2VK1fi559/xt9//40JEybg4cOHwh+xEyZMwIMHD+Dl5YVjx47hypUr2L9/P/z8/IRfBGvXro1WrVphy5YtwsPIjh074uTJk7h48aLU29zyMDU1xV9//YXs7Gzcu3cPZWVlcsUir06dOqGgoADnzp2TKM/JyUFmZiZycnJQWlqKzMxMZGZmCm9eyYr18OHDuHXrFu7duwcACAoKQlJSEsLDw3Hx4kVs3LgRK1asQHBwMADAzMwMHh4eGDVqFFJTU3Hq1Cl89dVXMDY2hoeHh8xzpaSkoEmTJmjatGmVrpeoprEvqlhFfVF5oqRhw4aIiorC3bt3kZeXh7y8PKGOq6sr7OzsMHz4cGRkZODEiRMYM2YMunTpIjHa5GX16tWDurq6sCD948ePAQBTp07FokWLsH37dly4cAEzZsxAZmYm/P39AbyY7kdNTQ0+Pj44e/YsDh48iEmTJmHo0KGoX7++1Hn++usvRERE4Pjx48jJycGuXbtw9+5dIfEFvOjLOnToIEzHRfQxUlRURFZWFs6fPy/z4d6XX36JzZs3IyUlBWfOnIGPj0+lDwJl/ZxWxNvbG3v37sX3338vLOxebt68edi0aRNCQ0Nx7tw5ZGVlIT4+HnPmzKn0mubNm4dff/0Vly9fxrlz57Bnzx7hZ9fb2xv6+vrw8PBASkoKrl27huTkZEyePBk3b96stN1yo0aNwt27dzFy5MgK95uZmeH48ePYv38/Ll68iLlz5+LYsWMSdUxNTXH69GlcuHAB9+7dq5aROkSfiwEDBkBRURErV66EtrY2goODERAQgI0bN+LKlSs4efIkli9fLkyd+iozMzNh9GhWVhbGjBmD27dvS9Sp6HenV73ubyV5mJmZIScnB/Hx8bhy5QqWLVsm8WJGVdy/fx95eXm4evUqdu/eDVdXVxw9ehTr1q0T+mwzMzPs2rULmZmZOHXqFIYMGSJ1bRX9XSjPPSMiIvpYMVlCH6URI0agpKRE5lt8CxcuxMKFC2FtbY3U1FTs3r1bmHe7/I3j0tJSdO3aFVZWVpgyZQp0dXUl3kx0dnZGaWmp8IBST08PLVu2hIGBwRtNBxMcHAxFRUW0bNkSdevWRU5OjtyxyKNOnTro06eP1FQS8+bNg62tLUJCQlBQUABbW1vY2tri+PHjMtsKCwtDdnY2mjZtKkxDYWdnhx9//BHx8fH44osvMG/ePISFhcHX11c4bv369bC3t0fPnj3h6OgIsViMffv2SQ03f9m2bdsk1i0g+piwL5JWUV+UmJiIy5cvIykpCQ0aNIChoaHwKaegoIDffvsN+vr66NixI3r06AELCwvEx8fLPJeSkhKWLVuGb7/9FkZGRkJidvLkyQgMDERQUBCsrKyQkJCA3bt3C+u7aGhoYP/+/Xjw4AFat26N/v37o3PnzlixYkWF59HR0cHhw4fRvXt3mJubY86cOYiOjka3bt2EOvHx8ezL6JOgo6MDHR0dmftnzpwJZ2dn9OzZEz169ICnp2elLzzI+jmtyJdffgk9PT1cuHABQ4YMkdjn5uaGPXv24I8//kDr1q3Rrl07xMbGyhx5Vk5FRQUzZ85Eq1at0LFjRygqKgr9ioaGBg4fPoyGDRsKa0KNGDECT58+rfQevHp9+vr6UFKqeHbjMWPGoG/fvhg0aBDatm2L+/fvY/z48RJ1Ro0ahebNm8PBwQF169aVejudiGRTUlLCxIkTsXjxYhQWFiI8PBxz585FZGQkLCws4O7ujr179wpTT71qzpw5sLOzg5ubG1xcXGBgYABPT0+JOhX97vQqef5Wep3evXsjICAAEydOhI2NDY4cOYK5c+dW5XYIXF1dYWhoCCsrK8yYMQMWFhY4ffo0OnXqJNSJiYlB7dq10b59e/Tq1Qtubm4SI/qAiv8ulOeeERERfaxE4uqYs4foPdu8eTMCAgLwzz//CNM7AEB2djYaN26MjIwM2NjY1FyANeT06dPo0qULrly5Ai0trZoO57XOnTuHL7/8EhcvXpR7uguiDwn7oop9bH3R2/r9998RFBSE06dPy3xgSkREREREREQfNo4soY9KUVERrly5goULF2LMmDESDycJaNWqFRYtWlTp3OEfktzcXGzatImJEvrosC+q3MfWF72twsJCrF+/nokSIiIiIiIioo8YR5bQR2X+/PlYsGABOnbsiF9//VXqjeXP/W1uIno/2BcREREREREREX1amCwhIiIiIiIiIiIiIqLPGqfhIiIiIiIiIiIiIiKizxqTJURERERERERERERE9FljsoSIiIiIiIiIiIiIiD5rTJYQEREREREREREREdFnjckSIiIiIiIiIiIiIiL6rDFZQkREREREREREREREnzUmS4iIiIiIiIiIiIiI6LPGZAkREREREREREREREX3W/h8L3jiQNWsi2AAAAABJRU5ErkJggg==",
+      "text/plain": [
+       "<Figure size 1600x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "x = np.arange(len(tasks))  # the label locations\n",
+    "width = 0.08  # the width of the bars\n",
+    "multiplier = 0\n",
+    "\n",
+    "fig, ax = plt.subplots(layout=\"constrained\", figsize=(16, 4))\n",
+    "colormap = plt.get_cmap(\"Set2\").colors\n",
+    "\n",
+    "for idx, model in enumerate(models):\n",
+    "    try:\n",
+    "        results = stats_df.set_index(\"model\").loc[model]\n",
+    "    except:\n",
+    "        continue\n",
+    "\n",
+    "    color = colormap[idx]\n",
+    "    \n",
+    "    \n",
+    "    errors = []\n",
+    "    values = []\n",
+    "    for task in tasks:\n",
+    "        try:\n",
+    "            result = results.set_index(\"task\").loc[task]\n",
+    "            values.append(round(result['% correct'], 2))\n",
+    "            errors.append(result['error'])\n",
+    "        except KeyError:\n",
+    "            values.append(np.nan)\n",
+    "            errors.append(np.nan)\n",
+    "        \n",
+    "\n",
+    "    offset = width * multiplier * 1.4\n",
+    "    rects = ax.bar(\n",
+    "        x + offset, values, width, label=model, yerr=errors, color=color\n",
+    "    )\n",
+    "    ax.bar_label(rects, padding=3)\n",
+    "    multiplier += 1\n",
+    "\n",
+    "# Add some text for labels, title and custom x-axis tick labels, etc.\n",
+    "ax.set_ylabel(\"% Questions Answered Correctly\")\n",
+    "ax.set_title(\"Tool Usage Performance\")\n",
+    "\n",
+    "labels = [\n",
+    "    task.removeprefix('Tool Usage - ')\n",
+    "    for task in tasks\n",
+    "]\n",
+    "\n",
+    "ax.set_xticks(x + width + 0.25, labels)\n",
+    "ax.legend(\n",
+    "    loc=\"center left\", ncols=1, bbox_to_anchor=(1.0, 0.5), frameon=False, title=\"Model\"\n",
+    ")\n",
+    "ax.set_ylim(0, 1.10)\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2cb9d0ea-4ae0-4320-99ac-9b8fd442de14",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

From e9d7b78d4c7c5e9bae6cf5b5f90c77731d12e321 Mon Sep 17 00:00:00 2001
From: Eugene Yurtsev <eyurtsev@gmail.com>
Date: Mon, 18 Dec 2023 23:30:46 -0500
Subject: [PATCH 2/3] x

---
 .../notebooks/tool_usage/analysis.ipynb       | 1166 ++++++++++++++++-
 1 file changed, 1140 insertions(+), 26 deletions(-)

diff --git a/docs/source/notebooks/tool_usage/analysis.ipynb b/docs/source/notebooks/tool_usage/analysis.ipynb
index a189305..aeed0f8 100644
--- a/docs/source/notebooks/tool_usage/analysis.ipynb
+++ b/docs/source/notebooks/tool_usage/analysis.ipynb
@@ -204,7 +204,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 127,
    "id": "c59d080c-d3ac-43c3-a527-9961913db2ba",
    "metadata": {},
    "outputs": [],
@@ -217,18 +217,6 @@
     "    stats_df[\"% correct\"] * (1 - stats_df[\"% correct\"]) / stats_df[\"total\"]\n",
     ")\n",
     "\n",
-    "# stats_df\n",
-    "\n",
-    "models = [\n",
-    "     'mistral-7b-instruct-v0.1',\n",
-    "     'claude-2.1',\n",
-    "     'gpt-3.5-turbo-0613 (functions)',\n",
-    "     'gpt-3.5-turbo-1106 (assistant)',\n",
-    "     'gpt-3.5-turbo-1106 (functions)',\n",
-    "     'gpt-4-0613 (functions)',\n",
-    "     'gpt-4-1106-preview (assistant)',\n",
-    "     'gpt-4-1106-preview (functions)'\n",
-    "]\n",
     "\n",
     "tasks = [\n",
     "    \"Tool Usage - Typewriter (1 tool)\",\n",
@@ -242,7 +230,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 128,
    "id": "3704cfb3-79ea-4e7a-bc43-c82a3ae92675",
    "metadata": {
     "tags": []
@@ -256,6 +244,8 @@
     "            names.append(f\"{r['model']} (assistant)\")\n",
     "        else:\n",
     "            names.append(f\"{r['model']} (functions)\")\n",
+    "    elif r['model'].endswith('-fw'):\n",
+    "        names.append(r['model'].removesuffix('-fw'))\n",
     "    else:\n",
     "        names.append(r['model'])\n",
     "    "
@@ -263,7 +253,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 129,
    "id": "89d8ae82-a206-4267-9243-33e92628638a",
    "metadata": {
     "tags": []
@@ -275,27 +265,720 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 141,
    "id": "0263997a-49ee-47b3-868a-c3461e832970",
    "metadata": {
     "tags": []
    },
    "outputs": [],
    "source": [
-    "# models = stats_df.set_index('task').loc['Tool Usage - Relational Data'].sort_values('% correct')['model'].to_list()"
+    "models = stats_df.set_index('task').loc['Tool Usage - Relational Data'].sort_values('% correct')['model'].to_list()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 142,
+   "id": "bed28840-0cbb-4747-8e31-a4f30f8ef976",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['llama-v2-70b-chat',\n",
+       " 'yi-34b-200k',\n",
+       " 'llama-v2-13b-chat',\n",
+       " 'mistral-7b-instruct-v0.1',\n",
+       " 'mixtral-8x7b-instruct',\n",
+       " 'claude-2.1',\n",
+       " 'gpt-3.5-turbo-1106 (functions)',\n",
+       " 'gpt-3.5-turbo-1106 (assistant)',\n",
+       " 'gpt-3.5-turbo-0613 (functions)',\n",
+       " 'gpt-4-1106-preview (assistant)',\n",
+       " 'gpt-4-0613 (functions)',\n",
+       " 'gpt-4-1106-preview (functions)']"
+      ]
+     },
+     "execution_count": 142,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 143,
+   "id": "51cd896d-68aa-47f7-b00b-ac56132b3a0b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "models = [\n",
+    " 'llama-v2-13b-chat',\n",
+    " 'llama-v2-70b-chat',\n",
+    "  'yi-34b-200k',\n",
+    " 'mistral-7b-instruct-v0.1',\n",
+    " 'mixtral-8x7b-instruct',\n",
+    " 'claude-2.1',\n",
+    " 'gpt-3.5-turbo-0613 (functions)',\n",
+    " 'gpt-3.5-turbo-1106 (functions)',\n",
+    " 'gpt-3.5-turbo-1106 (assistant)',\n",
+    " 'gpt-4-0613 (functions)',\n",
+    " 'gpt-4-1106-preview (functions)',\n",
+    "    'gpt-4-1106-preview (assistant)',\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 144,
+   "id": "3f506b06-a511-4f8e-94b4-94bae82669a1",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>task</th>\n",
+       "      <th>arch</th>\n",
+       "      <th>model</th>\n",
+       "      <th>total</th>\n",
+       "      <th>num_correct</th>\n",
+       "      <th>% correct</th>\n",
+       "      <th>error</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>10</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.158114</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>10</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.200000</td>\n",
+       "      <td>0.126491</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>10</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.300000</td>\n",
+       "      <td>0.144914</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>10</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>10</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>0.700000</td>\n",
+       "      <td>0.144914</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>10</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.400000</td>\n",
+       "      <td>0.154919</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>10</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.800000</td>\n",
+       "      <td>0.126491</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>10</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.154919</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>10</td>\n",
+       "      <td>6.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.154919</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>10</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.400000</td>\n",
+       "      <td>0.154919</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>10</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.158114</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>21</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.142857</td>\n",
+       "      <td>0.076360</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.047619</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>21</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.380952</td>\n",
+       "      <td>0.105971</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.047619</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>0.761905</td>\n",
+       "      <td>0.092943</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.904762</td>\n",
+       "      <td>0.064056</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0.809524</td>\n",
+       "      <td>0.085689</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.190476</td>\n",
+       "      <td>0.085689</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>0.900000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.100000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.950000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.750000</td>\n",
+       "      <td>0.096825</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>31</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0.850000</td>\n",
+       "      <td>0.079844</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.950000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>33</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>0.700000</td>\n",
+       "      <td>0.102470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>0.900000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>36</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.100000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>41</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>42</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>0.700000</td>\n",
+       "      <td>0.102470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>43</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.111803</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>44</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.250000</td>\n",
+       "      <td>0.096825</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>45</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.400000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>46</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>0.900000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>47</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                  task                 arch  \\\n",
+       "0                      Multiverse Math  anthropic_tool_user   \n",
+       "1                      Multiverse Math         custom_agent   \n",
+       "2                      Multiverse Math         custom_agent   \n",
+       "3                      Multiverse Math         custom_agent   \n",
+       "4                      Multiverse Math         custom_agent   \n",
+       "5                      Multiverse Math     openai_assistant   \n",
+       "6                      Multiverse Math     openai_assistant   \n",
+       "7                      Multiverse Math     openai_functions   \n",
+       "8                      Multiverse Math     openai_functions   \n",
+       "9                      Multiverse Math     openai_functions   \n",
+       "10                     Multiverse Math     openai_functions   \n",
+       "11                     Multiverse Math     openai_functions   \n",
+       "12        Tool Usage - Relational Data  anthropic_tool_user   \n",
+       "13        Tool Usage - Relational Data         custom_agent   \n",
+       "14        Tool Usage - Relational Data         custom_agent   \n",
+       "15        Tool Usage - Relational Data         custom_agent   \n",
+       "16        Tool Usage - Relational Data         custom_agent   \n",
+       "17        Tool Usage - Relational Data     openai_assistant   \n",
+       "18        Tool Usage - Relational Data     openai_assistant   \n",
+       "19        Tool Usage - Relational Data     openai_functions   \n",
+       "20        Tool Usage - Relational Data     openai_functions   \n",
+       "21        Tool Usage - Relational Data     openai_functions   \n",
+       "22        Tool Usage - Relational Data     openai_functions   \n",
+       "23        Tool Usage - Relational Data     openai_functions   \n",
+       "24    Tool Usage - Typewriter (1 tool)  anthropic_tool_user   \n",
+       "25    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "26    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "27    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "28    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "29    Tool Usage - Typewriter (1 tool)     openai_assistant   \n",
+       "30    Tool Usage - Typewriter (1 tool)     openai_assistant   \n",
+       "31    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "32    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "33    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "34    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "35    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "36  Tool Usage - Typewriter (26 tools)  anthropic_tool_user   \n",
+       "37  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "38  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "39  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "40  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "41  Tool Usage - Typewriter (26 tools)     openai_assistant   \n",
+       "42  Tool Usage - Typewriter (26 tools)     openai_assistant   \n",
+       "43  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "44  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "45  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "46  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "47  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "\n",
+       "                             model  total  num_correct  % correct     error  \n",
+       "0                       claude-2.1     10          5.0   0.500000  0.158114  \n",
+       "1                llama-v2-13b-chat     10          0.0   0.000000  0.000000  \n",
+       "2                llama-v2-70b-chat     10          2.0   0.200000  0.126491  \n",
+       "3            mixtral-8x7b-instruct     10          3.0   0.300000  0.144914  \n",
+       "4                      yi-34b-200k     10          0.0   0.000000  0.000000  \n",
+       "5   gpt-3.5-turbo-1106 (assistant)     10          7.0   0.700000  0.144914  \n",
+       "6   gpt-4-1106-preview (assistant)     10          4.0   0.400000  0.154919  \n",
+       "7   gpt-3.5-turbo-0613 (functions)     10          8.0   0.800000  0.126491  \n",
+       "8   gpt-3.5-turbo-1106 (functions)     10          6.0   0.600000  0.154919  \n",
+       "9           gpt-4-0613 (functions)     10          6.0   0.600000  0.154919  \n",
+       "10  gpt-4-1106-preview (functions)     10          4.0   0.400000  0.154919  \n",
+       "11        mistral-7b-instruct-v0.1     10          5.0   0.500000  0.158114  \n",
+       "12                      claude-2.1     21         15.0   0.714286  0.098581  \n",
+       "13               llama-v2-13b-chat     21          3.0   0.142857  0.076360  \n",
+       "14               llama-v2-70b-chat     21          1.0   0.047619  0.046471  \n",
+       "15           mixtral-8x7b-instruct     21          8.0   0.380952  0.105971  \n",
+       "16                     yi-34b-200k     21          1.0   0.047619  0.046471  \n",
+       "17  gpt-3.5-turbo-1106 (assistant)     21         16.0   0.761905  0.092943  \n",
+       "18  gpt-4-1106-preview (assistant)     21         19.0   0.904762  0.064056  \n",
+       "19  gpt-3.5-turbo-0613 (functions)     21         17.0   0.809524  0.085689  \n",
+       "20  gpt-3.5-turbo-1106 (functions)     21         15.0   0.714286  0.098581  \n",
+       "21          gpt-4-0613 (functions)     21         20.0   0.952381  0.046471  \n",
+       "22  gpt-4-1106-preview (functions)     21         20.0   0.952381  0.046471  \n",
+       "23        mistral-7b-instruct-v0.1     21          4.0   0.190476  0.085689  \n",
+       "24                      claude-2.1     20         18.0   0.900000  0.067082  \n",
+       "25               llama-v2-13b-chat     20          0.0   0.000000  0.000000  \n",
+       "26               llama-v2-70b-chat     20          2.0   0.100000  0.067082  \n",
+       "27           mixtral-8x7b-instruct     20         12.0   0.600000  0.109545  \n",
+       "28                     yi-34b-200k     20          1.0   0.050000  0.048734  \n",
+       "29  gpt-3.5-turbo-1106 (assistant)     20         19.0   0.950000  0.048734  \n",
+       "30  gpt-4-1106-preview (assistant)     20         15.0   0.750000  0.096825  \n",
+       "31  gpt-3.5-turbo-0613 (functions)     20         17.0   0.850000  0.079844  \n",
+       "32  gpt-3.5-turbo-1106 (functions)     20         19.0   0.950000  0.048734  \n",
+       "33          gpt-4-0613 (functions)     20         14.0   0.700000  0.102470  \n",
+       "34  gpt-4-1106-preview (functions)     20         18.0   0.900000  0.067082  \n",
+       "35        mistral-7b-instruct-v0.1     20          1.0   0.050000  0.048734  \n",
+       "36                      claude-2.1     20         20.0   1.000000  0.000000  \n",
+       "37               llama-v2-13b-chat     20          0.0   0.000000  0.000000  \n",
+       "38               llama-v2-70b-chat     20          2.0   0.100000  0.067082  \n",
+       "39           mixtral-8x7b-instruct     20         12.0   0.600000  0.109545  \n",
+       "40                     yi-34b-200k     20          0.0   0.000000  0.000000  \n",
+       "41  gpt-3.5-turbo-1106 (assistant)     20         12.0   0.600000  0.109545  \n",
+       "42  gpt-4-1106-preview (assistant)     20         14.0   0.700000  0.102470  \n",
+       "43  gpt-3.5-turbo-0613 (functions)     20         10.0   0.500000  0.111803  \n",
+       "44  gpt-3.5-turbo-1106 (functions)     20          5.0   0.250000  0.096825  \n",
+       "45          gpt-4-0613 (functions)     20          8.0   0.400000  0.109545  \n",
+       "46  gpt-4-1106-preview (functions)     20         18.0   0.900000  0.067082  \n",
+       "47        mistral-7b-instruct-v0.1     20          1.0   0.050000  0.048734  "
+      ]
+     },
+     "execution_count": 144,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stats_df"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
-   "id": "69df66a1-960c-40a3-abc8-58b503fceda5",
+   "execution_count": 145,
+   "id": "2cb9d0ea-4ae0-4320-99ac-9b8fd442de14",
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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",
+      "image/png": "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",
       "text/plain": [
-       "<Figure size 1600x400 with 1 Axes>"
+       "<Figure size 2000x400 with 1 Axes>"
       ]
      },
      "metadata": {},
@@ -304,11 +987,11 @@
    ],
    "source": [
     "x = np.arange(len(tasks))  # the label locations\n",
-    "width = 0.08  # the width of the bars\n",
+    "width = 0.05  # the width of the bars\n",
     "multiplier = 0\n",
     "\n",
-    "fig, ax = plt.subplots(layout=\"constrained\", figsize=(16, 4))\n",
-    "colormap = plt.get_cmap(\"Set2\").colors\n",
+    "fig, ax = plt.subplots(layout=\"constrained\", figsize=(20, 4))\n",
+    "colormap = plt.get_cmap(\"Set3\").colors\n",
     "\n",
     "for idx, model in enumerate(models):\n",
     "    try:\n",
@@ -347,7 +1030,7 @@
     "    for task in tasks\n",
     "]\n",
     "\n",
-    "ax.set_xticks(x + width + 0.25, labels)\n",
+    "ax.set_xticks(x + width + 0.37, labels)\n",
     "ax.legend(\n",
     "    loc=\"center left\", ncols=1, bbox_to_anchor=(1.0, 0.5), frameon=False, title=\"Model\"\n",
     ")\n",
@@ -356,10 +1039,441 @@
     "plt.show()"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 135,
+   "id": "580aa92a-97a2-49a9-944f-45db56dd3e2e",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# x = np.arange(len(tasks))  # the label locations\n",
+    "# width = 0.08  # the width of the bars\n",
+    "# multiplier = 0\n",
+    "\n",
+    "# fig, ax = plt.subplots(layout=\"constrained\", figsize=(16, 4))\n",
+    "# colormap = plt.get_cmap(\"Set2\").colors\n",
+    "\n",
+    "# for idx, model in enumerate(models):\n",
+    "#     try:\n",
+    "#         results = stats_df.set_index(\"model\").loc[model]\n",
+    "#     except:\n",
+    "#         continue\n",
+    "\n",
+    "#     color = colormap[idx]\n",
+    "    \n",
+    "    \n",
+    "#     errors = []\n",
+    "#     values = []\n",
+    "#     for task in tasks:\n",
+    "#         try:\n",
+    "#             result = results.set_index(\"task\").loc[task]\n",
+    "#             values.append(round(result['% correct'], 2))\n",
+    "#             errors.append(result['error'])\n",
+    "#         except KeyError:\n",
+    "#             values.append(np.nan)\n",
+    "#             errors.append(np.nan)\n",
+    "        \n",
+    "\n",
+    "#     offset = width * multiplier * 1.4\n",
+    "#     rects = ax.bar(\n",
+    "#         x + offset, values, width, label=model, yerr=errors, color=color\n",
+    "#     )\n",
+    "#     ax.bar_label(rects, padding=3)\n",
+    "#     multiplier += 1\n",
+    "\n",
+    "# # Add some text for labels, title and custom x-axis tick labels, etc.\n",
+    "# ax.set_ylabel(\"% Questions Answered Correctly\")\n",
+    "# ax.set_title(\"Tool Usage Performance\")\n",
+    "\n",
+    "# labels = [\n",
+    "#     task.removeprefix('Tool Usage - ')\n",
+    "#     for task in tasks\n",
+    "# ]\n",
+    "\n",
+    "# ax.set_xticks(x + width + 0.25, labels)\n",
+    "# ax.legend(\n",
+    "#     loc=\"center left\", ncols=1, bbox_to_anchor=(1.0, 0.5), frameon=False, title=\"Model\"\n",
+    "# )\n",
+    "# ax.set_ylim(0, 1.10)\n",
+    "\n",
+    "# plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 136,
+   "id": "fdf17371-2a6b-4bd7-bd8e-b2068df7fc2b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "subset_df = stats_df.set_index('task').loc['Tool Usage - Relational Data']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 137,
+   "id": "afc37ce2-0a37-4943-9f4a-15ef60eb67ca",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>arch</th>\n",
+       "      <th>model</th>\n",
+       "      <th>total</th>\n",
+       "      <th>num_correct</th>\n",
+       "      <th>% correct</th>\n",
+       "      <th>error</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>task</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>21</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.142857</td>\n",
+       "      <td>0.076360</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.047619</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>21</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.380952</td>\n",
+       "      <td>0.105971</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.047619</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>0.761905</td>\n",
+       "      <td>0.092943</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.904762</td>\n",
+       "      <td>0.064056</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0.809524</td>\n",
+       "      <td>0.085689</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>Tool Usage - Relational Data</th>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.190476</td>\n",
+       "      <td>0.085689</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                             arch  \\\n",
+       "task                                                \n",
+       "Tool Usage - Relational Data  anthropic_tool_user   \n",
+       "Tool Usage - Relational Data         custom_agent   \n",
+       "Tool Usage - Relational Data         custom_agent   \n",
+       "Tool Usage - Relational Data         custom_agent   \n",
+       "Tool Usage - Relational Data         custom_agent   \n",
+       "Tool Usage - Relational Data     openai_assistant   \n",
+       "Tool Usage - Relational Data     openai_assistant   \n",
+       "Tool Usage - Relational Data     openai_functions   \n",
+       "Tool Usage - Relational Data     openai_functions   \n",
+       "Tool Usage - Relational Data     openai_functions   \n",
+       "Tool Usage - Relational Data     openai_functions   \n",
+       "Tool Usage - Relational Data     openai_functions   \n",
+       "\n",
+       "                                                       model  total  \\\n",
+       "task                                                                  \n",
+       "Tool Usage - Relational Data                      claude-2.1     21   \n",
+       "Tool Usage - Relational Data               llama-v2-13b-chat     21   \n",
+       "Tool Usage - Relational Data               llama-v2-70b-chat     21   \n",
+       "Tool Usage - Relational Data           mixtral-8x7b-instruct     21   \n",
+       "Tool Usage - Relational Data                     yi-34b-200k     21   \n",
+       "Tool Usage - Relational Data  gpt-3.5-turbo-1106 (assistant)     21   \n",
+       "Tool Usage - Relational Data  gpt-4-1106-preview (assistant)     21   \n",
+       "Tool Usage - Relational Data  gpt-3.5-turbo-0613 (functions)     21   \n",
+       "Tool Usage - Relational Data  gpt-3.5-turbo-1106 (functions)     21   \n",
+       "Tool Usage - Relational Data          gpt-4-0613 (functions)     21   \n",
+       "Tool Usage - Relational Data  gpt-4-1106-preview (functions)     21   \n",
+       "Tool Usage - Relational Data        mistral-7b-instruct-v0.1     21   \n",
+       "\n",
+       "                              num_correct  % correct     error  \n",
+       "task                                                            \n",
+       "Tool Usage - Relational Data         15.0   0.714286  0.098581  \n",
+       "Tool Usage - Relational Data          3.0   0.142857  0.076360  \n",
+       "Tool Usage - Relational Data          1.0   0.047619  0.046471  \n",
+       "Tool Usage - Relational Data          8.0   0.380952  0.105971  \n",
+       "Tool Usage - Relational Data          1.0   0.047619  0.046471  \n",
+       "Tool Usage - Relational Data         16.0   0.761905  0.092943  \n",
+       "Tool Usage - Relational Data         19.0   0.904762  0.064056  \n",
+       "Tool Usage - Relational Data         17.0   0.809524  0.085689  \n",
+       "Tool Usage - Relational Data         15.0   0.714286  0.098581  \n",
+       "Tool Usage - Relational Data         20.0   0.952381  0.046471  \n",
+       "Tool Usage - Relational Data         20.0   0.952381  0.046471  \n",
+       "Tool Usage - Relational Data          4.0   0.190476  0.085689  "
+      ]
+     },
+     "execution_count": 137,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "subset_df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 138,
+   "id": "b380e417-c73f-4ebc-8489-c43249f167fd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "ename": "KeyError",
+     "evalue": "'model'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/agents_3_11/lib/python3.11/site-packages/pandas/core/indexes/base.py:3790\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3789\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 3790\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_engine\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcasted_key\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   3791\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m err:\n",
+      "File \u001b[0;32mindex.pyx:152\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mindex.pyx:176\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
+      "File \u001b[0;32mindex.pyx:213\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine._get_loc_duplicates\u001b[0;34m()\u001b[0m\n",
+      "\u001b[0;31mKeyError\u001b[0m: 'model'",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[138], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43msubset_df\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mloc\u001b[49m\u001b[43m[\u001b[49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[38;5;124;43mmodel\u001b[39;49m\u001b[38;5;124;43m'\u001b[39;49m\u001b[43m]\u001b[49m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/agents_3_11/lib/python3.11/site-packages/pandas/core/indexing.py:1153\u001b[0m, in \u001b[0;36m_LocationIndexer.__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1150\u001b[0m axis \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39maxis \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;241m0\u001b[39m\n\u001b[1;32m   1152\u001b[0m maybe_callable \u001b[38;5;241m=\u001b[39m com\u001b[38;5;241m.\u001b[39mapply_if_callable(key, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mobj)\n\u001b[0;32m-> 1153\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_getitem_axis\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmaybe_callable\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/agents_3_11/lib/python3.11/site-packages/pandas/core/indexing.py:1393\u001b[0m, in \u001b[0;36m_LocIndexer._getitem_axis\u001b[0;34m(self, key, axis)\u001b[0m\n\u001b[1;32m   1391\u001b[0m \u001b[38;5;66;03m# fall thru to straight lookup\u001b[39;00m\n\u001b[1;32m   1392\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_key(key, axis)\n\u001b[0;32m-> 1393\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_get_label\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/agents_3_11/lib/python3.11/site-packages/pandas/core/indexing.py:1343\u001b[0m, in \u001b[0;36m_LocIndexer._get_label\u001b[0;34m(self, label, axis)\u001b[0m\n\u001b[1;32m   1341\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21m_get_label\u001b[39m(\u001b[38;5;28mself\u001b[39m, label, axis: AxisInt):\n\u001b[1;32m   1342\u001b[0m     \u001b[38;5;66;03m# GH#5567 this will fail if the label is not present in the axis.\u001b[39;00m\n\u001b[0;32m-> 1343\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mobj\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mxs\u001b[49m\u001b[43m(\u001b[49m\u001b[43mlabel\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43maxis\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43maxis\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/agents_3_11/lib/python3.11/site-packages/pandas/core/generic.py:4236\u001b[0m, in \u001b[0;36mNDFrame.xs\u001b[0;34m(self, key, axis, level, drop_level)\u001b[0m\n\u001b[1;32m   4234\u001b[0m             new_index \u001b[38;5;241m=\u001b[39m index[loc]\n\u001b[1;32m   4235\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m-> 4236\u001b[0m     loc \u001b[38;5;241m=\u001b[39m \u001b[43mindex\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_loc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mkey\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   4238\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(loc, np\u001b[38;5;241m.\u001b[39mndarray):\n\u001b[1;32m   4239\u001b[0m         \u001b[38;5;28;01mif\u001b[39;00m loc\u001b[38;5;241m.\u001b[39mdtype \u001b[38;5;241m==\u001b[39m np\u001b[38;5;241m.\u001b[39mbool_:\n",
+      "File \u001b[0;32m~/.pyenv/versions/3.11.4/envs/agents_3_11/lib/python3.11/site-packages/pandas/core/indexes/base.py:3797\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   3792\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(casted_key, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;129;01mor\u001b[39;00m (\n\u001b[1;32m   3793\u001b[0m         \u001b[38;5;28misinstance\u001b[39m(casted_key, abc\u001b[38;5;241m.\u001b[39mIterable)\n\u001b[1;32m   3794\u001b[0m         \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(x, \u001b[38;5;28mslice\u001b[39m) \u001b[38;5;28;01mfor\u001b[39;00m x \u001b[38;5;129;01min\u001b[39;00m casted_key)\n\u001b[1;32m   3795\u001b[0m     ):\n\u001b[1;32m   3796\u001b[0m         \u001b[38;5;28;01mraise\u001b[39;00m InvalidIndexError(key)\n\u001b[0;32m-> 3797\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mKeyError\u001b[39;00m(key) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01merr\u001b[39;00m\n\u001b[1;32m   3798\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mTypeError\u001b[39;00m:\n\u001b[1;32m   3799\u001b[0m     \u001b[38;5;66;03m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[1;32m   3800\u001b[0m     \u001b[38;5;66;03m#  InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[1;32m   3801\u001b[0m     \u001b[38;5;66;03m#  the TypeError.\u001b[39;00m\n\u001b[1;32m   3802\u001b[0m     \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_check_indexing_error(key)\n",
+      "\u001b[0;31mKeyError\u001b[0m: 'model'"
+     ]
+    }
+   ],
+   "source": [
+    "subset_df.loc['model']\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 139,
+   "id": "302ae48c-d138-44b5-8c67-eed29e88ffdd",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "models = subset_df.model.to_list()\n",
+    "pct_correct = subset_df['% correct']\n",
+    "error = subset_df['error']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 140,
+   "id": "d03b1146-a052-43a0-88b2-dd8179f4d73f",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['claude-2.1',\n",
+       " 'llama-v2-13b-chat',\n",
+       " 'llama-v2-70b-chat',\n",
+       " 'mixtral-8x7b-instruct',\n",
+       " 'yi-34b-200k',\n",
+       " 'gpt-3.5-turbo-1106 (assistant)',\n",
+       " 'gpt-4-1106-preview (assistant)',\n",
+       " 'gpt-3.5-turbo-0613 (functions)',\n",
+       " 'gpt-3.5-turbo-1106 (functions)',\n",
+       " 'gpt-4-0613 (functions)',\n",
+       " 'gpt-4-1106-preview (functions)',\n",
+       " 'mistral-7b-instruct-v0.1']"
+      ]
+     },
+     "execution_count": 140,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "models"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 95,
+   "id": "84cf82f7-7772-450f-abcf-ee2b2f9b0bf4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "ename": "TypeError",
+     "evalue": "tuple indices must be integers or slices, not tuple",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[95], line 7\u001b[0m\n\u001b[1;32m      3\u001b[0m fig, ax \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39msubplots()\n\u001b[1;32m      5\u001b[0m colormap \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39mget_cmap(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSet3\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mcolors\n\u001b[0;32m----> 7\u001b[0m c \u001b[38;5;241m=\u001b[39m \u001b[43m[\u001b[49m\u001b[43mcolormap\u001b[49m\u001b[43m[\u001b[49m\u001b[43midx\u001b[49m\u001b[43m]\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mfor\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43midx\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;129;43;01min\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43menumerate\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mmodels\u001b[49m\u001b[43m)\u001b[49m\u001b[43m]\u001b[49m\n\u001b[1;32m      8\u001b[0m \u001b[38;5;66;03m# fruits = ['apple', 'blueberry', 'cherry', 'orange']\u001b[39;00m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;66;03m# counts = [40, 100, 30, 55]\u001b[39;00m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;66;03m# bar_labels = ['red', 'blue', '_red', 'orange']\u001b[39;00m\n\u001b[1;32m     11\u001b[0m \u001b[38;5;66;03m# bar_colors = ['tab:red', 'tab:blue', 'tab:red', 'tab:orange']\u001b[39;00m\n\u001b[1;32m     12\u001b[0m \n\u001b[1;32m     13\u001b[0m \u001b[38;5;66;03m# Add some text for labels, title and custom x-axis tick labels, etc.\u001b[39;00m\n\u001b[1;32m     14\u001b[0m ax\u001b[38;5;241m.\u001b[39mset_ylabel(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124m Questions Answered Correctly\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "Cell \u001b[0;32mIn[95], line 7\u001b[0m, in \u001b[0;36m<listcomp>\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m      3\u001b[0m fig, ax \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39msubplots()\n\u001b[1;32m      5\u001b[0m colormap \u001b[38;5;241m=\u001b[39m plt\u001b[38;5;241m.\u001b[39mget_cmap(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSet3\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mcolors\n\u001b[0;32m----> 7\u001b[0m c \u001b[38;5;241m=\u001b[39m [\u001b[43mcolormap\u001b[49m\u001b[43m[\u001b[49m\u001b[43midx\u001b[49m\u001b[43m]\u001b[49m \u001b[38;5;28;01mfor\u001b[39;00m idx \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(models)]\n\u001b[1;32m      8\u001b[0m \u001b[38;5;66;03m# fruits = ['apple', 'blueberry', 'cherry', 'orange']\u001b[39;00m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;66;03m# counts = [40, 100, 30, 55]\u001b[39;00m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;66;03m# bar_labels = ['red', 'blue', '_red', 'orange']\u001b[39;00m\n\u001b[1;32m     11\u001b[0m \u001b[38;5;66;03m# bar_colors = ['tab:red', 'tab:blue', 'tab:red', 'tab:orange']\u001b[39;00m\n\u001b[1;32m     12\u001b[0m \n\u001b[1;32m     13\u001b[0m \u001b[38;5;66;03m# Add some text for labels, title and custom x-axis tick labels, etc.\u001b[39;00m\n\u001b[1;32m     14\u001b[0m ax\u001b[38;5;241m.\u001b[39mset_ylabel(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m%\u001b[39m\u001b[38;5;124m Questions Answered Correctly\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
+      "\u001b[0;31mTypeError\u001b[0m: tuple indices must be integers or slices, not tuple"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "\n",
+    "# colormap = plt.get_cmap(\"Set3\").colors\n",
+    "\n",
+    "# c = [colormap[idx] for idx in enumerate(models)]\n",
+    "# fruits = ['apple', 'blueberry', 'cherry', 'orange']\n",
+    "# counts = [40, 100, 30, 55]\n",
+    "# bar_labels = ['red', 'blue', '_red', 'orange']\n",
+    "# bar_colors = ['tab:red', 'tab:blue', 'tab:red', 'tab:orange']\n",
+    "\n",
+    "# Add some text for labels, title and custom x-axis tick labels, etc.\n",
+    "ax.set_ylabel(\"% Questions Answered Correctly\")\n",
+    "ax.set_title(\"Tool Usage Performance\")\n",
+    "\n",
+    "\n",
+    "ax.bar(models, pct_correct)\n",
+    "\n",
+    "ax.set_ylabel('fruit supply')\n",
+    "ax.set_title('Fruit supply by kind and color')\n",
+    "# ax.legend(title='Fruit color')\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "2cb9d0ea-4ae0-4320-99ac-9b8fd442de14",
+   "id": "52588782-199e-4110-9aaa-94844616dde6",
    "metadata": {},
    "outputs": [],
    "source": []

From b4111be318a18bf234ce9b73aa441c09908c748a Mon Sep 17 00:00:00 2001
From: Eugene Yurtsev <eyurtsev@gmail.com>
Date: Tue, 19 Dec 2023 18:07:27 -0500
Subject: [PATCH 3/3] x

---
 .../notebooks/tool_usage/analysis_v3.ipynb    | 1149 +++++++++++++++++
 1 file changed, 1149 insertions(+)
 create mode 100644 docs/source/notebooks/tool_usage/analysis_v3.ipynb

diff --git a/docs/source/notebooks/tool_usage/analysis_v3.ipynb b/docs/source/notebooks/tool_usage/analysis_v3.ipynb
new file mode 100644
index 0000000..8a0ca30
--- /dev/null
+++ b/docs/source/notebooks/tool_usage/analysis_v3.ipynb
@@ -0,0 +1,1149 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "1ba9f105-c48f-4d8c-8253-355ef13156b0",
+   "metadata": {},
+   "source": [
+    "# Plots for blog post\n",
+    "\n",
+    "Get all data from \"woof\" experiment"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "13a7483b-d08f-49fa-83da-619863171e5b",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "import datetime\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "from langsmith.client import Client\n",
+    "\n",
+    "from langchain_benchmarks import (\n",
+    "    __version__,\n",
+    "    clone_public_dataset,\n",
+    "    model_registry,\n",
+    "    registry,\n",
+    ")\n",
+    "from langchain_benchmarks.rate_limiting import RateLimiter\n",
+    "from langchain_benchmarks.tool_usage.agents import (\n",
+    "    AnthropicToolUserFactory,\n",
+    "    CustomAgentFactory,\n",
+    "    OpenAIAgentFactory,\n",
+    "    OpenAIAssistantFactory,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "925b08db-0442-41d0-8584-bdf40ecf76e6",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "from datetime import datetime\n",
+    "\n",
+    "client = Client()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "280c9b90-61f1-4d76-8741-500abdd6079c",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "claude-2.1-anthropic_tool_user-Multiverse Math-2023-12-19-woof\n",
+      "claude-2.1-anthropic_tool_user-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "claude-2.1-anthropic_tool_user-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "claude-2.1-anthropic_tool_user-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gemini-pro-custom_agent-Multiverse Math-2023-12-19-woof\n",
+      "gemini-pro-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Multiverse Math-2023-12-19-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-0613-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Multiverse Math-2023-12-19-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_assistant-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Multiverse Math-2023-12-19-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-3.5-turbo-1106-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Multiverse Math-2023-12-19-woof\n",
+      "gpt-4-0613-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-4-0613-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Multiverse Math-2023-12-19-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_assistant-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Multiverse Math-2023-12-19-woof\n",
+      "gpt-4-1106-preview-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "gpt-4-1106-preview-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Multiverse Math-2023-12-19-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "llama-v2-13b-chat-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Multiverse Math-2023-12-19-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "llama-v2-70b-chat-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Multiverse Math-2023-12-19-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "mistral-7b-instruct-v0.1-openai_functions-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Multiverse Math-2023-12-19-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "mixtral-8x7b-instruct-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Multiverse Math-2023-12-19-woof\n",
+      "yi-34b-200k-fw-custom_agent-Tool Usage - Relational Data-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Tool Usage - Typewriter (1 tool)-2023-12-18-woof\n",
+      "yi-34b-200k-fw-custom_agent-Tool Usage - Typewriter (26 tools)-2023-12-18-woof\n"
+     ]
+    }
+   ],
+   "source": [
+    "experiment_ids = [\"woof\"]\n",
+    "\n",
+    "\n",
+    "def _endswith(s, suffixes):\n",
+    "    return any(s.endswith(suffix) for suffix in suffixes)\n",
+    "\n",
+    "\n",
+    "client = Client()\n",
+    "projects = [\n",
+    "    project\n",
+    "    for project in client.list_projects()\n",
+    "    if _endswith(project.name, experiment_ids)\n",
+    "]\n",
+    "\n",
+    "print(\"\\n\".join(sorted([project.name for project in projects])))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7a87b357-0625-41d1-856b-560ecd975a00",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "dfs = []\n",
+    "for project in projects:\n",
+    "    # Temporary way to get tag information\n",
+    "    project_info = client.read_project(project_id=project.id)\n",
+    "\n",
+    "    if project_info.extra is None:\n",
+    "        continue\n",
+    "        # raise ValueError(project.name)\n",
+    "    try:\n",
+    "        test_results = client.get_test_results(project_name=project.name)\n",
+    "    except Exception:\n",
+    "        continue\n",
+    "\n",
+    "    for k, v in project_info.extra[\"metadata\"].items():\n",
+    "        test_results[k] = v\n",
+    "\n",
+    "    dfs.append(test_results)\n",
+    "\n",
+    "\n",
+    "df = pd.concat(dfs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "62c30d47-a971-4182-94aa-ceb292ad46f5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "# pd.set_option('display.max_colwidth', None)\n",
+    "# subset_df.sort_values(['model', 'input.question', 'arch'])[['model', 'input.question', 'outputs.output', 'reference.reference', 'correct']].iloc[:50]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "270b8ae9-c84b-4ebc-88ab-fa0ac5e28a57",
+   "metadata": {},
+   "source": [
+    "Compute some statistics. We're using estimating standard error of the mean assuming a bernoulli process."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "162a25e4-3178-4bc3-91a6-1d991eae8bf4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "tasks = [\n",
+    "    \"Tool Usage - Typewriter (1 tool)\",\n",
+    "    \"Tool Usage - Typewriter (26 tools)\",\n",
+    "    \"Multiverse Math\",\n",
+    "    \"Tool Usage - Relational Data\",\n",
+    "]\n",
+    "\n",
+    "\n",
+    "correct = []\n",
+    "\n",
+    "for r in df.to_dict(orient=\"records\"):\n",
+    "    if \"Typewriter\" in r[\"task\"]:\n",
+    "        correct.append(r[\"feedback.Correct Final State\"])\n",
+    "    else:\n",
+    "        correct.append(r[\"feedback.correctness\"])\n",
+    "\n",
+    "df[\"correct\"] = correct\n",
+    "df[\"correct\"].fillna(0, inplace=True)\n",
+    "\n",
+    "num_correct = (\n",
+    "    df.groupby([\"model\", \"arch\", \"task\"])[\"correct\"].sum().to_frame(\"num_correct\")\n",
+    ")\n",
+    "total = df.groupby([\"task\", \"arch\", \"model\"]).size().to_frame(\"total\")\n",
+    "stats_df = total.join(num_correct)\n",
+    "stats_df[\"% correct\"] = stats_df[\"num_correct\"] / stats_df[\"total\"]\n",
+    "stats_df[\"error\"] = np.sqrt(\n",
+    "    stats_df[\"% correct\"] * (1 - stats_df[\"% correct\"]) / stats_df[\"total\"]\n",
+    ")\n",
+    "\n",
+    "stats_df = stats_df.reset_index()\n",
+    "\n",
+    "names = []\n",
+    "for r in stats_df.to_dict(orient=\"records\"):\n",
+    "    if r[\"model\"].startswith(\"gpt\"):\n",
+    "        if r[\"arch\"] == \"openai_assistant\":\n",
+    "            names.append(f\"{r['model']} (assistant)\")\n",
+    "        else:\n",
+    "            names.append(f\"{r['model']} (functions)\")\n",
+    "    elif r[\"model\"].endswith(\"-fw\"):\n",
+    "        names.append(r[\"model\"].removesuffix(\"-fw\"))\n",
+    "    else:\n",
+    "        names.append(r[\"model\"])\n",
+    "\n",
+    "\n",
+    "stats_df[\"model\"] = names"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "018e0336-98fc-4a58-bde6-b239817ca3b2",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['claude-2.1',\n",
+       " 'gemini-pro',\n",
+       " 'llama-v2-13b-chat',\n",
+       " 'llama-v2-70b-chat',\n",
+       " 'mixtral-8x7b-instruct',\n",
+       " 'yi-34b-200k',\n",
+       " 'gpt-3.5-turbo-1106 (assistant)',\n",
+       " 'gpt-4-1106-preview (assistant)',\n",
+       " 'gpt-3.5-turbo-0613 (functions)',\n",
+       " 'gpt-3.5-turbo-1106 (functions)',\n",
+       " 'gpt-4-0613 (functions)',\n",
+       " 'gpt-4-1106-preview (functions)',\n",
+       " 'mistral-7b-instruct-v0.1']"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "list(stats_df.model.unique())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "76511574-9636-43a1-8fd3-0b23c5a573c5",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>task</th>\n",
+       "      <th>arch</th>\n",
+       "      <th>model</th>\n",
+       "      <th>total</th>\n",
+       "      <th>num_correct</th>\n",
+       "      <th>% correct</th>\n",
+       "      <th>error</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>gemini-pro</td>\n",
+       "      <td>20</td>\n",
+       "      <td>7.0</td>\n",
+       "      <td>0.350000</td>\n",
+       "      <td>0.106654</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.200000</td>\n",
+       "      <td>0.089443</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.250000</td>\n",
+       "      <td>0.096825</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>20</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.200000</td>\n",
+       "      <td>0.089443</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>0.450000</td>\n",
+       "      <td>0.111243</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>9.0</td>\n",
+       "      <td>0.450000</td>\n",
+       "      <td>0.111243</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>0.700000</td>\n",
+       "      <td>0.102470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.111803</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>13.0</td>\n",
+       "      <td>0.650000</td>\n",
+       "      <td>0.106654</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>11.0</td>\n",
+       "      <td>0.550000</td>\n",
+       "      <td>0.111243</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>Multiverse Math</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.111803</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>gemini-pro</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>21</td>\n",
+       "      <td>3.0</td>\n",
+       "      <td>0.142857</td>\n",
+       "      <td>0.076360</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.047619</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>21</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.380952</td>\n",
+       "      <td>0.105971</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>21</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.047619</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>16.0</td>\n",
+       "      <td>0.761905</td>\n",
+       "      <td>0.092943</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.904762</td>\n",
+       "      <td>0.064056</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>21</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0.809524</td>\n",
+       "      <td>0.085689</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>22</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.714286</td>\n",
+       "      <td>0.098581</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>24</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>21</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>0.952381</td>\n",
+       "      <td>0.046471</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>Tool Usage - Relational Data</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>21</td>\n",
+       "      <td>4.0</td>\n",
+       "      <td>0.190476</td>\n",
+       "      <td>0.085689</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>26</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>0.900000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>27</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.100000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>29</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>31</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.950000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>32</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>15.0</td>\n",
+       "      <td>0.750000</td>\n",
+       "      <td>0.096825</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>33</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>17.0</td>\n",
+       "      <td>0.850000</td>\n",
+       "      <td>0.079844</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>34</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>19.0</td>\n",
+       "      <td>0.950000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>0.700000</td>\n",
+       "      <td>0.102470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>36</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>0.900000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>37</th>\n",
+       "      <td>Tool Usage - Typewriter (1 tool)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>anthropic_tool_user</td>\n",
+       "      <td>claude-2.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>20.0</td>\n",
+       "      <td>1.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>39</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-13b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>llama-v2-70b-chat</td>\n",
+       "      <td>20</td>\n",
+       "      <td>2.0</td>\n",
+       "      <td>0.100000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>41</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>mixtral-8x7b-instruct</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>42</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>custom_agent</td>\n",
+       "      <td>yi-34b-200k</td>\n",
+       "      <td>20</td>\n",
+       "      <td>0.0</td>\n",
+       "      <td>0.000000</td>\n",
+       "      <td>0.000000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>43</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>12.0</td>\n",
+       "      <td>0.600000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>44</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_assistant</td>\n",
+       "      <td>gpt-4-1106-preview (assistant)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>14.0</td>\n",
+       "      <td>0.700000</td>\n",
+       "      <td>0.102470</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>45</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>10.0</td>\n",
+       "      <td>0.500000</td>\n",
+       "      <td>0.111803</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>46</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-3.5-turbo-1106 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>5.0</td>\n",
+       "      <td>0.250000</td>\n",
+       "      <td>0.096825</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>47</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-0613 (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>8.0</td>\n",
+       "      <td>0.400000</td>\n",
+       "      <td>0.109545</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>48</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>gpt-4-1106-preview (functions)</td>\n",
+       "      <td>20</td>\n",
+       "      <td>18.0</td>\n",
+       "      <td>0.900000</td>\n",
+       "      <td>0.067082</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>49</th>\n",
+       "      <td>Tool Usage - Typewriter (26 tools)</td>\n",
+       "      <td>openai_functions</td>\n",
+       "      <td>mistral-7b-instruct-v0.1</td>\n",
+       "      <td>20</td>\n",
+       "      <td>1.0</td>\n",
+       "      <td>0.050000</td>\n",
+       "      <td>0.048734</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                                  task                 arch  \\\n",
+       "0                      Multiverse Math  anthropic_tool_user   \n",
+       "1                      Multiverse Math         custom_agent   \n",
+       "2                      Multiverse Math         custom_agent   \n",
+       "3                      Multiverse Math         custom_agent   \n",
+       "4                      Multiverse Math         custom_agent   \n",
+       "5                      Multiverse Math         custom_agent   \n",
+       "6                      Multiverse Math     openai_assistant   \n",
+       "7                      Multiverse Math     openai_assistant   \n",
+       "8                      Multiverse Math     openai_functions   \n",
+       "9                      Multiverse Math     openai_functions   \n",
+       "10                     Multiverse Math     openai_functions   \n",
+       "11                     Multiverse Math     openai_functions   \n",
+       "12                     Multiverse Math     openai_functions   \n",
+       "13        Tool Usage - Relational Data  anthropic_tool_user   \n",
+       "14        Tool Usage - Relational Data         custom_agent   \n",
+       "15        Tool Usage - Relational Data         custom_agent   \n",
+       "16        Tool Usage - Relational Data         custom_agent   \n",
+       "17        Tool Usage - Relational Data         custom_agent   \n",
+       "18        Tool Usage - Relational Data         custom_agent   \n",
+       "19        Tool Usage - Relational Data     openai_assistant   \n",
+       "20        Tool Usage - Relational Data     openai_assistant   \n",
+       "21        Tool Usage - Relational Data     openai_functions   \n",
+       "22        Tool Usage - Relational Data     openai_functions   \n",
+       "23        Tool Usage - Relational Data     openai_functions   \n",
+       "24        Tool Usage - Relational Data     openai_functions   \n",
+       "25        Tool Usage - Relational Data     openai_functions   \n",
+       "26    Tool Usage - Typewriter (1 tool)  anthropic_tool_user   \n",
+       "27    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "28    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "29    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "30    Tool Usage - Typewriter (1 tool)         custom_agent   \n",
+       "31    Tool Usage - Typewriter (1 tool)     openai_assistant   \n",
+       "32    Tool Usage - Typewriter (1 tool)     openai_assistant   \n",
+       "33    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "34    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "35    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "36    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "37    Tool Usage - Typewriter (1 tool)     openai_functions   \n",
+       "38  Tool Usage - Typewriter (26 tools)  anthropic_tool_user   \n",
+       "39  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "40  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "41  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "42  Tool Usage - Typewriter (26 tools)         custom_agent   \n",
+       "43  Tool Usage - Typewriter (26 tools)     openai_assistant   \n",
+       "44  Tool Usage - Typewriter (26 tools)     openai_assistant   \n",
+       "45  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "46  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "47  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "48  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "49  Tool Usage - Typewriter (26 tools)     openai_functions   \n",
+       "\n",
+       "                             model  total  num_correct  % correct     error  \n",
+       "0                       claude-2.1     20         12.0   0.600000  0.109545  \n",
+       "1                       gemini-pro     20          7.0   0.350000  0.106654  \n",
+       "2                llama-v2-13b-chat     20          4.0   0.200000  0.089443  \n",
+       "3                llama-v2-70b-chat     20          5.0   0.250000  0.096825  \n",
+       "4            mixtral-8x7b-instruct     20          4.0   0.200000  0.089443  \n",
+       "5                      yi-34b-200k     20          1.0   0.050000  0.048734  \n",
+       "6   gpt-3.5-turbo-1106 (assistant)     20          9.0   0.450000  0.111243  \n",
+       "7   gpt-4-1106-preview (assistant)     20          9.0   0.450000  0.111243  \n",
+       "8   gpt-3.5-turbo-0613 (functions)     20         14.0   0.700000  0.102470  \n",
+       "9   gpt-3.5-turbo-1106 (functions)     20         10.0   0.500000  0.111803  \n",
+       "10          gpt-4-0613 (functions)     20         13.0   0.650000  0.106654  \n",
+       "11  gpt-4-1106-preview (functions)     20         11.0   0.550000  0.111243  \n",
+       "12        mistral-7b-instruct-v0.1     20         10.0   0.500000  0.111803  \n",
+       "13                      claude-2.1     21         15.0   0.714286  0.098581  \n",
+       "14                      gemini-pro     21         15.0   0.714286  0.098581  \n",
+       "15               llama-v2-13b-chat     21          3.0   0.142857  0.076360  \n",
+       "16               llama-v2-70b-chat     21          1.0   0.047619  0.046471  \n",
+       "17           mixtral-8x7b-instruct     21          8.0   0.380952  0.105971  \n",
+       "18                     yi-34b-200k     21          1.0   0.047619  0.046471  \n",
+       "19  gpt-3.5-turbo-1106 (assistant)     21         16.0   0.761905  0.092943  \n",
+       "20  gpt-4-1106-preview (assistant)     21         19.0   0.904762  0.064056  \n",
+       "21  gpt-3.5-turbo-0613 (functions)     21         17.0   0.809524  0.085689  \n",
+       "22  gpt-3.5-turbo-1106 (functions)     21         15.0   0.714286  0.098581  \n",
+       "23          gpt-4-0613 (functions)     21         20.0   0.952381  0.046471  \n",
+       "24  gpt-4-1106-preview (functions)     21         20.0   0.952381  0.046471  \n",
+       "25        mistral-7b-instruct-v0.1     21          4.0   0.190476  0.085689  \n",
+       "26                      claude-2.1     20         18.0   0.900000  0.067082  \n",
+       "27               llama-v2-13b-chat     20          0.0   0.000000  0.000000  \n",
+       "28               llama-v2-70b-chat     20          2.0   0.100000  0.067082  \n",
+       "29           mixtral-8x7b-instruct     20         12.0   0.600000  0.109545  \n",
+       "30                     yi-34b-200k     20          1.0   0.050000  0.048734  \n",
+       "31  gpt-3.5-turbo-1106 (assistant)     20         19.0   0.950000  0.048734  \n",
+       "32  gpt-4-1106-preview (assistant)     20         15.0   0.750000  0.096825  \n",
+       "33  gpt-3.5-turbo-0613 (functions)     20         17.0   0.850000  0.079844  \n",
+       "34  gpt-3.5-turbo-1106 (functions)     20         19.0   0.950000  0.048734  \n",
+       "35          gpt-4-0613 (functions)     20         14.0   0.700000  0.102470  \n",
+       "36  gpt-4-1106-preview (functions)     20         18.0   0.900000  0.067082  \n",
+       "37        mistral-7b-instruct-v0.1     20          1.0   0.050000  0.048734  \n",
+       "38                      claude-2.1     20         20.0   1.000000  0.000000  \n",
+       "39               llama-v2-13b-chat     20          0.0   0.000000  0.000000  \n",
+       "40               llama-v2-70b-chat     20          2.0   0.100000  0.067082  \n",
+       "41           mixtral-8x7b-instruct     20         12.0   0.600000  0.109545  \n",
+       "42                     yi-34b-200k     20          0.0   0.000000  0.000000  \n",
+       "43  gpt-3.5-turbo-1106 (assistant)     20         12.0   0.600000  0.109545  \n",
+       "44  gpt-4-1106-preview (assistant)     20         14.0   0.700000  0.102470  \n",
+       "45  gpt-3.5-turbo-0613 (functions)     20         10.0   0.500000  0.111803  \n",
+       "46  gpt-3.5-turbo-1106 (functions)     20          5.0   0.250000  0.096825  \n",
+       "47          gpt-4-0613 (functions)     20          8.0   0.400000  0.109545  \n",
+       "48  gpt-4-1106-preview (functions)     20         18.0   0.900000  0.067082  \n",
+       "49        mistral-7b-instruct-v0.1     20          1.0   0.050000  0.048734  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "stats_df"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d7eef8a9-366c-4620-9e2c-2e4d1287d267",
+   "metadata": {},
+   "source": [
+    "## Color palette"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7cd1965c-6bc9-4a3f-9f4a-a3698d165b39",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<svg  width=\"550\" height=\"55\"><rect x=\"0\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#0173b2;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"55\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#de8f05;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"110\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#029e73;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"165\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#d55e00;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"220\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#cc78bc;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"275\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#ca9161;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"330\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#fbafe4;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"385\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#949494;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"440\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#ece133;stroke-width:2;stroke:rgb(255,255,255)\"/><rect x=\"495\" y=\"0\" width=\"55\" height=\"55\" style=\"fill:#56b4e9;stroke-width:2;stroke:rgb(255,255,255)\"/></svg>"
+      ],
+      "text/plain": [
+       "[(0.00392156862745098, 0.45098039215686275, 0.6980392156862745),\n",
+       " (0.8705882352941177, 0.5607843137254902, 0.0196078431372549),\n",
+       " (0.00784313725490196, 0.6196078431372549, 0.45098039215686275),\n",
+       " (0.8352941176470589, 0.3686274509803922, 0.0),\n",
+       " (0.8, 0.47058823529411764, 0.7372549019607844),\n",
+       " (0.792156862745098, 0.5686274509803921, 0.3803921568627451),\n",
+       " (0.984313725490196, 0.6862745098039216, 0.8941176470588236),\n",
+       " (0.5803921568627451, 0.5803921568627451, 0.5803921568627451),\n",
+       " (0.9254901960784314, 0.8823529411764706, 0.2),\n",
+       " (0.33725490196078434, 0.7058823529411765, 0.9137254901960784)]"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import seaborn as sns\n",
+    "\n",
+    "pallete = sns.color_palette(\"colorblind\")\n",
+    "\n",
+    "pallete"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "112041b3-4580-4682-9621-e4ddfcb51dbe",
+   "metadata": {},
+   "source": [
+    "# Individual plots"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 72,
+   "id": "068c69be-32e4-40e7-809c-47a31a0f22c7",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "models = [\n",
+    "    # 'llama-v2-13b-chat',\n",
+    "    # 'llama-v2-70b-chat',\n",
+    "    # 'yi-34b-200k',\n",
+    "    # \"mistral-7b-instruct-v0.1\",\n",
+    "    # \"mixtral-8x7b-instruct\",\n",
+    "    \"gemini-pro\",\n",
+    "    \"claude-2.1\",\n",
+    "    \"gpt-3.5-turbo-0613 (functions)\",\n",
+    "    \"gpt-3.5-turbo-1106 (functions)\",\n",
+    "    'gpt-3.5-turbo-1106 (assistant)',\n",
+    "    \"gpt-4-0613 (functions)\",\n",
+    "    \"gpt-4-1106-preview (functions)\",\n",
+    "    'gpt-4-1106-preview (assistant)',\n",
+    "    \n",
+    "\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 75,
+   "id": "f53d65ac-7720-4dbd-9390-0a1a13cd3d07",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "assert len(models) <= len(pallete)\n",
+    "model_to_color = dict(zip(models, pallete))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 77,
+   "id": "daf8f644-342c-4b45-8b5c-6e176f8437c4",
+   "metadata": {
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 400x300 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 400x300 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 400x300 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAqsAAAEZCAYAAACw8WwSAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8g+/7EAAAACXBIWXMAAA9hAAAPYQGoP6dpAACi8ElEQVR4nOzdeVxN+f/A8ddt30sqKpItlUENspNtZN/3oezZqez7vkfGNmPJPoaxj2UkQtkjg5KRJWMKiaQo6v7+6Nf5drXdUsR8no9Hj0f3nM/5nPc53ep9P+ezyORyuRxBEARBEARBKIJUvnQAgiAIgiAIgpAdkawKgiAIgiAIRZZIVgVBEARBEIQiSySrgiAIgiAIQpElklVBEARBEAShyBLJqiAIgiAIglBkiWRVEARBEARBKLJEsioIgiAIgiAUWSJZFQRBEARBEIoskawK/zkBAQHIZDICAgIKtF6ZTMbMmTMLtM78cnNzw9ra+kuHIQiCIAifTCSrQpG2efNmZDKZ9KWmpoalpSVubm48efLks8dz9OjRIpOQFgRnZ2fp3qqoqGBgYEClSpXo06cPfn5+n1T3mjVr2Lx5c8EEKgiCIPxnqX3pAARBGbNnz6Zs2bK8e/eOixcvsnnzZgIDA7l16xZaWlqfLY6jR4+yevXqLBPWt2/foqb29f1KlSpVigULFgCQkJDAvXv32LdvH9u3b6dbt25s374ddXX1PNe7Zs0aTExMcHNzK+CIBUEQhP+Sr+8/q/Cf1LJlS2rUqAHAwIEDMTExYdGiRRw6dIhu3bp94ejSfM6kuSAZGhry448/KmxbuHAho0aNYs2aNVhbW7No0aIvFJ0gCILwXye6AQhfpQYNGgAQERGhsP3OnTt06dIFY2NjtLS0qFGjBocOHcq1vnPnztG1a1esrKzQ1NSkdOnSjB07lrdv30pl3NzcWL16NYBC14R0WfVZvX79Oi1btsTAwAA9PT2aNm3KxYsXFcqkd3UICgrCw8MDU1NTdHV16dixI8+fP1coe/DgQVq3bo2FhQWampqUL1+eOXPmkJKSkvtNywNVVVVWrlyJvb09q1atIi4uTtrn6+tLkyZNMDMzQ1NTE3t7e9auXatwvLW1Nbdv3+bMmTPSfXJ2dgYgNjYWLy8vqlSpgp6eHgYGBrRs2ZIbN24U6DUIgiAI3wbRsip8lR4+fAhAsWLFpG23b9+mXr16WFpaMnHiRHR1ddm9ezcdOnRg7969dOzYMdv69uzZQ2JiIkOHDqV48eJcvnyZn376iX/++Yc9e/YAMGTIEP7991/8/PzYtm1brjHevn2bBg0aYGBgwPjx41FXV+fnn3/G2dmZM2fOUKtWLYXyI0eOpFixYsyYMYOHDx+yYsUKRowYwW+//SaV2bx5M3p6enh4eKCnp8epU6eYPn06r1+/ZsmSJXm5hblSVVWlZ8+eTJs2jcDAQFq3bg3A2rVrqVy5Mu3atUNNTY3Dhw8zbNgwUlNTGT58OAArVqxg5MiR6OnpMWXKFABKlCgBwP379zlw4ABdu3albNmyPH36lJ9//plGjRoRGhqKhYVFgV6HIAiC8JWTC0IR5uvrKwfkJ0+elD9//lz++PFj+e+//y43NTWVa2pqyh8/fiyVbdq0qbxKlSryd+/eSdtSU1PldevWlVesWFHadvr0aTkgP336tLQtMTEx07kXLFggl8lk8kePHknbhg8fLs/u1waQz5gxQ3rdoUMHuYaGhjwiIkLa9u+//8r19fXlDRs2zHSNzZo1k6empkrbx44dK1dVVZW/evUqxziHDBki19HRUbhuV1dXeZkyZbKMM6NGjRrJK1eunO3+/fv3ywG5j49PjjG0aNFCXq5cOYVtlStXljdq1ChT2Xfv3slTUlIUtj148ECuqakpnz17dq4xC4IgCP8tohuA8FVo1qwZpqamlC5dmi5duqCrq8uhQ4coVaoUkPZo+dSpU3Tr1o34+HhiYmKIiYnhxYsXtGjRgr///jvH2QO0tbWl7xMSEoiJiaFu3brI5XKuX7+e53hTUlI4ceIEHTp0oFy5ctJ2c3NzevXqRWBgIK9fv1Y4ZvDgwQrdCho0aEBKSgqPHj3KMs7062zQoAGJiYncuXMnz3HmRk9PTzpXVjHExcURExNDo0aNuH//vkJ3gexoamqiopL2pyclJYUXL16gp6dHpUqVuHbtWgFfgSAIgvC1E90AhK/C6tWrsbGxIS4ujk2bNnH27Fk0NTWl/ffu3UMulzNt2jSmTZuWZR3Pnj3D0tIyy32RkZFMnz6dQ4cO8fLlS4V9yiRgH3v+/DmJiYlUqlQp0z47OztSU1N5/PgxlStXlrZbWVkplEvv4pAxntu3bzN16lROnTqVKdnNT5y5efPmDQD6+vrStqCgIGbMmMGFCxdITEzMFIOhoWGOdaampuLj48OaNWt48OCBQn/b4sWLF2D0giAIwrdAJKvCV8HJyUmaDaBDhw7Ur1+fXr16ER4ejp6eHqmpqQB4eXnRokWLLOuoUKFClttTUlJo3rw5sbGxTJgwAVtbW3R1dXny5Alubm5S3YVNVVU1y+1yuRyAV69e0ahRIwwMDJg9ezbly5dHS0uLa9euMWHChEKJ89atW8D/7l1ERARNmzbF1tYWb29vSpcujYaGBkePHmX58uVKxTB//nymTZtG//79mTNnDsbGxqioqDBmzJjPdq8FQRCEr4dIVoWvjqqqKgsWLKBx48asWrWKiRMnSo/a1dXVadasWZ7qu3nzJnfv3mXLli307dtX2p7VpPgZH9PnxNTUFB0dHcLDwzPtu3PnDioqKpQuXTpPcQYEBPDixQv27dtHw4YNpe0PHjzIUz3KSklJYefOnejo6FC/fn0ADh8+TFJSEocOHVJoCT59+nSm47O7V7///juNGzdm48aNCttfvXqFiYlJAV6BIAiC8C0QfVaFr5KzszNOTk6sWLGCd+/eYWZmhrOzMz///DNRUVGZyn88BVRG6S2a6S2Y6d/7+PhkKqurqwukJVY5UVVV5YcffuDgwYPSzAUAT58+ZefOndSvXx8DA4Mc61AmzuTkZNasWZOnepSRkpLCqFGjCAsLY9SoUVKsWcUQFxeHr69vpjp0dXWzvE+qqqoKx0PabAxfYkUyQRAEoegTLavCV2vcuHF07dqVzZs34+7uzurVq6lfvz5VqlRh0KBBlCtXjqdPn3LhwgX++eefbOfxtLW1pXz58nh5efHkyRMMDAzYu3dvpr6rANWrVwdg1KhRtGjRAlVVVXr06JFlvXPnzsXPz4/69eszbNgw1NTU+Pnnn0lKSmLx4sV5vt66detSrFgxXF1dGTVqFDKZjG3btmVK/PIqLi6O7du3A5CYmCitYBUREUGPHj2YM2eOVPaHH35AQ0ODtm3bMmTIEN68ecP69esxMzPL9CGhevXqrF27lrlz51KhQgXMzMxo0qQJbdq0Yfbs2fTr14+6dety8+ZNduzYoTAQTRAEQRAkX2weAkFQQvq0TleuXMm0LyUlRV6+fHl5+fLl5R8+fJDL5XJ5RESEvG/fvvKSJUvK1dXV5ZaWlvI2bdrIf//9d+m4rKauCg0NlTdr1kyup6cnNzExkQ8aNEh+48YNOSD39fWVyn348EE+cuRIuampqVwmkylMY8VHU1fJ5XL5tWvX5C1atJDr6enJdXR05I0bN5afP39eqWvMKs6goCB57dq15dra2nILCwv5+PHj5X/++WemcnmZugqQvvT09OQVK1aU//jjj/ITJ05kecyhQ4fkVatWlWtpacmtra3lixYtkm/atEkOyB88eCCVi46Olrdu3Vqur68vB6RprN69eyf39PSUm5uby7W1teX16tWTX7hwQd6oUaMsp7oSBEEQ/ttkcvknNssIgiAIgiAIQiERfVYFQRAEQRCEIkskq4IgCIIgCEKRJZJVQRAEQRAEocgSyaogCIIgCIJQZIlkVRAEQRAEQSiyRLKqJLlczuvXrz95TktBEISiQvxdEwThayAWBVDS69evMTIy4vHjx3leeUgQBKEoev36NaVLl+bVq1cYGhp+6XAEQRCyJJJVJcXHxwPkeT13QRCEoi4+Pl4kq4IgFFkiWVWSvr4+gGhZFQThm5Hespr+900QBKEoEsmqkmQyGQAGBgYiWRUE4ZuS/vdNEAShKBIDrARBEARBEIQiSySrgiAIgiAIQpElklVBEARBEAShyBLJqiAIgiAIglBkiWRVEARBEARBKLJEsioIgiAIgiAUWSJZFQThk6xevRpra2u0tLSoVasWly9fzrbs+/fvmT17NuXLl0dLS4tq1apx/PhxhTIzZ85EJpMpfNna2n71MQmCIAj5I5JVQRDy7bfffsPDw4MZM2Zw7do1qlWrRosWLXj27FmW5adOncrPP//MTz/9RGhoKO7u7nTs2JHr168rlKtcuTJRUVHSV2Bg4FcdkyAIgpB/MrlcLv/SQXwNXr9+jaGhIXFxcWJRAEH4f7Vq1aJmzZqsWrUKgNTUVEqXLs3IkSOZOHFipvIWFhZMmTKF4cOHS9s6d+6MtrY227dvB9JaMQ8cOEBISMg3E1NRJf6uCYLwNRAtq4Ig5EtycjLBwcE0a9ZM2qaiokKzZs24cOFClsckJSWhpaWlsE1bWztTK+Xff/+NhYUF5cqVo3fv3kRGRn61MQmCIAifRiSrgiDkS0xMDCkpKZQoUUJhe4kSJYiOjs7ymBYtWuDt7c3ff/9Namoqfn5+7Nu3j6ioKKlMrVq12Lx5M8ePH2ft2rU8ePCABg0aEB8f/1XGJAiCIHwakawKgvDZ+Pj4ULFiRWxtbdHQ0GDEiBH069cPFZX//Slq2bIlXbt2pWrVqrRo0YKjR4/y6tUrdu/e/Z+JSRAEQfgfkawKgpAvJiYmqKqq8vTpU4XtT58+pWTJklkeY2pqyoEDB0hISODRo0fcuXMHPT09ypUrl+15jIyMsLGx4d69e19lTIIgCMKnEcmqIAj5oqGhQfXq1fH395e2paam4u/vT506dXI8VktLC0tLSz58+MDevXtp3759tmXfvHlDREQE5ubmX2VM2Sno6bUEQRC+WfL/iDNnzsjbtGkjNzc3lwPy/fv35+n4uLg4OSCPi4srnAAF4Su0a9cuuaampnzz5s3y0NBQ+eDBg+VGRkby6OhouVwul/fp00c+ceJEqfzFixfle/fulUdERMjPnj0rb9Kkibxs2bLyly9fSmU8PT3lAQEB8gcPHsiDgoLkzZo1k5uYmMifPXv21caUVYwaGhryTZs2yW/fvi0fNGiQ3MjISP706dMsy48fP15uYWEhP3LkiDwiIkK+Zs0auZaWlvzatWv5On868XdNEISvwX8mWT169Kh8ypQp8n379olkVRAK0E8//SS3srKSa2hoyJ2cnOQXL16U9jVq1Eju6uoqvQ4ICJDb2dnJNTU15cWLF5f36dNH/uTJE4X6unfvLjc3N5draGjILS0t5d27d5ffu3fvq48pIycnJ/nw4cOl1ykpKXILCwv5ggULsixvbm4uX7VqlcK2Tp06yXv37p3vGORy8XdNEISvw39ynlWZTMb+/fvp0KGD0seI+QgFQSgIycnJ6Ojo8Pvvvyv8DXJ1deXVq1ccPHgw0zHFixdn8eLFDBgwQNr2448/EhgYyMOHD/Mdi/i7JgjC10DtSwdQVCUlJZGUlCS9fv369ReMRhC+PukrPSnL3Nz8k/qAKqMoxJTT9Fp37tzJ8pj06bUaNmxI+fLl8ff3Z9++faSkpBRobIIgCEWRSFazsWDBAmbNmvWlwxCEr9bPP/+cp9+hGTNmMHPmzMILiKIZkzJ8fHwYNGgQtra2yGQyypcvT79+/di0adOXDk0QBKHQFalk1d7enkGDBtG3b1+KFy/+RWOZNGkSHh4e0uvXr19TunTpLxiRIHxdhgwZQrt27aTXb9++pX79+gAEBgaira2tUL6wW1WLSkyfMr3Wu3fvePHiBRYWFkycODHH6bUEQRC+FUUqWY2MjMTLy4vJkyfToUMHBg0aRJMmTb5ILJqammhqan6RcwvCt+DjR+gJCQnS9w4ODujq6v4nY8o4vVZ6n9X06bVGjBiR47Hp02u9f/+evXv30q1bt0KPVxAE4UsrUvOsRkdHs2bNGr777jt+++03mjdvToUKFVi4cGG2SyUKgiB8bTw8PFi/fj1btmwhLCyMoUOHkpCQQL9+/QDo27cvkyZNkspfunSJffv2cf/+fc6dO4eLiwupqamMHz/+S12CIAjCZ1OkklU9PT2GDBnClStXuHHjBsOGDePly5dMnjwZKysrOnXqxLFjx8jPBAZv3rwhJCSEkJAQAB48eEBISAiRkZEFfBWCIAg56969O0uXLmX69Ok4ODgQEhLC8ePHpUFXkZGRCgPB3r17x9SpU7G3t6djx45YWloSGBiIkZHRF7oCQRCEz6fIT12VlJTE77//zsaNGzlz5gwAlpaWDBgwgIEDB2JpaalUPQEBATRu3DjTdldXVzZv3pzr8WKKF0H4NAkJCejp6QFpHx6/RDeAjxXFmD4n8XdNEISvQZFPViFtqpfNmzezfPlyhdYGdXV1Bg4cyJIlS9DR0SnUGMQfdUH4NEUxMSwKMX3J6bTE3zVBEL4GRWqA1cdOnDjBhg0bOHToEO/fv8fc3Jxp06bh6urKtWvXWLZsGevWrSMxMRFfX98vHa4gCEKefa3TaQmCIHwuRa5l9cmTJ2zatAlfX18ePXoEwA8//MCQIUNo27YtqqqqCuXbtm1LUFAQsbGxhRqXaIEQhE9TFFoxP1YUYvq4ZVWZ6bREy6ogCP8lRapltU2bNvz555/S6i4TJkxg8ODBWFtbZ3tM3bp1OXr06OcLUigUq1evZsmSJURHR1OtWjV++uknnJycsi2/YsUK1q5dS2RkJCYmJnTp0oUFCxagpaUFwNmzZ1myZAnBwcFERUXleXldQXmRkZHExMTkWu7t27fS9yEhIZmSsJyYmJhgZWVVZGLKazw5KQrTaQmCIBRlRSpZPXbsGI0bN2bIkCF07NgRNbXcw2vbti0WFhafITqhsPz22294eHiwbt06atWqxYoVK2jRogXh4eGYmZllKr9z504mTpzIpk2bqFu3Lnfv3sXNzQ2ZTIa3tzeQ9g+/WrVq9O/fn06dOn3uS/rPiIyMxM7WlsQMSZ8y0lsOlaWjrU3YnTtKJYiRkZHY2dmRmJhYaDHp6OgQFhZWYAmrIAiCkL0ilayGh4dToUKFPB3z3Xff8d133xVSRMLn4O3tzaBBg6Q5JtetW8eRI0fYtGkTEydOzFT+/Pnz1KtXj169egFgbW1Nz549uXTpklSmZcuWtGzZ8vNcwH9YTEwMiW/fMrtPQ6xLGOZYNin5A4NWHgNg/aiWaGoo9+fn4dM4pm87S0xMjFLJYUxMDImJiWwZsxLbUhVzLPs26R3OUzoCEDBvP9qaWrnWf+efv3FdMUrpeARBEIRPU6SS1bwmqsLXLzk5meDgYIUJ0FVUVGjWrBkXLlzI8pi6deuyfft2Ll++jJOTE/fv3+fo0aP06dPnc4UtfMS6hCG2pU1yLPM26b30vU2p4mhrqhdqTLalKvJ9+So5lkl497/WV4dyldHVKtxZRQRBEIS8+6LJ6tmzZ/N9bMOGDQswEuFLiYmJkfooZ1SiRAnu3LmT5TG9evUiJiaG+vXrI5fL+fDhA+7u7kyePPlzhCwIgiAIwmf0RZNVZ2dnZDJZvo5NSUkp4GiEr0VAQADz589nzZo11KpVi3v37jF69GjmzJnDtGnTvnR4giDkQNnBbwWlIAfDCYLwZXzRZHX69On5TlaFb4OJiQmqqqo8ffpUYfvTp08pWbJklsdMmzaNPn36MHDgQACqVKlCQkICgwcPZsqUKaioFKlVhAVB+H+RkZFUsrXj3du8DX77FFraOoTf+ToGw1lbWzNmzBjGjBmjVPn0lRlfvnwplt4VvmlfNFkVE1sLGhoaVK9eHX9/f2lqqdTUVPz9/RkxYkSWxyQmJmZKSNPn3y1i0wYLgpBBTExMWqLaygOMSxf+CWMf8+6o91czGO7KlSt5mqqsbt26REVFYWiY8+BGQfjaFakBVpGRkRgZGeU4OXV8fDwvX778Kv7wCMrx8PDA1dWVGjVq4OTkxIoVK0hISJBmB+jbty+WlpYsWLAASJuuzNvbG0dHR6kbwLRp0xQWjXjz5g337t2TzvHgwQNCQkIwNjYW7x1B+NKMSyMrUb7QT/O1fXQ1NTXNU3kNDY1sn0B9iuTkZDQ0NAq8XkHIryL1vLRs2bL4+PjkWGblypWULVv2M0UkfA7du3dn6dKlTJ8+HQcHB0JCQjh+/Lg06CoyMlJhhZ+pU6fi6enJ1KlTsbe3Z8CAAbRo0YKff/5ZKnP16lUcHR1xdHQE0hJiR0dHpk+f/nkvroCtXr0aa2trtLS0qFWrFpcvX862bHqf8I+/WrdurVAuLCyMdu3aYWhoiK6uLjVr1iQyMrKwL0UQiqz4+Hh69+6Nrq4u5ubmLF++HGdnZ+nxfFJSEl5eXlhaWqKrq0utWrUICAiQjt+8eTNGRkb88ccfVKpUCR0dHbp06ZI2pdqWLVhbW1OsWDFGjRqlMP7C2tqaFStWSK9lMhkbNmygY8eO6OjoULFiRQ4dOiTtDwgIQCaT8erVq2yvZebMmTg4OPDzzz9TunRpdHR06NatG3FxcVIZNzc3OnTowLx587CwsKBSpUoA3Lx5kyZNmqCtrU3x4sUZPHgwb968+bSbKwj5UKRaVuVyea6PccVj3m/TiBEjsn3sn/GfAICamhozZsxgxowZ2dbn7Oz8zb1X8rp4wr59+0hOTpZev3jxgmrVqtG1a1dpW0REBPXr12fAgAHMmjULAwMDbt++La0E9ili4hKJef2/volJyR+k7+/+8yLTPKsmBjqYGBbu1FFRsU+JevlMev02+Z30fciD22hrKF63eTEzzI0VZ6oQvn0eHh4EBQVx6NAhSpQowfTp07l27RoODg5A2t+r0NBQdu3ahYWFBfv378fFxYWbN29SsWLa3L6JiYmsXLmSXbt2ER8fT6dOnejYsSNGRkYcPXqU+/fv07lzZ+rVq0f37t2zjWXWrFksXryYJUuW8NNPP9G7d28ePXqEsbGx0tdz7949du/ezeHDh3n9+jUDBgxg2LBh7NixQyrj7++PgYEBfn5+QNrCKi1atKBOnTpcuXKFZ8+eMXDgQEaMGMHmzZvzflMF4RMUqWRVGf/88w/6+vpfOgzhM/p47fTcFOTa6UVJXhdP+Pif2a5du9DR0VFIVqdMmUKrVq1YvHixtK18+YJ5PLvvfDgbjodkuS99cYCMBro4MLilY4GcOzvrT2xnzm/Ls9znPLljpm3Tuo9leg/PAjn317QE7H9ZfHw8W7ZsYefOnTRt2hQAX19faaXEyMhIfH19iYyMlLZ5eXlx/PhxfH19mT9/PgDv379n7dq10u9Tly5d2LZtG0+fPkVPTw97e3saN27M6dOnc0xW3dzc6NmzJwDz589n5cqVXL58GRcXF6Wv6d27d2zduhVLS0sAfvrpJ1q3bs2yZcukbgS6urps2LBBevy/fv166bj0frSrVq2ibdu2LFq0KNN0g4JQmL54sjp79myF1x+3oqVLSUnh8ePH7Nq1i9q1a3+GyISi4ueff2bWrFlKl58xY8Y3N3gvP4snfGzjxo306NFD+seTmprKkSNHGD9+PC1atOD69euULVuWSZMmSYPdPkWnupVo+J3yg2hMDAp/Qv5BP/xIm5o/KF3evFjmFuv8iIyMxNbWViERVUZeloDV1tbmjpJL0grZu3//Pu/fv8fJyUnaZmhoqPBoPCUlBRsbG4XjkpKSKF68uPRaR0dH4YNfiRIlsLa2Rk9PT2Hbs2fPyEnVqlWl73V1dTEwMMj2mIx1//jjj6xbtw4AKysrKVEFqFOnDqmpqYSHh0vJapUqVRT6qYaFhVGtWjWFAV/16tWTjhPJqvA5ffFkNWNSIZPJCAgIyDZhBbCwsGDRokWFH5hQZAwZMoR27dpJr9++fSv9Ew8MDMzU8vQttqrmZ/GEjC5fvsytW7fYuHGjtO3Zs2e8efOGhQsXMnfuXBYtWsTx48fp1KkTp0+fplGjRp8Us4lh4T/Wzytz4xJf5LF+TEwMb9++xdXVNdcBMcnJySxfntb6O3bsWKUGukRHR7Nly5avZtT71+zNmzeoqqoSHBwsDehMlzFZVFdXXKFNJpNluS01NTXH8+XlmJCQEOn7nAYqZyUvsxAIwuf2xZPV06dPA2l9UZs0aYKbmxuurq6ZyqmqqmJsbIytra2YR/M/5uPH+gkJCdL3Dg4O4o+sEjZu3EiVKlUUWovS/+G1b9+esWPHAmn38/z586xbt+6Tk1Uhs5IlS1K6dM6tzUlJSdL3pUqVQlNTs7DDEjIoV64c6urqXLlyRUr84+LiuHv3Lg0bNsTR0ZGUlBSePXtGgwYNvnC0irJbsjwyMpJ///1X6rZw8eJFVFRUpNbirNjZ2bF582YSEhKkv7FBQUG5HicIheGLJ6sZ/yHOmDEDZ2dn8U9SED6Sn8UT0iUkJLBr165MXW5MTExQU1PD3t5eYbudnR2BgYEFE7ggZCX28eeZVir2cZ4P0dfXx9XVlXHjxmFsbIyZmRkzZsxARUUFmUyGjY0NvXv3pm/fvixbtgxHR0eeP3+Ov78/VatWzTTbRlGgpaWFq6srS5cu5fXr14waNYpu3brl+Lejd+/ezJgxA1dXV2bOnMnz588ZOXIkffr0EV0AhM/uiyerGeU0ulsQ/svys3hCuj179pCUlMSPP/6Yqc6aNWsSHh6usP3u3buUKVOmQOMXBEj7gKSlrcO7o96f7Zxa2jqYmJjk6Rhvb2/c3d1p06YNBgYGjB8/nsePH0uzZPj6+jJ37lw8PT158uQJJiYm1K5dmzZt2hTGJXyyChUq0KlTJ1q1akVsbCxt2rRhzZo1OR6jo6PDn3/+yejRo6lZsyY6Ojp07twZb+/P97MThHRFKlndsmULK1eu5PDhw9Ljioz+/fdf2rZti6enJ7169foCEQrCl5PXxRPSbdy4kQ4dOigM/kg3btw4unfvTsOGDWncuDHHjx/n8OHDOfYbF4T8srKyIvxOmFKzIhSU/MySoK+vrzCtU0JCArNmzWLw4MFAWj/SWbNmZTvw083NDTc3N4VtM2fOzDTw8+MpoB4+fKjwOqvp9zLOqZqXKfqGDh3K0KFDs9yX3VRUVapU4dSpU0rVLwiFqUglq5s3b0ZDQyPLRBXSBldpa2uzceNGkawK/zndu3fn+fPnTJ8+nejoaBwcHDItnvBxf+7w8HACAwM5ceJElnV27NiRdevWsWDBAkaNGkWlSpXYu3dvnkahC0JeWFlZFflBYNevX+fOnTs4OTkRFxcndaFp3779F45MEP6bitRIpdDQUGnFoew4ODgQGhr6mSIqGAW96tC+ffv44YcfKF68ODKZTGEE6NccU1FTFO/RiBEjePToEUlJSVy6dIlatWpJ+wICAjK1kFSqVAm5XE7z5s2zrbN///78/fffvH37lpCQEPEPWRCApUuXUq1aNZo1a0ZCQgLnzp3Lc3cCQRAKRpFqWY2Li6NYsWI5ljEwMODly5efKaJPVxirDiUkJFC/fn26devGoEGDvomYipqv8R6JxRMEoWA4OjoSHBz8pcMoEFl1PxCEr02RSlYtLCxybW26cePGVzUSsTBWHerTpw+QuX/T1xxTUfM13iOxeIIgCILwLSpSyWqzZs3YtGkTfn5+WT62PHHiBMePH2fAgAFfILq8K4xVh77FmIqar/UeicUTBEEQhG9RkUpWJ02axG+//UarVq3o06cPzZs3x9LSkidPnnDixAm2b9+OgYGBQhJRlBXGqkPfYkxFzdd6j8TiCYIgCMK3qEglq2XLluXIkSP06NGDzZs3s2XLFmmfXC6nVKlS7N69m7Jly37BKD+frFYd+tKKYkxFjbhHQl7ExcXx+vVr6XXGvs///PNPpuVWDQwMMDQ0/GzxCYIgfGlFKlkFqF+/Pvfv3+fgwYNcvnyZuLg4jIyMcHJyol27dkqtk11UFMaqQ99iTEWNuEfC5xQYGMixY8ey3Ld8+fJM21q2bFkkV0kSBEEoLAWarMrlcu7du4eWllau61/nRENDg65duyoMTvkaFcaqQ99iTEWNuEfC51S/fn2qVq2qdHkDA4NCjKbwRUZGFvlFAbLz8OFDypYty/Xr13FwcCiQOrNjbW3NmDFjGDNmTKGeRxC+BvlKVvft28eBAwfw8fGRppp6+PAhbdu2leZA7dq1Kzt27EBVVTVfgb1584a7d++SkJBAgwYN8lVHUVAYqw7FxsYSGRnJv//+CyAtl1myZMlcW/6KakxFjbhHwudiaGj4n3msHxkZiZ1tJRLfvvts59TR1iLsTniRX4igMKxfv56tW7dy69YtAKpXr878+fNz7KIUFRWFp6cnV69e5d69e4waNYoVK1Z8pogFIWv5SlbXrl3L06dPFeZEHTt2LLdv36ZJkya8ePGCPXv20LRp0zzPJ/nw4UNGjx7N0aNHSU1NRSaT8eHDBwCCgoIYNGgQa9aswdnZOT+hf3aFserQoUOHpKQJoEePHoDyUxEVxZiKGnGPBKHgxcTEkPj2Hd4/qlLBTFbo57v3TI7H9nfExMT8J5PVgIAAevbsSd26ddHS0mLRokX88MMP3L59G0tLyyyPSUpKwtTUlKlTp2bZDUUQvoR8JauhoaG0bNlSeh0fH8+RI0fo3r07v/76K+/fv8fR0ZFNmzblKVmNjIykdu3avHjxgvbt2xMdHa0wVVCtWrWIiYnh119//WqSVUhbdSi7x8dZrcGevupQdrJad/pbiEnZx4Nv376Vvg8JCck0JVN28vo4sCjeI0H4FlQwk/Fd6cJPVvMrNTWVpUuX8ssvv/D48WNKlCjBkCFD6N27t0K5lJQUBg8ezKlTp4iOjsbKyophw4YxevRoqYyzszMODg4KrZMdOnTAyMhIWnHu2bNnDBgwgJMnT1KyZEnmzp2bKaZXr17h5eXFwYMHSUpKokaNGixfvpxq1aplex07duxQeL1hwwb27t2Lv78/ffv2zfIYa2trfHx8ANi0aVOO90kQPpd8JauxsbEKjy0DAwP58OEDPXv2BEBdXZ3mzZtn+kXJzYwZM3j58iVnzpyhbt26zJo1SyFZVVNTo0GDBgQFBeUn7CKnKK449KViioyMpJKtLe8yJKLKyMsa9lra2oTfuVMgLSxF8WcnCELBmDRpEuvXr2f58uXUr1+fqKioLKetS01NpVSpUuzZs4fixYtz/vx5Bg8ejLm5Od26dVP6fG5ubvz777+cPn0adXV1Ro0axbNnzxTKdO3aFW1tbY4dO4ahoSE///wzTZs25e7du5kWJclOYmIi79+/V7q8IBQV+UpWDQwMePHihfT69OnTqKioKPQtVVdXV5jnURl//vknHTt2pG7dutmWKVOmDKdOncp70EVQUVxx6EvFFBMTw7u3b5ENagUWOf8hlSd/gAW70l5M6oFMQ4m38b+xvFt/tMAeBxbFn50gCJ8uPj4eHx8fVq1ahaurKwDly5enfv36mVafU1dXV/g7ULZsWS5cuMDu3buVTlbv3r3LsWPHuHz5MjVr1gTS+r7b2dlJZQIDA7l8+TLPnj1DU1MTgKVLl3LgwAF+//13Bg8erNS5JkyYgIWFBc2aNVOqvCAUFflKVm1tbTl8+DBz585FVVWVnTt3Ur16dYU+rI8ePcrzsqixsbFYW1vnWEYul5OUlJSfsIucorji0BePycIYWZlc3jdJ70l/2C6zMkOmqZ5rtdk/nM+fL36fBEEoFGFhYSQlJdG0aVOlyq9evZpNmzYRGRnJ27dvSU5OztNMAWFhYaipqVG9enVpm62tLUZGRtLrGzdu8ObNm0wDN9++fUtERASRkZHY29tL2ydPnszkyZMVyi5cuJBdu3YREBCAlpaW0vEJQlGQr2R11KhRdO3alVKlSkktqB/3sbl48SLff/99nuotUaIEf//9d45lbt68+c10lC+KKw4VxZiKInGfBOHbpGwfeIBdu3bh5eXFsmXLqFOnDvr6+ixZsoRLly5JZVRUVDL1ZX///n2eYnrz5g3m5uZZ9pU3MjLCyMiIkJAQadvHj/mXLl3KwoULOXnyZJ6mSROEoiJfyWrnzp1ZvXq1tJxkjx49FAaOnDlzhtevX+Pi4pKneps3b862bdv466+/svyFOnfuHKdOnRLzzgmCIAiFomLFimhra+Pv78/AgQNzLBsUFETdunUZNmyYtC0iIkKhjKmpqUL/9pSUFG7dukXjxo2BtFbUDx8+EBwcLHUDCA8P59WrV9Ix33//PdHR0aipqWX79LFChQpZbl+8eDHz5s3jzz//pEaNGjlejyAUVfleFGDo0KEMHTo0y32NGjXi5cuXea5z6tSp/P777zRs2JBx48Zx7949AI4dO8b58+fx9vbGxMSEcePG5TdsQRAEQciWlpYWEyZMYPz48WhoaFCvXj2eP3/O7du3M3UNqFixIlu3buXPP/+kbNmybNu2jStXrigsCd6kSRM8PDw4cuQI5cuXx9vbWyERrVSpEi4uLgwZMoS1a9eipqbGmDFjFFp4mzVrRp06dejQoQOLFy/GxsaGf//9lyNHjtCxY8dsk9BFixYxffp0du7cibW1NdHR0QDo6emhp6cHpA0me/LkCVu3bpWOS2+lffPmDc+fPyckJAQNDQ2FrgaC8DkVqeVWra2t+fPPP+nRowfTpk1DJpMhl8tp06YNcrkcKysrfv/9d9H/TxAE4St271lB9yIv2PNMmzYNNTU1pk+fzr///ou5uTnu7u6Zyg0ZMoTr16/TvXt3ZDIZPXv2ZNiwYQrL5/bv358bN27Qt29f1NTUGDt2rNSqms7X15eBAwfSqFEjSpQowdy5c5k2bZq0XyaTcfToUaZMmUK/fv14/vw5JUuWpGHDhjmODVm7di3Jycl06dJFYXvGAZ9RUVFERkYq7Hd0dJS+Dw4OZufOnZQpUybTADNB+Fw+KVmNjo4mODiYV69ekZKSkmWZ7OZyy06tWrX4+++/OXz4MJcuXSI2NhYDAwNq1apF+/bt0dDQ+JSQBUEQhC/ExMQEHW0tPLZ/3hWsTExM8nSMiooKU6ZMYcqUKZn2Zex/qqmpia+vL76+vgplMq5sp66uzpo1a1izZk225ytZsiR//PGHwrY+ffoovNbX12flypWsXLlS6etQJrlMn+s1o5zmixaELyFfyeq7d+8YNGgQu3btIjU1NcsycrkcmUyWp2R19uzZlC1blj59+tCxY0c6duyYn/AEQRCEIsjKyoqwO+FKLf5RUPK6GIggCEVPvpLViRMnsmPHDmxsbOjZsyelSpVCTe3TexTMnTtXDJ4SBEH4hllZWYnkURCEPMlXhrl7927s7e0JDg6WJiguCFZWVgodzwVBUKTskrTw+ZalFQRBEITClK9k9dWrV/Tq1atAE1VImwJr69atxMXFYWhoWKB1C8LXLjIyEjtbOxLfJub52LwsS6ujrUPYnTCRsAqCIAhFQr6S1UqVKvH06dOCjoVp06YREhJCkyZNmD17NjVr1sTMzKzAzyMIX6OYmBgS3yYyp+0kyhbPPZF89z6JgTvGALCh9wq01HP/cPngRSTTDi8osGVpBUEQBOFT5StZHTduHO7u7ty7dy/biYjzQ0dHB0gbnJVxKcuPyWQyPnz4UGDnFYSvSdniVtiWrJhrubfJ/+sGUKlEebQ1lF+ZRxAEQRCKinwlq6VKlaJFixY4OTkxZswYvv/+ewwMDLIs27BhQ6XrbdCgATKZLD8hCYIgCIIgCN+gfCWrzs7O0oT9M2fOzDHBzG7+1axkte6xIAiCIAiC8N+Vr2R1+vTphdIC2qRJE+rXr8/s2bMLvG5BEARBEATh65OvZDV9mbaCdunSJWrXrl0odQtfL/mrNxCX8L/Xyf/rryyPfAYaH72NDXWRGel9rvAEQciDvEy/VhDEVGyFx9ramjFjxvwn50d/8eIFdnZ2XL58GWtrawCCgoJwd3fnzp07tG7dmgMHDnyx+Nzc3Hj16tVni+H48eNMnDiRa9euoaKiUuD1f/pM/gXI1taWR48efekwhCJGHvAXHLqQ9c4Fu8i0MGC7Osg61C3ssARByKPIyEgq2dryLsMcwIVNS1ub8Dt3PnvCKpPJ2L9/Px06dMix3L59+5g/fz737t3j/fv3VKxYEU9Pz0zLrWYUEBBA48aNM22PioqiZMmS2R73NSWXf/31F8OHD+fKlSuYmpoycuRIxo8fr1Dm1atXTJkyhX379hEbG0uZMmVYsWIFrVq1AuDs2bMsWbKE4OBgoqKisvx5zJw5k127dvH48WM0NDSoXr068+bNo1atWjnGN2/ePNq3by8lqgAeHh44ODhw7Ngx9PQ+T4PJw4cPKVu2LNevX8fBwUHa7uPj81mXzXVxcWHatGns2LEjx/dufn1SspqQkMCBAwcICQnh9evXGBgY4ODgQIcOHdDV1c1zfSNHjmTEiBGEhoZib2//KaEJ3xCZc1VwLK/8AYZ5f+8JglD4YmJiePf2LbJBrcDCuPBP+G8s79YfLdJTsRkbGzNlyhRsbW3R0NDgjz/+oF+/fpiZmdGiRYscjw0PD1cY3Py5pnpMTk5GQ0Oj0Op//fo1P/zwA82aNWPdunXcvHmT/v37Y2RkxODBg6UYmjdvjpmZGb///juWlpY8evQIIyMjqZ6EhASqVatG//796dSpU5bnsrGxYdWqVZQrV463b9+yfPlyfvjhB+7du4epqWmWxyQmJrJx40b+/PNPhe0RERG4u7tTqlSpgrkRn+BLzFXv5ubGypUri1ayunfvXgYPHsyrV68UsneZTIaRkRHr16/P9s2RnXLlyuHs7Ezt2rUZMmQINWvWpESJEln2j83LLANfmrKPvfK74hDk/VFXUYwpOzIjPfhCj/UL+z6JR5TCf5KFMbIyJQr9NPlpV4qPj8fd3Z0DBw5gYGDA+PHjOXjwIA4ODqxYsQJIa6EcMGAAoaGhHDp0CCMjIyZPnszw4cOl/QAdO3YEoEyZMjx8+DDL8zk7Oyu8Hj16NFu2bCEwMDDXZNXMzEwhOcuJs7Mzjx49YuzYsYwdOxZAGiSd3uiUbsWKFaxYsUKKOf2Rcs2aNVm9ejWampo8ePBAul89e/bM8j5A2t/QkSNH4u/vj4qKCi4uLvz000+UKJH9z3/Hjh0kJyezadMmNDQ0qFy5MiEhIXh7e0vJ6qZNm4iNjeX8+fOoq6sDKLRyArRs2ZKWLVvmeF969eql8Nrb25uNGzfy119/0bRp0yyPOXr0KJqamlK3xfTWTYD+/fvTv39/fH19ARgzZozCypwHDhygY8eOUt6Ufv89PT2ZNm0aL1++pGXLlqxfvx59fX0AUlNTWbp0Kb/88guPHz+mRIkSDBkyhClTpkjndXR0BKBRo0YEBARk6gaQlJTEuHHj2LVrF69fv6ZGjRosX76cmjVrAv9rrT958iQTJkwgNDQUBwcHfH19qVSpEgA3btxgzJgxXL16FZlMRsWKFfn555+pUaMGAG3btmXEiBFERERQvnweGpiUkK9k9fz58/To0QNVVVUGDhxI48aNMTc3Jzo6mtOnT7NlyxZ69OjBmTNnqFOnjtL1ZpxlYNmyZQU2y8CXlPbYy453eVx1KC8rDgFoaesQruSqQ2krIVUi8e27Qo1JR1uLsDvhX20y9jnu09d+jwThW+Ph4UFQUBCHDh2iRIkSTJ8+nWvXrik8YgVYsmQJkydPZtasWfz555+MHj0aGxsbmjdvzpUrVzAzM8PX1xcXFxdUVVWVOrdcLufUqVOEh4ezaNGiXMs7ODiQlJTEd999x8yZM6lXr162Zfft20e1atUYPHgwgwYNUiqejPz9/TEwMMDPz09he073ITU1lfbt26Onp8eZM2f48OEDw4cPp3v37jnO/nPhwgUaNmyo0HrbokULFi1axMuXLylWrBiHDh2iTp06DB8+nIMHD2JqakqvXr2YMGGC0vf7Y8nJyfzyyy8YGhpSrVq1bMudO3eO6tWrS69Lly5NVFQUlSpVYvbs2XTv3h1DQ0N+++03pc4bERHBgQMH+OOPP3j58iXdunVj4cKFzJs3D4BJkyaxfv16li9fTv369YmKiuLOnTsAXL58GScnJ06ePEnlypWzbfEeP348e/fuZcuWLZQpU4bFixfTokUL7t27h7Hx/55yTJkyhWXLlmFqaoq7uzv9+/cnKCgIgN69e+Po6MjatWtRVVUlJCRE+qAAYGVlRYkSJTh37lzRSFbnz5+PpqYmQUFBmX6g3bt3Z9iwYdStW5f58+dz+PBhpestrFkGvqS0x16J0MoDjEvnXPhDEuyamPZ9j4WgpuRytrGPeXfUW+lHXWkrIb3D+0dVKpjlfL/fvZfT7ae0Dwa7R6qipa7cz+feMzke298V6cdvuUm/T4vqQ7lcnqi8+wB9/v+J0LYWoKXEb9b9OJgQ+HXfI0H4lsTHx7NlyxZ27twptar5+vpiYWGRqWy9evWYODHt77WNjQ1BQUEsX76c5s2bS4+PjYyMcuxDmi4uLg5LS0uSkpJQVVVlzZo1NG/ePNvy5ubmrFu3jho1apCUlMSGDRtwdnbm0qVLfP/991keY2xsjKqqKvr6+krF9DFdXV02bNiQKRnK6T74+/tz8+ZNHjx4QOnSaf//tm7dSuXKlbly5YrUqvex6OhoqcUwXXpLbHR0NMWKFeP+/fucOnWK3r17c/ToUe7du8ewYcN4//49M2bMyNO1/fHHH/To0YPExETMzc3x8/PDxMQk2/KPHj1SeE+oqqpSsmRJZDIZhoaGeb6/qampbN68WWpJ7dOnD/7+/sybN4/4+Hh8fHxYtWoVrq6uAJQvX15qFEl/rxUvXjzb8yYkJLB27Vo2b94stTSvX78ePz8/Nm7cyLhx46Sy8+bNo1GjRgBMnDiR1q1b8+7dO7S0tIiMjGTcuHHY2toCULFi5sVpLCwsCmXsUb6S1QsXLtC9e/dsP3lUrVqVbt26cfDgwTzVW1izDBQJxqWRlcj5k4b8fYYWPLNyyNS1lKo6v12oK5jJ+K50zslnYtL/vre3lKGj+W19mFBGOUOwL55zmcT3//ve1hh01LMvKwhC0XT//n3ev3+Pk5OTtM3Q0FB6DJrRx08N69SpI3UTyEpkZKTCWIzJkyczefJkAPT19QkJCeHNmzf4+/vj4eEhdYvLSqVKlRRiqlu3LhERESxfvpxt27axY8cOhgwZIu0/duwYDRo0yPHac1OlSpUsW+1yug9hYWGULl1aSlQB7O3tMTIyIiwsjJo1a1K5cmUpuWnQoAHHjh1TKp7U1FTMzMz45ZdfUFVVpXr16jx58oQlS5bkOVlt3LgxISEhxMTEsH79erp168alS5ey7QP89u1btLSU+/+sDGtraylRhbQPI8+ePQPS7mFSUlK2XRKUERERwfv37xVa3tXV1XFyciIsLEyhbNWqVRXiAHj27BlWVlZ4eHgwcOBAtm3bRrNmzejatWumFlRtbW0SE/P2JFkZ+UpWExMTc+xvAmmfggojYEEQBEH42lhYWCj0C8346FVFRUVautzBwYGwsDAWLFiQbbKaFScnJwIDAwFo166dwmh2S0vLbI9TUVHJNGr8/fv3mcrlZ9C0Mo4ePSqdL72vf8mSJXn69KlCufTX6a2H5ubmqKurKzzyt7OzIzo6Os8DwHR1dalQoQIVKlSgdu3aVKxYkY0bNzJp0qQsy5uYmPDy5ctc61X23mZ8lA5pY39SU1MB8jROpCBkjCX9SXd6LDNnzqRXr14cOXKEY8eOMWPGDHbt2iX1zQaIjY3NdmDap8jXZFjW1taZ+q18zN/fP1NnZ2UlJCSwY8cOxo0bx5AhQxg3bhw7duwgISEh94MFQRAEIR/KlSuHuro6V65ckbbFxcVx9+7dTGUvXryY6bWdnZ30Wl1dXWFshZqampQQVahQQSFZ/VhqaipJSUnZ7s9KSEiI1BKmr6+vcK70hEdDQyPTeA9TU1Oio6MVkqqMSXVucroPdnZ2PH78mMePH0v7Q0NDefXqldTKXKZMGSnO9KS6Tp06nD17ViGx8/Pzo1KlShQrVgxI635w7949KZECuHv3Lubm5p88U0Fu99/R0ZHQ0NBc6zE1NSU+Pl4hd8nLvYW0R+3a2tr4+/tnuT/9WnMax1O+fHk0NDSkvqeQljRfuXIlzzMv2djYMHbsWE6cOEGnTp2kgWQA7969IyIiQhrsVZDylax269aN4OBgXF1d+ffffxX2RUVF4ebmRnBwMN27d89z3Xv37sXKyoq+ffuybNky1q9fz7Jly+jbty9WVlbs27cvPyELgiAIQo709fVxdXVl3LhxnD59mtu3bzNgwABUVFQyjacICgpi8eLF3L17l9WrV7Nnzx5Gjx4t7be2tsbf35/o6OgcW+EWLFiAn58f9+/fJywsjGXLlrFt2zZ+/PFHqcykSZPo27ev9HrFihUcPHiQe/fucevWLcaMGcOpU6cURuFnxdramrNnz/LkyRNplhNnZ2eeP3/O4sWLiYiIYPXq1Uo/is/tPjRr1owqVarQu3dvrl27xuXLl+nbty+NGjWSRpBnpVevXmhoaDBgwABu377Nb7/9ho+PDx4eHlKZoUOHEhsby+jRo7l79y5Hjhxh/vz5CvfgzZs3hISESAnigwcPCAkJITIyEkhrGJs8eTIXL17k0aNHBAcH079/f548eULXrl2zja9Fixbcvn0719bVWrVqoaOjw+TJk4mIiGDnzp1s3rw5t1uqQEtLiwkTJjB+/Hi2bt1KREQEFy9eZOPGjUDajBDa2tocP36cp0+fEhcXl6kOXV1dhg4dyrhx4zh+/DihoaEMGjSIxMREBgwYoFQcb9++ZcSIEQQEBPDo0SOCgoK4cuWKwge0ixcvoqmpmaeB9crKVzeACRMmcPz4cbZt28Zvv/1GhQoVKFGiBE+fPuXevXskJyfj5OTEhAkT8lRvYc0yIAiCIBQh/8bmu699Xs+TV97e3ri7u9OmTRtp6qrHjx9n6qPo6enJ1atXmTVrFgYGBnh7eytMNbVs2TI8PDxYv349lpaW2U5dlZCQwLBhw/jnn3/Q1tbG1taW7du3KzT2REVFSQkWpI1a9/T05MmTJ+jo6FC1alVOnjyZ5UIBGc2ePZshQ4ZQvnx5kpKSkMvl2NnZsWbNGubPn8+cOXPo3LkzXl5e/PLLL0rdr5zug0wm4+DBg4wcOZKGDRsqTF2VE0NDQ06cOMHw4cOpXr06JiYmTJ8+XZq2CtJG4P/555+MHTuWqlWrYmlpyejRoxXyjqtXryrck/Rk19XVlc2bN6OqqsqdO3fYsmULMTExFC9enJo1a3Lu3DkqV66cbXxVqlTh+++/Z/fu3Qp9gz9mbGzM9u3bGTduHOvXr6dp06bMnDlT4TqUMW3aNNTU1Jg+fTr//vsv5ubmuLu7A2kt9itXrmT27NlMnz6dBg0aZDnTwsKFC0lNTaVPnz7Ex8dTo0YN/vzzT6mlOjeqqqq8ePGCvn378vTpU0xMTOjUqROzZs2Syvz666/07t0bHR2dPF2fMvKVrOro6HD27FkWLVrE1q1bCQ0NlZrEy5Urh6urK+PHj0dTU8nR7P+vsGYZEARBEL48ExMTtLS1ebf+6Gc7p5a2do4juz+mr6/Pjh07pNcJCQnMmjUrU4JhYGDA7t27s62nbdu2tG3bNtfzzZ07l7lz5+ZY5uPWuPHjx2dazUkZtWvX5saNG5m2u7u7S8lPuvTBX1mdP112CXhGVlZWeR5sDWkDfc6dO5djmTp16mTqhpCRs7Nzjqs4aWlp5ftp7fTp0xk3bhyDBg2SlhfNOJ9qug4dOmRaNSvj1GEzZ87MNLj841XGVFRUmDJlClOmTMkyloEDBzJw4ECFbR//zLS0tFi5ciUrV67Mso6s7pWDg4PCtl9//TXLYyFt9pzff/+dq1evZlvmU+R7UQBNTU2mT5/O9OnTiY+Pl1awyjiiLa8Ka5YBQfgviHnzgpg3/2tJepdhdonwp/fQ+mh2CRM9Y0z0cpnmQBAKkJWVFeF37ii10EZByevCG9evX+fOnTs4OTkRFxfH7NmzAWjfvn1hhSh8hVq3bs3ff//NkydPFGY7+K96+PAha9asyTTlWEH5pOVW0+nr639SkppOzDIgCPm39/ofrA/aluW+gTvGZto2qF4fhjRwLeywBEGBlZVVkZ9XeOnSpYSHh0trxZ87dy5PrbPCf0PG1s//uho1auTYD/lTFUiyWlDSZxmYP39+tmU+ZZYBQfiWdXZsQ6OKdZUub6L3GdZmF4SvjKOjI8HBwTmWUebxtyAIBUepZLVcuXLIZDJOnjxJ2bJlKVeunFKVy2QyIiIilA6mW7duzJkzB1dXVxYsWKCwQkRUVBSTJk0iODiYadOmKV2nIPxXmOgVF4/1BUEQhG+OUslqamqqwrQdH7/OTk4dm7NSWLMMCIIgCIIgCF8npZLVjx95FNYjkMKaZUAQBEEQBEH4OhWpPqtQOLMMCIIgCIIgCF+nfK1g1aRJE7Zu3Zpjme3bt9OkSZN8BZVOX18fS0tLkagKgiAIgiD8R+UrWQ0ICMi1K8CjR484c+ZMrnXJ5XIGDRpE//79FdYB/lhycjL9+/fPNHGxIAiCIAiC8O0qtG4ACQkJqKur51pu//79bNq0iQ0bNuRYXkNDg0aNGtG/f39cXFwyrQghCIIgFH2RkZFFelEAQXnW1taZVlv6r0hOTsbe3p6tW7dSt27alIF37tzBzc2NkJAQbG1tCQkJ+WLxzZw5kwMHDny2GEJDQ/nhhx8IDw9HV1e3wOtXOlnNuC4xpC0r9vE2gJSUFB4/fszevXuVmg/1119/pWTJkri65j45eZ8+fZg6dSrbtm0TyaogCMJXJjIyEjvbSiS+fZd74QKio61F2J3wz56wymQy9u/fn+v/qn379jF//nzu3bvH+/fvqVixIp6envTp0yfbYwICAhTWvE8XFRVFyZIlsz3ua0ku3717h7u7O8HBwYSFhdGmTRsOHDigUCYqKgpPT0+uXr3KvXv3GDVqFCtWrMhU1549e5g2bRoPHz6kYsWKLFq0iFatWimUCQsLY8KECZw5c4YPHz5gb2/P3r17c3zPrFu3jrJly0qJKsCMGTPQ1dUlPDwcPT29T7oHeZHVe83Ly4uRI0d+thjs7e2pXbs23t7ehTK9qNLJqrW1tTRdlUwmw8fHBx8fn2zLy+VylixZkmu9ly5dolmzZtLaujlRUVGhadOmnDp1StmwBUEQhCIiJiaGxLfvWFQfyhkW/vnux8GEwHfExMQU2dZVY2NjpkyZgq2tLRoaGvzxxx/069cPMzMzWrRokeOx4eHhGBgYSK/NzMwKO1wgrVVRQ0Oj0OpPSUlBW1ubUaNGsXfv3izLJCUlYWpqytSpU1m+fHmWZc6fP0/Pnj1ZsGABbdq0YefOnXTo0IFr167x3XffARAREUH9+vUZMGAAs2bNwsDAgNu3b6OlpZVlnZCW36xatUpaijddREQErVu3pkyZMvm88oKjp6f3WRNmgH79+jFo0CAmTZqEmlrBPrhXus9q37596du3L3369EEul1O1alVpW8avfv364enpydGjR/H09My13mfPnuVpXV1LS0uePXumdPmiTP4mFvnTCOmLZ/f/t/PZfYV98qcRyDOs+15YnsXJufX4f1+hT/43V27oE8V9tx7LeRaXt7l0vxXPEyH0xf++7mT40dyJVdwX+iKtvCAIacoZgn3xwv/KT0IcHx9P79690dXVxdzcnOXLl+Ps7KzQGmltbc2cOXPo2bMnurq6WFpasnr1aoX9AB07dkQmk+X4lNHZ2ZmOHTtiZ2dH+fLlGT16NFWrViUwMDDXWM3MzChZsqT0lVOjj7OzM48ePWLs2LHIZDKp8WnmzJk4ODgolF2xYoVCzG5ubnTo0IF58+ZhYWFBpUqVFO5XdvcB0lrT27dvj56eHgYGBnTr1o2nT5/meF26urqsXbuWQYMGZdtSbG1tjY+PD3379sXQMOsftI+PDy4uLowbNw47OzvmzJnD999/z6pVq6QyU6ZMoVWrVixevBhHR0fKly9Pu3btckz8g4ODpcQ0nUwmIzg4mNmzZyOTyZg5cyYBAQHIZDJevXollQsJCUEmk0njfjZv3oyRkRF//vkndnZ26Onp4eLiQlRUlMI5N23aROXKldHU1MTc3JwRI0ZI9wEyv9c+/rmmpqYye/ZsSpUqhaamJg4ODhw/flza//DhQ2QyGfv27aNx48bo6OhQrVo1Lly4IJV59OgRbdu2pVixYujq6lK5cmWOHj0q7W/evDmxsbFKjVfKK6VT382bN0vfnzlzhn79+jFq1KhPDkBTU5PEROX/k799+/bbmWf1r+NwYVfW+3ZNzLytTg+o26tQQ9p5IZWVf6Zmua/bTymZto1qocIYF9VCjako2n0X1vyV9b4+f2beNqwqDHco1JAEQSgAHh4eBAUFcejQIUqUKMH06dO5du1apoRuyZIlTJ48mVmzZvHnn38yevRobGxsaN68OVeuXMHMzAxfX19cXFxQVVXub6RcLufUqVOEh4ezaNGiXMs7ODiQlJTEd999x8yZM6lXr162Zfft20e1atUYPHgwgwYNUiqejPz9/TEwMMDPz09he073ITU1VUpU0x+xDx8+nO7duxMQEJDnGPLqwoULeHh4KGxr0aKF1KUgNTWVI0eOMH78eFq0aMH169cpW7YskyZNyrH7xrlz57CxsVGYqSgqKopmzZrh4uKCl5cXenp6XL16Vak4ExMTWbp0Kdu2bUNFRYUff/wRLy8vduzYAcDatWvx8PBg4cKFtGzZkri4OIKCggCUfq/5+PiwbNkyfv75ZxwdHdm0aRPt2rXj9u3bVKxYUSo3ZcoUli5dSsWKFZkyZQo9e/bk3r17qKmpMXz4cJKTkzl79iy6urqEhoYqtN5qaGjg4ODAuXPnaNq0qVLXrqx8tdM+ePCgwAIoXbo0165dU7r89evXi+zjnDyr6gLlaylfXrdY4cXy/3rVUaFZZeUniTAzyL3Mt6ibDTRW/oEAptqFF4sgCAUjPj6eLVu2sHPnTumfra+vr8LS3+nq1avHxIlpjQo2NjYEBQWxfPlymjdvjqmpKQBGRkY59iFNFxcXh6WlJUlJSaiqqrJmzRqaN2+ebXlzc3PWrVtHjRo1SEpKYsOGDTg7O3Pp0iW+//77LI8xNjZGVVUVfX19pWL6mK6uLhs2bMj0+D+n++Dv78/Nmzd58OCB9AR169atVK5cmStXrlCzZs08x5EX0dHRlChRQmFbiRIliI6OBtKe7L5584aFCxcyd+5cFi1axPHjx+nUqROnT5+mUaNGWdb76NGjTO+JkiVLoqamhp6eXp7v7/v371m3bh3ly5cHYMSIEQpdDObOnYunpyejR4+WtqXfO2Xfa0uXLmXChAn06NEDgEWLFnH69GlWrFih0Bru5eUltRjPmjWLypUrc+/ePWxtbYmMjKRz585UqVIFSFus6WMWFhY8evQoT9evjHwlq/Hx8Tx//pzSpUsrjOD/7bffOHToEFpaWgwfPjzbX5qMGjduzNq1a7lx4wbVqlXLseyNGzc4e/as1Pz9tZPpGYOe8ZcOQ4GZoQyzz9CX7GtnqpP2JQjCt+P+/fu8f/8eJycnaZuhoaHCY+90derUyfQ6qwE+6SIjI7G3t5deT548mcmTJwNpc4qHhITw5s0b/P398fDwoFy5cjg7O2dZV6VKlRRiqlu3LhERESxfvpxt27axY8cOhgwZIu0/duwYDRo0yPHac1OlSpUs+6nmdB/CwsIoXbq0Qlc/e3t7jIyMCAsLo2bNmlSuXFlKbho0aMCxY8c+Kc68SE1Ne4rYvn17xo4dC6S1Vp8/f55169Zlm6y+ffs2xz6teaWjoyMlqpD2YSS9u+OzZ8/4999/P6ml8vXr1/z777+ZWt7r1avHjRs3FLZVrVpVIY70GGxtbRk1ahRDhw7lxIkTNGvWjM6dOyuUB9DW1s7T03Jl5StZHT9+PNu3b+fp06dSsrp27VpGjBiBXJ7Wh3HXrl0EBwdja2ubY12jRo1i3bp1dO7cmSNHjmT5RwHg7t27dO7cGVVV1W8mWRUEQRD+GywsLBSmETI2/l9DhYqKChUqVADSkqWwsDAWLFiQbbKaFScnJ6mfa7t27ahV639P7SwtLbM9TkVFRfq/nS6rOc8LYzoigKNHj0rn09Yu2EdQJUuWzNQ/9unTp1ILpImJCWpqagofIgDs7Oxy7DNsYmLCzZs3cz1/eh/ijPc3q3v78bSdMplMOqag70luMsaS3q85PakfOHAgLVq04MiRI5w4cYIFCxawbNkyhVkHYmNjFRLvgpKvRQHOnDlDs2bN0NH5X9PSwoULsbS05OzZs+zevVvp2QAqVqzIwoULuX//Pg4ODvTt2xdfX1/8/Pzw8/Nj8+bN9OnTBwcHB+7fv8/ChQsV+lcIgiAIQkEoV64c6urqXLlyRdoWFxfH3bt3M5W9ePFiptd2dnbSa3V1dVJS/tfPX01NjQoVKkhfGZPVj6WmppKUlJSn2ENCQqSWMH19fYVzpSc8GhoaCjFB2mPk6OhohYQqL3Nz5nQf7OzsePz4MY8fP5b2h4aG8urVKylBLFOmjBRnTkl1ftSpUwd/f3+FbX5+flJrsIaGBjVr1iQ8PFyhzN27d3Mc0e/o6MidO3cyJfkfS39En3GwVF7nPdXX18fa2jrTdWT08XvtYwYGBlhYWEj9XNMFBQVlStRzU7p0adzd3dm3bx+enp6sX79eYf+tW7dwdHTMU53KyFfLalRUFC4uLtLrsLAwHj9+zOLFi6lfvz4Av//+O2fPnlWqPk9PT/T19aUW2/ROxenkcjkGBgb4+Pjkq2O4IAiCIORGX18fV1dXxo0bh7GxMWZmZsyYMQMVFRWplSldUFAQixcvpkOHDvj5+bFnzx6OHDki7U9PMOrVq4empibFimU95mDBggXUqFGD8uXLk5SUxNGjR9m2bRtr166VykyaNIknT55Iy5yvWLGCsmXLUrlyZd69e8eGDRs4deoUJ06cyPH6rK2tOXv2LD169EBTUxMTExOcnZ15/vw5ixcvpkuXLhw/fpxjx44pTImVk5zuQ7NmzahSpQq9e/dmxYoVfPjwgWHDhtGoUSNq1KiRY72hoaEkJycTGxtLfHy8lORlHOiWvu3Nmzc8f/6ckJAQNDQ0pARs9OjRNGrUiGXLltG6dWt27drF1atX+eWXX6Q6xo0bR/fu3WnYsCGNGzfm+PHjHD58OMcBYI0bN+bNmzfcvn1bmgIrKxUqVKB06dLMnDmTefPmcffuXZYtW5bjdWdl5syZuLu7Y2ZmRsuWLYmPjycoKEhq0VTmvTZu3DhmzJhB+fLlcXBwwNfXl5CQkEz5Vk7GjBlDy5YtsbGx4eXLl5w+fVrhA9rDhw958uQJzZo1y/M15iZfyWpSUpJC35UzZ84gk8n44YcfpG3lypXj0KFDStc5ePBgunfvzu+//05QUJDUAbpkyZLUq1ePLl26ZDs9hSAIgvD1uB9XdM/j7e2Nu7s7bdq0wcDAgPHjx/P48eNMfRTTJ6RPn5vT29tbYV7UZcuW4eHhwfr167G0tMx2ifKEhASGDRvGP//8g7a2Nra2tmzfvp3u3btLZaKiohQW4UlOTsbT05MnT56go6ND1apVOXnyZJYLBWQ0e/ZshgwZIiXGcrkcOzs71qxZw/z585kzZw6dO3fGy8tLIaHLSU73QSaTcfDgQUaOHEnDhg1RUVHBxcWFn376Kdd6W7VqpTBQJ721LmNrZsYWvODgYHbu3EmZMmWke123bl127tzJ1KlTmTx5MhUrVuTAgQMKCWbHjh1Zt24dCxYsYNSoUVSqVIm9e/dKDW9ZKV68OB07dmTHjh0sWLAg23Lq6ur8+uuvDB06lKpVq1KzZk3mzp1L165dc73+jFxdXXn37h3Lly/Hy8sLExMTunTpIu1X5r02atQo4uLi8PT05NmzZ9jb23Po0KE8PalOSUlh+PDh/PPPPxgYGODi4qIwx+2vv/7KDz/8UCjzzOYrWS1VqhR//fW/eXv++OMPjI2NFTravnjxIs8T0hoaGjJgwAAGDBiQn7AEQRCEIszExAQdbS0mBH7eFaxMTEyULq+vr6/Q2pSQkMCsWbMYPHiwQjkDAwN2796dbT1t27albdu2uZ5v7ty5zJ07N8cyGaeOhLRxI+PHj8+17o/Vrl0704AaAHd3d9zd3RW2pQ/+yur86bJLwDOysrLi4MGDeYpT2bpzewwP0LVr11yTw/79+9O/f39lQwPSpnhq3rw5U6ZMkXKdrB7x16tXTyFfAsW43dzccHNzU9jfoUOHTNc2ZMgQhUFzGWX1Xps5cyYzZ86UXquoqDBjxgxmzJiRZR3W1taZzmlkZKSwLacPGcnJyaxbt46dO3dmW+ZT5CtZbdmyJatXr8bLywstLS2OHz9O3759FcrcvXv325liShAEQfhkVlZWhN0JJyYm5rOd08TEJE//i65fv86dO3dwcnIiLi5OmkKoffv2hRWi8BWqWrUqixYt4sGDB9JUTv9lkZGRTJ48Oce5fj9FvpLVSZMmcfjwYby9vYG06Q0yzgn27NkzgoKCxKh9QRAEQYGVlVWRb8hYunQp4eHhaGhoUL16dc6dO5en1lnhv+HjFtH/svRBcoUlX8lqyZIluX37tjQ6rWHDhgqdsWNiYliyZEmu6xoLgiAIQlHi6OhIcHBwjmWUeUQtCELByVeyCmlzf7Vp0ybLffb29nmeDkEQBEEQBEEQPpbvZBXSOtSePHmSO3fukJCQwLRp0wB49+4dr1+/xsTERJoUVxAEQRAEQRDyKt+Z5KFDh7CysqJt27Z4eXkpjDr766+/MDc3Z9euXQURoyAIgiAIgvAfla9kNSgoiC5duqCpqYmPjw+9evVS2O/k5ESFChXYu3dvgQQpCIIgCIIg/DflqxvAnDlzMDIyIjg4GBMTE168eJGpTI0aNbh06VKO9WSc5DivivpoUkEQBEEQBOHT5StZvXTpEl26dMlxKo/SpUvnOhGwtbV1piXslCGTyfjw4UOejxMEQRAEQRC+LvlebjW3dYNfvXqV6+Cqvn37ZkpW79+/z7lz5zAyMsLBwYESJUrw9OlTQkJCePXqFQ0aNKBcuXL5CVsQBEH4wiIjI4v0ogCC8qytrRkzZgxjxoz50qF8dsnJydjb27N161bq1q1bqOcKCAigcePGvHz5EiMjo0I9V37Url2bcePG0blz50I7R76S1XLlynHlypUcy1y4cAFbW9scy3y8hNvt27epV68ekydPZtKkSejq6kr7EhISmDdvHmvXrmXt2rX5CVsQBEH4giIjI7GztSPxbeJnO6eOtg5hd8I+e8Iqk8nYv38/HTp0yLHcvn37mD9/Pvfu3eP9+/dUrFgRT09P+vTpk+0x6cnLx6KioihZsmS2x30tyeW7d+9wd3cnODiYsLAw2rRpw4EDBxTKREVF4enpydWrV7l37x6jRo1ixYoVmeras2cP06ZN4+HDh1SsWJFFixbRqlUrhTJhYWFMmDCBM2fO8OHDB+zt7dm7d2+O75l169ZRtmzZQk9UAerWrUtUVBSGhoa5li3MxHbz5s2MGTOGV69eKWyfOnUqY8eOpWPHjoU2A1S+ktXOnTszd+5cfH196devX6b9S5cu5datWyxevDhP9Y4fPx4nJ6cs10nW1dVl/vz5XLlyhQkTJnD48OH8hC4IgiB8ITExMSS+TWRO20mULV74yeODF5FMO7yAmJiYItu6amxszJQpU7C1tUVDQ4M//viDfv36YWZmluvCOuHh4QpPOc3MzAo7XCCtVVFDQ6PQ6k9JSUFbW5tRo0ZlO1A7KSkJU1NTpk6dyvLly7Msc/78eXr27MmCBQto06YNO3fupEOHDly7do3vvvsOgIiICOrXr8+AAQOYNWsWBgYG3L59Gy0trWzjk8vlrFq1SmHlzsKkoaGR44eQL61ly5YMHDiQY8eO0bp160I5R75S4HHjxmFnZ8fAgQNp3ry5tJLV+PHjadCgARMmTMDBwSHPy60GBQXh5OSUYxknJyfOnTuXn7AFQRCEIqBscStsS1Ys9K/8JMTx8fH07t0bXV1dzM3NWb58Oc7OzgqtkdbW1syZM4eePXuiq6uLpaUlq1evVtgP0LFjR2QymfQ6K87OznTs2BE7OzvKly/P6NGjqVq1KoGBgbnGamZmRsmSJaWvnFq1nJ2defToEWPHjkUmk0ld8GbOnImDg4NC2RUrVijE7ObmRocOHZg3bx4WFhZUqlRJ4X5ldx8grTW9ffv26OnpYWBgQLdu3Xj69GmO16Wrq8vatWsZNGhQtkmatbU1Pj4+9O3bN9sWRx8fH1xcXKScZc6cOXz//fesWrVKKjNlyhRatWrF4sWLcXR0pHz58rRr1y7HxD84OJiIiIhMidmECROwsbFBR0eHcuXKMW3aNN6/fy/tv3HjBo0bN0ZfXx8DAwOqV6/O1atXAXj06BFt27alWLFi6OrqUrlyZY4ePQqktZbKZDKpRTO7sg8fPpRa3IsVK4ZMJpOWhD1+/Dj169fHyMiI4sWL06ZNGyIiIqTYHj58iEwmY9++fTRu3BgdHR2qVavGhQsXpBj69etHXFyc9P5Jn7JUVVWVVq1aFep0pflKVvX09Dh37hw9evQgICCAwMBA5HI5S5cu5fz583Tr1o2TJ0+iqamZp3pTU1O5d+9ejmX+/vtv5HJ5fsIWBEEQhBx5eHgQFBTEoUOH8PPz49y5c1y7di1TuSVLllCtWjWuX7/OxIkTGT16NH5+fgBSNzlfX1+ioqJy7TaXTi6X4+/vT3h4OA0bNsy1vIODA+bm5jRv3pygoKAcy+7bt49SpUoxe/ZsoqKiiIqKUiqmdOlx+fn58ccff0jbc7oPqamptG/fntjYWM6cOYOfnx/379+ne/fueTp3fl24cIFmzZopbGvRooWUgKWmpnLkyBFsbGxo0aIFZmZm1KpVK1OXg4+dO3cOGxsb9PX1Fbbr6+uzefNmQkND8fHxYf369Qqtvr1796ZUqVJcuXKF4OBgJk6ciLq6OgDDhw8nKSmJs2fPcvPmTRYtWoSenl6W58+ubOnSpaWW6PDwcKKiovDx8QHSulJ6eHhw9epV/P39UVFRoWPHjqSmpirUPWXKFLy8vAgJCcHGxoaePXvy4cMH6taty4oVKzAwMJDeP15eXtJxhd2QmO8VrIoVK8aOHTtYuXIlV65cITY2FgMDA2rWrEmJEiXyVWfDhg3Zu3cvu3btokePHpn2//rrr+zbt4+WLVvmN2xBEARByFJ8fDxbtmxh586dNG3aFEhLOC0sLDKVrVevHhMnTgTAxsaGoKAgli9fTvPmzTE1NQXAyMhIqce3cXFxWFpakpSUhKqqKmvWrKF58+bZljc3N2fdunXUqFGDpKQkNmzYgLOzM5cuXeL777/P8hhjY2NUVVXR19fP1yNlXV1dNmzYkOnxf073wd/fn5s3b/LgwQNKly4NwNatW6lcuTJXrlyhZs2aeY4jL6KjozPlIyVKlCA6OhqAZ8+e8ebNGxYuXMjcuXNZtGgRx48fp1OnTpw+fZpGjRplWe+jR4+yfE9MnTpV+t7a2hovLy927drF+PHjgbRW5nHjxknjeSpWrCiVj4yMpHPnzlSpUgUgx4HkOZU1NjYG0lrdM/ZZ/Xjw06ZNmzA1NSU0NFTqEgHg5eUltRjPmjWLypUrc+/ePWxtbTE0NEQmk2X5/rGwsODx48ekpqYWSr/VT66xePHiuLi40KtXL9q0aZPvRBVg8eLF6Ojo0Lt3bxwdHRk5ciRz5sxh5MiRODo68uOPP6Knp8eiRYs+NWxBEARBUHD//n3ev3+v0B3N0NBQ4bF3ujp16mR6HRYWlm3dkZGR6OnpSV/z58+X9unr6xMSEsKVK1eYN28eHh4eBAQEZFtXpUqVGDJkCNWrV6du3bps2rSJunXrSq14O3bsUDhXQbR4ValSJct+qjndh7CwMEqXLi0lqgD29vYYGRlJZSpXrizF+bkbotJbFdu3b8/YsWNxcHBg4sSJtGnThnXr1mV73Nu3b7Ps0/rbb79Rr149SpYsiZ6eHlOnTlWYT97Dw4OBAwfSrFkzFi5cqPAYftSoUcydO5d69eoxY8YM/vrrr2zPn5ey6f7++2969uxJuXLlMDAwkLp5fDzffdWqVaXvzc3NgbSkPjfa2tqkpqaSlJSUa9n8KJxhW/lkb29PUFAQDRo04MaNG6xevZoZM2awevVqbty4QYMGDQgKCsLe3v5LhyoIgiAISrOwsCAkJET6cnd3l/apqKhQoUIFHBwc8PT0pEuXLixYsCBP9Ts5OUnd6Nq1a6dwrho1amR7nIqKSqaudRn7WabLODtPQTp69KgU54YNGwq07pIlS2bqH/v06VOpZdDExAQ1NbVMOYWdnV2OixaZmJjw8uVLhW0XLlygd+/etGrVij/++IPr168zZcoUkpOTpTIzZ87k9u3btG7dmlOnTmFvb8/+/fsBGDhwIPfv36dPnz7cvHmTGjVq8NNPP2V5/ryUTde2bVtiY2NZv349ly5dkhZtyhgfIHVLAKR+zR93FchKbGwsurq6aGtr51o2P/LVDaBJkyZKlZPJZNLgK2V99913BAQE8PjxY27cuEFcXByGhoZUq1ZN4dOZIAiCIBSkcuXKoa6uzpUrV6TZA+Li4rh7926mPqQXL17M9NrOzk56ra6uTkpKivRaTU2NChUqKBVHflqoQkJCpJYwfX39TP0pIW1UecaYAExNTYmOjkYul0vJSUhIiNLnzek+2NnZ8fjxYx4/fiz9/w4NDeXVq1dSglimTBmlz5VXderUwd/fX2FwnJ+fn9QarKGhQc2aNQkPD1c47u7duznG5ejoyNq1axXu2fnz5ylTpgxTpkyRyj169CjTsTY2NtjY2DB27Fh69uyJr68vHTt2BNIWU3J3d8fd3Z1Jkyaxfv16Ro4cmWUM2ZVNb/3O+HN+8eIF4eHhrF+/ngYNGgAoNYDvY1m9f9LdunULR0fHPNeprHwlqzk9noC0JDXjDzE/Pn50IAiCIHwbHrzI/1LbhXkefX19XF1dGTduHMbGxpiZmTFjxgxUVFQy/T8LCgpi8eLFdOjQAT8/P/bs2cORI0ek/dbW1vj7+1OvXj00NTUpVqxYludcsGABNWrUoHz58iQlJXH06FG2bdumMJ/4pEmTePLkCVu3bgXSRuuXLVuWypUr8+7dOzZs2MCpU6c4ceJEjtdnbW3N2bNn6dGjB5qampiYmODs7Mzz589ZvHgxXbp04fjx4xw7dizXhX+UuQ/NmjWjSpUq9O7dmxUrVvDhwweGDRtGo0aNcmzthbSkNjk5mdjYWOLj46UEOuPMBenb3rx5w/PnzwkJCUFDQ0NKhEePHk2jRo1YtmwZrVu3ZteuXVy9epVffvlFqmPcuHF0796dhg0b0rhxY44fP87hw4dzzHMaN27MmzdvuH37ttTfs2LFikRGRrJr1y5q1qzJkSNHpFZTSOs6MG7cOLp06ULZsmX5559/uHLlitSXdMyYMbRs2RIbGxtevnzJ6dOnFT78ZJRT2TJlyiCTyfjjjz9o1aoV2traFCtWjOLFi/PLL79gbm5OZGSk1M84L6ytrXnz5g3+/v5Uq1YNHR0ddHR0gLRBZz/88EOe61RWvpLV7JqEX79+zbVr15g8eTKlSpXi119/zVdQycnJnDx5kjt37pCQkMC0adOAtImCX79+jYmJSaFNPCsIgiAUDhMTE3S0dZh2OG+PuD+FjrZOjkuDf8zb2xt3d3fatGmDgYEB48eP5/Hjx5n6KKZPSJ8+N6e3t7fCvKjLli3Dw8OD9evXY2lpycOHD7M8X0JCAsOGDeOff/5BW1sbW1tbtm/frjBiPioqSuGxdHJyMp6enjx58gQdHR2qVq3KyZMns1woIKPZs2czZMgQKTGWy+XY2dmxZs0a5s+fz5w5c+jcuTNeXl4KCV1OcroPMpmMgwcPMnLkSBo2bIiKigouLi65PrIGaNWqlULLZHqrXcYuCxlb8oKDg9m5cydlypSR7nXdunXZuXMnU6dOZfLkyVSsWJEDBw4oDCjq2LEj69atY8GCBYwaNYpKlSqxd+9e6tevn21sxYsXp2PHjuzYsUPqrtGuXTvGjh3LiBEjSEpKonXr1kybNk1heqcXL17Qt29fnj59iomJCZ06dWLWrFlAWkvo8OHD+eeffzAwMMDFxSXb+WNzKmtpacmsWbOYOHEi/fr1o2/fvmzevJldu3YxatQovvvuOypVqsTKlStxdnbO9eeQUd26dXF3d6d79+68ePGCGTNmMHPmTJ48ecL58+fZvn17nurLC5m8EOaBio+Pp0qVKvTv35/p06fn6dhDhw4xePBgnj9/LrXOpjc7X758mTp16rBt2zZ69epV0GHn6PXr1xgaGhIXF6f0J06Aa9euUb16dfhxObIS5QslNvnTCNg+luDg4GxHgmYV0yEPNb4rnf/W75zceiynnfeHPMckm/EjsjL5H6SXHfmjp8hnbVc6nowx7WkN9sULPCRCX0DXI+T5Hm13W4ttyYq5ls+PO9F/8+PmoXmOaatXW2xLK58Q5CmmxzH0XXo4zzFdWnqM78tXKfB4rkXcpJZXy3y9lyZMmFAoT4weP37MokWL8hQT5P/v2qf42pZbTUhIwNLSkmXLljFgwADg61kJSig8f/31F82bNyciIiLbKab+KyZMmMDLly+V/oCTH/meuion+vr6tGzZEl9f3zwlq0FBQXTp0gVzc3N8fHy4ePGiQuusk5MTFSpUYO/evZ89WRUEQRA+nZWVVZFdTQrg+vXr3LlzBycnJ+Li4qRVitq3b/+FIxOKkqpVq7Jo0SIePHggTSH1X2VmZoaHh0ehnqNQklVIG2GY10mH58yZg5GREcHBwZiYmPDixYtMZWrUqCGNYhMEQRCEgrZ06VLCw8PR0NCgevXqnDt3Lk9dCYT/hvTVof7rPD09C/0chZKs3r9/nz179uS4xFxWLl26RJcuXXL8o1C6dGkOHjz4iREKgiAIQmaOjo4EBwfnWCa7/qeCIBSOfCWr/fv3z3L7hw8fePLkCYGBgbx//156fKKspKSkXPtNvXr1SgyuEgRBEARB+I/IV7K6efPmHPdXqlQJT09PBg4cmKd6y5Url+sayhcuXJCWKhMEQRAEQRC+bflKVh88eJDldhUVFYyMjLKcjFgZnTt3Zu7cufj6+tKvX79M+5cuXcqtW7dYvHhxvuoXBEEQBEEQvi75SlYLa8WJcePGsXfvXgYOHMjOnTulFTzGjx/PhQsXOH/+PA4ODowYMaJQzi8IgiAIgiAULZ88wOrly5ekpqZSvPinT0Spp6fHuXPnGDFiBLt375bmV126dCkymYxu3bqxZs0aNDU1P/lcgiAIgiAIQtGXr2R19+7drF+/ngsXLvD27VsANDU1sbW1xdXVFTc3NwwNDfMVULFixdixYwcrV67kypUrxMbGYmBgQM2aNSlRouAnixcEQRAEQRCKrjwlq3FxcXTt2hV/f3/kcjlqamqYmZkB8OLFC0JCQrhx4wYrV67k4MGD0pJmb9684fz587muG9ukSRPq1avHnDlzKF68OC4uLvm8LEEQBKEo+tpWsBLyr0+fPtjZ2TF58mQAEhMT6dOnD35+fsTHx/Py5UuMjIy+SGwBAQE0btz4s8WQnJyMjY0Nv//+OzVq1Cj0831rlE5W5XI57du35+zZs9SvX58pU6bQqFEjab3kd+/eERAQwIIFCzh37hzOzs7cuXMHmUyGi4sLbdu2zTVZvXTpErVr1/60KxIEQRCKpMjISOxsbUn8/ydyn4OOtjZhd+589oRVJpOxf/9+OnTooPQxu3btomfPnrRv354DBw7kWPbdu3d4enqya9cukpKSaNGiBWvWrMn0BHLz5s14e3tz9+5dDAwM6Nq1K6tXr5bqcHd3Jzg4mLCwMNq0aZPpvIGBgUyYMIE7d+6QmJhImTJlGDJkCGPHjs0xvhs3bnD06FHWrl0rbduyZQvnzp3j/PnzmJiY5PsJbF45Ozvj4ODAihUrpG1169YlKirqs8WgoaGBl5cXEyZMwN/f/7Oc81uidLK6fft2zp49y6BBg/j5558z7dfS0sLFxQUXFxfc3d355ZdfGDBgABEREYSGhiq1hrKtrS2PHj3K0wUIgiAIX4eYmBgS375ldp+GWJco/CTh4dM4pm87S0xMTJFvXX348CFeXl40aNBAqfJjx47lyJEj7NmzB0NDQ0aMGEGnTp0ICgqSynh7e7Ns2TKWLFlCrVq1SEhIUFjQICUlBW1tbUaNGsXevXuzPI+uri4jRoygatWq6OrqEhgYyJAhQ9DV1WXw4MHZxvfTTz/RtWtX9PT0pG0RERHY2dlJT12/JA0NDUqWLPlZz9m7d288PT25ffs2lStX/qzn/topPbv+9u3bsbS05Keffsq17MqVK7G0tOSPP/4gIiKCbdu20bt371yPGzlyJAcPHiQ0NFTZsARBEISvjHUJQ2xLmxT6V34S4vj4eHr37o2uri7m5uYsX74cZ2dnhQYXa2tr5syZQ8+ePdHV1cXS0lJqrUzfD9CxY0dkMlmuqzmmpKTQu3dvZs2aRbly5XKNMS4ujo0bN+Lt7U2TJk2oXr06vr6+nD9/nosXLwJpg5+nTp3K1q1b6dWrF+XLl6dq1aq0a9dOqkdXV5e1a9cyaNCgbBM3R0dHevbsSeXKlbG2tubHH3+kRYsWnDt3Lsfr+f3332nbtq20zdnZmWXLlnH27FlkMhnOzs5AWgv0x625RkZG0nzuDx8+RCaTsW/fPho3boyOjg7VqlXjwoULCscEBQXh7OyMjo4OxYoVo0WLFrx8+RI3NzfOnDmDj48PMpkMmUzGw4cPCQgIQCaT8erVK6mOvXv3UrlyZTQ1NbG2tmbZsmUK57C2tmb+/Pn0798ffX19rKys+OWXX6T9ycnJjBgxAnNzc7S0tChTpgwLFiyQ9hcrVox69eqxa9eubO+dkDWlk9WQkBBatWqFhoZGrmU1NDRo1aoVAKdOnVIqUYW0RQGcnZ2pXbs248aNY/fu3Zw5c4azZ89m+hIEQRCEgubh4UFQUBCHDh3Cz8+Pc+fOce3atUzllixZQrVq1bh+/ToTJ05k9OjR+Pn5AUiL2/j6+hIVFZXrYjezZ8/GzMyMAQMGKBVjcHAw79+/p1mzZtI2W1tbrKyspCTOz8+P1NRUnjx5gp2dHaVKlaJbt248fvxYqXNk5/r165w/f55GjRplW+avv/4iLi5OoW/mvn37GDRoEHXq1CEqKop9+/bl6bxTpkzBy8uLkJAQbGxs6NmzJx8+fADS8pOmTZtib2/PhQsXCAwMpG3btqSkpODj40OdOnUYNGgQUVFRREVFUbp06Uz1BwcH061bN3r06MHNmzeZOXMm06ZNy7QI0rJly6hRowbXr19n2LBhDB06lPDwcCCtoe7QoUPs3r2b8PBwduzYkemDipOTU46JvpA1pbsBvHr1ClNTU6UrNjU1RVVVlTp16ih9jLOzMzKZDLlczrJly5DJZNmWTZ/WShAEQRAKQnx8PFu2bGHnzp00bdoUSEs4LSwsMpWtV68eEydOBMDGxoagoCCWL19O8+bNpf+VRkZGuT5qDgwMZOPGjYSEhCgdZ3R0NBoaGpkGBpUoUYLo6GgA7t+/T2pqKvPnz8fHxwdDQ0OmTp1K8+bN+euvv5RqeMqoVKlSPH/+nA8fPjBz5swcV6h89OgRqqqq0gBsAGNjY3R0dPL9+N3Ly4vWrVsDMGvWLCpXrsy9e/ewtbVl8eLF1KhRgzVr1kjlMz5m19DQQEdHJ8fzent707RpU6ZNmwak/UxDQ0NZsmQJbm5uUrlWrVoxbNgwACZMmMDy5cs5ffo0lSpVIjIykooVK1K/fn1kMlmWc9JbWFiI7o75oHSyWrx48Tx9Inv8+DEmJiZ5Cmb69Ok5JqiCIAiCUFju37/P+/fvcXJykrYZGhpSqVKlTGU/boipU6eOwgCej0VGRmJvby+9njx5MiNHjqRPnz6sX78+2/+X8+fPZ/78+dJrZbvJpaam8v79e1auXCkNbv71118pWbIkp0+fpkWLFkrVk+7cuXO8efOGixcvMnHiRCpUqEDPnj2zLPv27Vs0NTUL9P951apVpe/Nzc0BePbsGba2toSEhNC1a9dPqj8sLIz27dsrbKtXrx4rVqwgJSUFVVXVTHHIZDJKlizJs2fPAHBzc6N58+ZUqlQJFxcX2rRpk2lguba2NomJiZ8U63+R0slqjRo1OHLkCK9fv8bAwCDHsq9fv+bIkSPUq1cvT8HMnDkzT+UFQRAE4WtgYWGh0HpqbGxMREQEDx8+VOjbmZqaCoCamhrh4eG4u7vTrVs3hXpKlixJcnIyr169Umhdffr0qdR6mJ7QZUyQTU1NMTExITIyMs/xly1bFoAqVarw9OlTZs6cmW2yamJiQmJiIsnJybm24KY/Tc3o/fv3mcqpq6srHAP/u1fa2trKX8gnyhhHeizpcXz//fc8ePCAY8eOcfLkSbp160azZs34/fffpfKxsbF5ekotpFG6z2q/fv2IjY2lT58+0jKoWUlOTqZPnz68fPmSfv36FUiQgiAIglDYypUrh7q6ukIf07i4OO7evZupbPpApoyv7ezspNfq6uoK3dXU1NSoUKGC9GVsbIytrS03b94kJCRE+mrXrh2NGzcmJCSE0qVLY2xsrHCcmpoa1atXR11dXWEKpPDwcCIjI6UW3/TGovT+lJCWKMXExHzykumpqak55gEODg6Acq3ApqamREVFSa///vvvPLc8Vq1aNcfpoDQ0NHLtOmhnZ6cwkwKkDdqysbGRWlWVYWBgQPfu3Vm/fj2//fYbe/fuJTY2Vtp/69YtHB0dla5PSKN0y2rHjh1p27Ythw8fxsHBAU9PT5o0aSJ1VH78+DH+/v7SfG5t2rTJ0/xyGV2/fp1ff/1Vmtft5MmTQFo/mEuXLtGsWTOMjY3zVbcgCILwZT18Glckz6Ovr4+rqyvjxo3D2NgYMzMzZsyYgYqKSqZH2kFBQSxevJgOHTrg5+fHnj17OHLkiLTf2toaf39/6tWrh6amJsWKFct0Pi0trUzTOKW3lOY0vZOhoSEDBgzAw8MDY2NjDAwMGDlyJHXq1JHmKrexsaF9+/aMHj2aX375BQMDAyZNmoStrS2NGzeW6goNDSU5OZnY2Fji4+Ol1t/0hHP16tVYWVlha2sLwNmzZ1m6dCmjRo3KNj5TU1O+//57AgMDpXqy06RJE1atWkWdOnVISUlhwoQJmVovczNp0iSqVKnCsGHDcHd3R0NDg9OnT9O1a1dMTEywtrbm0qVLPHz4ED09vSzzB09PT2rWrMmcOXPo3r07Fy5cYNWqVQr9YHPj7e2Nubk5jo6OqKiosGfPHkqWLKnQ+n3u3DnmzJmTp+sT8riC1a+//oqrqyt79+5lyJAhWZaRy+V06dIl0wg6ZY0fP55ly5ZJjwUy/oGQy+X06tWLZcuWMXr06HzVLwiCIHwZJiYm6GhrM33b55vRRUdbO0/jJ7y9vXF3d6dNmzYYGBgwfvx4Hj9+LC2Ak87T05OrV68ya9YsDAwM8Pb2VugHumzZMjw8PFi/fj2WlpYK85sWhOXLl6OiokLnzp0VFgXIaOvWrYwdO5bWrVujoqJCo0aNOH78uEIy2KpVK4UBP+mtfun/g1NTU5k0aRIPHjxATU2N8uXLs2jRomxzgHQDBw5k69atjBgxIsdyy5Yto1+/fjRo0AALCwt8fHwIDg7O072wsbHhxIkTTJ48GScnJ7S1talVq5bUTcHLywtXV1fs7e15+/YtDx48yFTH999/z+7du5k+fTpz5szB3Nyc2bNnKwyuyo2+vj6LFy/m77//RlVVlZo1a3L06FFUVNIeYl+4cIG4uDi6dOmSp+sT8pis6ujosGfPHvz9/dm0aRMXLlyQRh6WLFmSunXr0r9/f5o0aZKvYHx9fVm6dClt27Zl3rx5/PrrryxcuFDab21tjZOTE4cOHRLJqiAIwlfGysqKsDt3ivRyq/r6+uzYsUN6nZCQwKxZszJNgG9gYMDu3buzradt27YKfVGVpWxDj5aWFqtXr1aY3/VjBgYGbNy4kY0bN2ZbJrckeuTIkYwcOVKpmDJyc3NjwYIFXLhwQeqakNUANAsLC/7880+FbRnnPrW2ts7Up9XIyCjTtkaNGmV6jJ/OxsYm07ysWdXbuXNnOnfunO01ZXWvMvZDHjRoEIMGDcr2+BUrVjBu3LjP2sf2W5GnZDVd06ZNpWk9CtKaNWuws7Nj7969qKmpZdkx29bWVuoWIAiCIHxdrKysivRqUtevX+fOnTs4OTkRFxfH7NmzATKNFBdypq2tzdatWz/rB5OiLDk5mSpVquS6TK2QtXwlq4UlNDSUQYMGoaaWfVglSpSQpokQBEEQhIK2dOlSwsPD0dDQoHr16pw7dy7PUzEKSKtUCWmDvKZOnfqlw/hqFalkVU1NjeTk5BzL/PvvvwprDQuCIAhCQXF0dMy1z2RB9z8VBCFnSk9d9TlUqVKFU6dOZTvFRPrMANWrV//MkQmCIAiCIAhfQpFKVvv378/du3dxd3fPNIfb69evcXNzIzo6OscOzIIgCIIgCMK3o0h1A+jfvz8nT55k48aN/Pbbb9LcZE5OToSFhZGQkICbm5uY9kEQBEEQBOE/oki1rALs3LmTn3/+mbJly/LkyRPkcjlXr17FysqKtWvXsmnTpi8doiAIgiAIgvCZFKmW1XTpc5W9ffuWly9fYmBgIAZVCYIgCIIg/AcVWLLq5+fHnTt3kMlk2NnZFcg8rNra2mLyXEEQBEEQhP+wT05W7927R6dOnbh165a0TSaTUbVqVfbv34+1tbXSdTVt2pQmTZrg7OxMrVq1cpxvVRAEQfj6REZGFukVrISvn5ubG69eveLAgQOf9bwNGzbE3d2dXr16ARAdHU2fPn04f/486urqCitzfW6bN29mzJgxny2GmJgY7O3tuXbtGqVKlfrk+j45Gxw8eDCqqqoEBgbi6OhIUlISR44cYejQobi7u3P8+HGl6woKCuL06dPIZDK0tbWpW7cujRs3pnHjxtSsWRNVVdVPDVcQBEH4QiIjI7GzsyMxMfGznVNHR4ewsLDPnrDKZDL2799Phw4dlD5m165d9OzZk/bt2+eaaP3yyy/s3LmTa9euER8fz8uXL6VByenmzZvHkSNHCAkJQUNDI8tEJTIykqFDh3L69Gn09PRwdXVlwYIFCo1FSUlJzJ49m+3btxMdHY25uTnTp0+nf//+Sl/b5+Tj45NpKdXCdujQIZ4+fUqPHj2kbcuXLycqKoqQkBAMDQ0/WyzW1taMGTOGMWPGSNu6d+9Oq1atPlsMJiYm9O3blxkzZuS43K+ylE5WM67vm1FgYCBHjhyhbt26QNqj+969e3Pp0iU2bNiQp2Di4uK4cOECp0+f5tSpU5w9e5aTJ08ik8nQ1dWlXr16NG7cGGdnZ5ycnPJUtyAIgvBlxcTEkJiYyJYxK7EtVbHQz3fnn79xXTGKmJiYIt+6+vDhQ7y8vGjQoIFS5RMTE3FxccHFxYVJkyZlWSY5OZmuXbtSp06dLBOGlJQUWrduTcmSJTl//jxRUVH07dsXdXV15s+fL5Xr1q0bT58+ZePGjVSoUIGoqChSU1Pzd6E5SE5OznKZ9bz6nIlhupUrV9KvXz9UVP43bj0iIoLq1atTsWLhv9dz8yW6Vfbr14/q1auzZMkSjI2NP6kupWcDaNCgASNHjuTNmzcK24sXL87Vq1cVtqWmphISEkLx4sXzFIympibOzs7MmjWLc+fO8fLlS06cOMGkSZOoUqUK/v7+TJo0SUqMBUEQhK+PbamKfF++SqF/5Schjo+Pp3fv3ujq6mJubs7y5ctxdnZWaKWytrZmzpw59OzZE11dXSwtLVm9erXCfoCOHTsik8ly7Q6XkpJC7969mTVrFuXKlVMqzjFjxjBx4kRq166dbZlZs2YxduxYqlSpkuX+EydOEBoayvbt23FwcKBly5bMmTOH1atXS6tJHj9+nDNnznD06FGaNWuGtbU1derUoV69ejnG5+zszIgRIxgxYgSGhoaYmJgwbdo0hRbP9PvYt29fDAwMGDx4MJDWCNagQQO0tbUpXbo0o0aNIiEhAYDJkydTq1atTOerVq0as2fPBtK6AWRs0U5NTWXBggWULVsWbW1tqlWrxu+//y7tr1GjBkuXLpVed+jQAXV1dSnf+eeff5DJZNy7dy/La33+/DmnTp2ibdu2Cte2d+9etm7dikwmw83NjYcPHyKTyQgJCZHKvXr1CplMRkBAAAABAQHIZDL8/f2pUaMGOjo61K1bl/DwcIVzHj58mJo1a6KlpYWJiQkdO3aU7vujR48YO3YsMpkMmUwGpHUD+Ljlfe3atZQvXx4NDQ0qVarEtm3bFPbLZDI2bNhAx44d0dHRoWLFihw6dEja//LlS3r37o2pqSna2tpUrFgRX19faX/lypWxsLBg//79Wd63vFA6WT169ChHjx7F3t6eI0eOSNtHjx7N1KlTcXFxYeLEidIvRmBgoMIvd35oa2tTqlQpLC0tMTc3R09PD7lcXiif6ARBEATBw8ODoKAgDh06hJ+fH+fOnePatWuZyi1ZsoRq1apx/fp1Jk6cyOjRo/Hz8wPgypUrAPj6+hIVFSW9zs7s2bMxMzNjwIABBX9BObhw4QJVqlShRIkS0rYWLVrw+vVrbt++DaQ93q5RowaLFy/G0tISGxsbvLy8ePv2ba71b9myBTU1NS5fvoyPjw/e3t6ZnrguXbpUuo/Tpk0jIiICFxcXOnfuzF9//cVvv/1GYGAgI0aMAKB3795cvnyZiIgIqY7bt2/z119/SX1FP7ZgwQK2bt3KunXruH37NmPHjuXHH3/kzJkzADRq1EhKFuVyOefOncPIyIjAwEAAzpw5g6WlJRUqVMiy/sDAQHR0dLCzs5O2XblyBRcXF7p160ZUVBQ+Pj653q+MpkyZwrJly7h69SpqamoKXS6OHDlCx44dadWqFdevX8ff31962rxv3z5KlSrF7NmziYqKIioqKsv69+/fz+jRo/H09OTWrVsMGTKEfv36cfr0aYVys2bNolu3bvz111+0atWK3r17ExsbC8C0adMIDQ3l2LFjhIWFsXbtWkxMTBSOd3Jy4ty5c3m69qwo3Q3ghx9+4NatW0yZMoUOHTrQuXNnfvrpJyZOnEiZMmVYuXIlv/zyCwB2dnbs2rWLbt265TmgiIgIqRtAQEAAT58+RS6XU758ebp06SL1YRUEQRCEghQfH8+WLVvYuXOnNKONr68vFhYWmcrWq1ePiRMnAmBjY0NQUBDLly+nefPmmJqaAmBkZETJkiVzPGdgYCAbN25UaG37XKKjoxUSVUB6HR0dDcD9+/cJDAxES0uL/fv3ExMTw7Bhw3jx4oVCK1pWSpcuzfLly5HJZFSqVImbN2+yfPlyhVUomzRpgqenp/R64MCB9O7dW2rsqlixIitXrqRRo0asXbuWypUrU61aNXbu3Mm0adMA2LFjB7Vq1coymUxKSmL+/PmcPHlS6spYrlw5AgMD+fnnn2nUqBHOzs5s3LiRlJQUbt26hYaGBt27dycgIAAXFxcCAgJo1KhRttf56NEjSpQoodAFwNTUFE1NTbS1taX3wMuXL3O8XxnNmzdPOufEiRNp3bo17969Q0tLi3nz5tGjRw9mzZolla9WrRoAxsbGqKqqoq+vn+N7b+nSpbi5uTFs2DAg7UPaxYsXWbp0qUKO5ebmRs+ePQGYP38+K1eu5PLly7i4uBAZGYmjoyM1atQAyPIJgoWFBdevX1f6urOTp0UBtLW18fb25vz584SFhWFnZ8fmzZvp2bMnFy5cIDY2ltjYWIKCgvKVqFpZWWFjY8OQIUM4f/48LVq0wNfXl0ePHvH333/zyy+/0LNnz1x/+QVBEAQhr+7fv8/79+8VxkQYGhpSqVKlTGU/HsNRp04dwsLCsq07MjISPT096Wv+/PnEx8fTp08f1q9fn6lFKt38+fMVjouMjMzn1eVPamoqMpmMHTt24OTkRKtWrfD29mbLli28ffuWc+fOKcS3Y8cO6djatWtLj6Eh7R79/fffpKSkSNvSE510N27cYPPmzQp1tmjRgtTUVB48eACkta7u3LkTSGsJ/fXXX+ndu3eW8d+7d4/ExESaN2+uUOfWrVul1tkGDRoQHx/P9evXOXPmjJTApre2njlzBmdn52zv0du3b9HS0lL+piqhatWq0vfm5uYAPHv2DICQkJBPnh40LCwsU1eOevXqZXoPZ4xDV1cXAwMDKY6hQ4eya9cuHBwcGD9+POfPn890Hm1t7QIZUJmv2QBq1qzJtWvXWLRoEcOGDWP79u2sX7+esmXLflIw//zzDwDNmjVj4MCBNGnSJNtfYEEQBEH4WlhYWCi0nhobGxMREcHDhw8V+jqmd3NTU1MjPDwcd3d3hcafrFp586tkyZJcvnxZYdvTp0+lfZCWKFlaWioMWrKzs0Mul/PPP/9Qo0YNhev6uKU2N7q6ugqv37x5w5AhQxg1alSmsumD5Hr27MmECRO4du0ab9++5fHjx3Tv3j3L+tP7nR45cgRLS0uFfZqamkBaC3i1atUICAjgwoULNG/enIYNG9K9e3fu3r3L33//nWPLqomJiVKtpuktrxn77b5//z7Lsurq6tL36Ql/+nvjcw6UyhhHeizpcbRs2ZJHjx5x9OhR/Pz8aNq0KcOHD1fo/xsbGys9afgU+V5uVVVVlcmTJxMSEsKHDx/47rvvWLJkySf1J/X29qZdu3ZcvXqVnj17UqJECapWrcro0aM5ePAgcXFx+a5bEARBEHJSrlw51NXVFfqYxsXFcffu3UxlL168mOl1xj6L6urqCi2IampqVKhQQfoyNjbG1taWmzdvEhISIn21a9eOxo0bExISQunSpTE2NlY4riDnH69Tpw43b96UWsogbYEfAwMD7O3tgbTWtn///VdhcPXdu3dRUVGhVKlSaGtrK8Snr68vlbt06VKme1SxYsUcp6H8/vvvCQ0NVagz/St9poBSpUrRqFEjduzYwY4dO2jevDlmZmZZ1mdvb4+mpiaRkZGZ6itdurRUrlGjRpw+fZqzZ8/i7OyMsbExdnZ2zJs3D3Nzc2xsbLKN2dHRkejo6FwT1vSkLWM/0vx0/6hatSr+/v7Z7tfQ0FB472XFzs6OoKAghW1BQUHSz11ZpqamuLq6sn37dlasWCF1B01369YtHB0d81RnVvL0rn/y5Ak7duwgMjISKysrevfujY2NDQEBAfzyyy9MmDCBXbt2sWHDhnwFlz4vmFwu59q1a5w+fZrTp0+zZcsWfvrpJ1RVValWrRpNmzZl0aJFea5fEARB+PLu/PN3kTyPvr4+rq6ujBs3DmNjY8zMzJgxYwYqKioKj7Mh7R/74sWL6dChA35+fuzZs0dh8LG1tTX+/v7Uq1cPTU1NihUrlul8WlpafPfddwrb0kdsf7z9Y9HR0URHR0sj1G/evIm+vj5WVlbSNEGRkZHExsYSGRlJSkqKlBhVqFABPT09fvjhB+zt7enTpw+LFy8mOjqaqVOnMnz4cKnVsVevXsyZM4d+/foxa9YsYmJiGDduHP3798+1hS8yMhIPDw+GDBnCtWvX+Omnn1i2bFmOx0yYMIHatWszYsQIBg4ciK6uLqGhofj5+bFq1SqpXO/evZkxYwbJycksX7482/r09fXx8vJi7NixpKamUr9+feLi4ggKCsLAwABXV1cgbRT9Tz/9hKmpKba2ttK2VatW0bVr1xxjdnR0xMTEhKCgINq0aZNtOW1tbWrXrs3ChQspW7Ysz549Y+rUqTnWnZUZM2bQtGlTypcvT48ePfjw4QNHjx5lwoQJQNp77+zZs/To0QNNTc0sn1CPGzeObt264ejoSLNmzTh8+DD79u3j5MmTSscxffp0qlevTuXKlUlKSuKPP/5Q+MCWmJhIcHCwwjRo+aV0snr+/HlcXFxITEzExMSEmJgY5s6dy4kTJ6hduzaDBw+mbdu2DB8+nFq1ajFmzBhmz56dr34cMpmM6tWrU716dby8vHj37h1r1qxh0aJFXLt2jevXr4tkVRAE4StjYmKCjo4OrisyP+ItLDo6OnnqTubt7Y27uztt2rTBwMCA8ePH8/jx40z/yzw9Pbl69SqzZs3CwMAAb29vWrRoIe1ftmwZHh4erF+/HktLSx4+fFhQlwTAunXrFAbYNGzYEEgbEObm5gakJRNbtmyRyqQ3Ip0+fRpnZ2dUVVX5448/GDp0KHXq1EFXVxdXV1dpCigAPT09/Pz8GDlyJDVq1KB48eJ069aNuXPn5hpj3759efv2LU5OTqiqqjJ69GhpeqrsVK1alTNnzjBlyhQaNGggDbD++DF/ly5dGDFiBKqqqrkuvDBnzhxMTU1ZsGAB9+/fx8jIiO+//57JkydLZRo0aEBqaqrC435nZ2d8fHxy7K8KaU+a+/Xrx44dO3JMVgE2bdrEgAEDqF69OpUqVWLx4sX88MMPOR7zMWdnZ/bs2cOcOXNYuHAhBgYG0s8f0maXGDJkCOXLlycpKSnLBRI6dOiAj48PS5cuZfTo0ZQtWxZfX99crzUjDQ0NJk2axMOHD9HW1qZBgwbs2rVL2n/w4EGsrKyUnjs4J0onq15eXpiamnL69GmsrKyIjIykcePGeHl5SdM7mJubs2/fPvbt28fIkSPZv38/f/+d90/QqampXL16VWpZDQoKIjExEblcjrq6OjVr1sxznYIgCMKXZWVlRVhYWJFeblVfX19hkFBCQgKzZs3KlGQZGBiwe/fubOtp27atQl9UZW3evFmpcjNnzmTmzJm51pVbfWXKlOHo0aM5lrG1tZWm5coLdXV1VqxYwdq1a7Pcn10CX7NmTU6cOJFj3UZGRrx79y7LfR9fs0wmY/To0YwePTrb+oyNjTN1Y+zQoYPSK2GNHTuWypUr8+jRI8qUKQOQ5SpkdnZ2mQYiZTyHs7NzpnM6ODhk2tapUyc6deqUZSy1a9fmxo0bCtvc3NykDzHphg4dytChQ7O9pqyuPeMqaFOnTs2xZdjn/9q786AorjwO4N/hHgYBFRQdDi+MN6AEpQyH4oFEo1EiGlaOBFcULwgSyQoGD6h4QPCIugaRRF2jm8S4aizBAAuoIREV44FGFwazgBdRVASXmf2Dmo4jh2CAGeX7qaKK7n7z+tfjCD9ev/69xERER0c3eLw5mpysKutwKf/TW1tbY+rUqdi2bVudtlOnToWHhwciIiKaFUx8fDzS09ORlZWFiooKKBQKaGtrY9iwYULJqjfeeAOGhobN6peIiDSDtbW1Rq8mdebMGVy+fBlOTk64d++eMMo4efJkNUdGmszCwgJJSUmQyWRCstqe3b59G1OnThXKXv1ZTU5WpVJpnacGc3Nz6zxdp2RiYlJvItuY8PBwaGlpwd7eXkhOXVxcVCZsExERtaZ169ahoKAAenp6GDZsGLKysliZhp7redMR2hMzM7NmD1g2psnJqnKS9IABA2Bvb49z587h0qVL2Lp1a4sFc+DAAbi6utZZEoyIiKgtODg44PTp0422aen5p68iZY1SopbQ5NJVs2fPxr59+2BtbY1z587BysoK+/bte+5k6eZ46623mKgSERERkaBZpau8vb3h7e3dWrGguLgYV69exYgRI4R5qXK5HGvXrsXBgwchFosRGhqKN998s9ViICIiIiLN0XLVhVtAVFQU/vWvfwlrEgO16+MuX75c2M7MzMSJEydYEYCIiIioHXjhFaxaQ05ODsaMGSMs76VQKLBp0yb069cPMpkMubm5kEgkWLt2rZojJSIiIqK2oFHJ6s2bN1VKPpw9exa3bt3CggULYGlpCUdHR0yZMkVlKTwiIiIienVpVLIql8tVivJmZGRAJBJh9OjRwj6pVKoyTYCIiIiIXl0aNWfV2tpapZbrgQMH0K1bN7z22mvCvtLSUlYMICJ6SclkMo1ewYpefgEBAfj999/rXUGqNbm6uiI4OBjvvvtuq56nsLAQPXv2xJkzZ2Bvb9+q53oRM2bMwOuvv44PPvigxfrUqGR12rRpWL16Nby9vWFgYIDs7GzMnz9fpc3FixfRq1cvNUVIREQvSiaToV+/fqisrGyzc4rFYly+fLnNE1aRSIRvv/22WYXi9+7di5kzZ2Ly5MnPTbT+/ve/Y8+ePcjLy0NFRQXKy8vrDOSsXr0ahw8fxtmzZ6Gnp6eyVKaSTCbD3LlzkZ6eDiMjI/j7+yMuLg46On+kB1VVVVixYgV27dqF0tJSdOvWDdHR0XjvvfeafG1tKTExscnLpLaUgwcPoqysDDNmzGj1c1lZWaGkpKRJC1W0ZmKbkZGBUaNG1fnsLVu2DK6urggKCoKJiUmLnEujktXw8HAcO3YM33zzDQBgyJAhKmsfFxUVITc3F0uXLlVThERE9KJu376NyspK+Pv7w8LCotXPV1paipSUFNy+fVvjR1cLCwsRHh4OFxeXJrV/9OgRPD094enpicjIyHrbVFdX45133oGzszOSkpLqHK+pqcGbb74JCwsLnDhxAiUlJfDz84Ouri5iY2OFdtOnT0dZWRmSkpLQp08flJSUqEzZaynV1dXQ09P70/20VILUHBs2bEBgYCC0tFp/dqW2tnab/P95UYMGDULv3r2xa9cuhISEtEifGjVn1djYGKdOnUJ+fj7y8/Nx+vRpdOzYUaXNN998g3nz5qkpQiIi+rMsLCxgZWXV6l8v8gu9oqICvr6+kEgk6NatGxISEuDu7o7FixcLbXr06IGVK1di5syZkEgkkEql2Lx5s8pxAHj77bchEomE7YbU1NTA19cXMTExTb5zuHjxYixduhQjRoxosE1MTAxCQ0MxePDgeo8fO3YMFy9exK5du2Bvb48JEyZg5cqV2Lx5M6qrqwEAR48eRWZmJo4cOYIxY8agR48ecHZ2xsiRIxuNz93dHfPnz8f8+fNhYmICMzMzREVFqYx4Kt9HPz8/GBsbC4sMZWdnw8XFBWKxGFZWVli4cCEePnwIAPjoo48wfPjwOuezs7PDihUrANROA3h6RFsulyMuLg49e/aEWCyGnZ0d/vnPfwrHHR0dsW7dOmF7ypQp0NXVxYMHDwAAN27cgEgkwq+//lrvtd66dQs//PADJk2apLI/Pj4egwcPhkQigZWVFebNmyf0CdQOwE2aNAkdO3aERCLBwIEDceTIEQBAeXk5fH19YW5uDrFYDFtbWyQnJwOo/cNGJBLh7Nmzz23bs2dPALUrs4lEIri7uwMAfvrpJ4wdOxZmZmYwMTGBm5sb8vLyVOIXiUT4/PPP8fbbb8PQ0BC2trY4ePCgEMOoUaMAAB07doRIJEJAQIDw2kmTJmHv3r31vl8vQqOSVaVBgwZh0KBB0NbWVtlvY2ODyZMnQyqVqikyIiJ6lYWFhSEnJwcHDx5EamoqsrKy6vwSB4C1a9fCzs4OZ86cwdKlS7Fo0SKkpqYCgFCxJjk5GSUlJc+tYLNixQp06dIF77//fstfUCNOnjyJwYMHo2vXrsK+8ePH4/79+7hw4QKA2tvbjo6OWLNmDaRSKfr27Yvw8PAmTeVISUmBjo4OcnNzkZiYiPj4eHz++ecqbdatWye8j1FRUbh27Ro8PT0xbdo05Ofn46uvvlKZEujr64vc3Fxcu3ZN6OPChQvIz89vcK5oXFwcvvjiC2zduhUXLlxAaGgo/vKXvyAzMxMA4ObmJiwPq1AokJWVBVNTU2RnZwOore8ulUrRp0+fevvPzs6GoaEh+vfvr7JfS0sLGzZswIULF5CSkoIffvgBERERwvGQkBBUVVXh3//+N86fP49PPvkERkZGAGrrzl+8eBHff/89Ll26hC1btjR427+xtsrngNLS0lBSUiLcua6oqIC/vz+ys7Nx6tQp2NrawsvLCxUVFSp9x8TEYPr06cjPz4eXlxd8fX1x9+5dWFlZ4euvvwYAFBQUoKSkBImJicLrnJyckJubi6qqqnpjbi6NmgZARESkLhUVFUhJScGePXvg4eEBoDbh7N69e522I0eOFKak9e3bFzk5OUhISMDYsWNhbm4OADA1NX3u6G52djaSkpKEUbK2VFpaqpKoAhC2lVV3rl+/juzsbBgYGODbb7/F7du3MW/ePNy5c0cYvWuIlZUVEhISIBKJ8Nprr+H8+fNISEjA7NmzhTajR49WeRAnKCgIvr6+wki2ra0tNmzYADc3N2zZsgUDBw6EnZ0d9uzZg6ioKADA7t27MXz48HqTyaqqKsTGxiItLQ3Ozs4AgF69eiE7Oxvbtm2Dm5sb3N3dkZSUhJqaGvzyyy/Q09ODj48PMjIy4OnpiYyMDLi5uTV4nUVFRejatWudKQDPjsavWrUKwcHB+OyzzwDUzheeNm2aMPL99Ki6TCaDg4MDHB0dhdc3pLG2ys9i586dVT6LT1dZAmrnQJuamiIzMxMTJ04U9gcEBGDmzJkAgNjYWGzYsAG5ubnw9PREp06dAABdunSpM1+6e/fuqK6uRmlpqUpJ0helcSOraWlp8PLygrm5OXR1daGtrV3n6+mJ30RERC3h+vXrePLkCZycnIR9JiYmKhVplJSJz9Pbly5darBvmUwGIyMj4Ss2NhYVFRWYNWsWtm/f3uCoWWxsrMrrZDLZC17di5HL5RCJRNi9ezecnJzg5eWF+Ph4pKSkoLKyEllZWSrx7d69W3jtiBEjIBKJhG1nZ2dcvXoVNTU1wj5lgqV07tw57Ny5U6XP8ePHQy6X4z//+Q+A2tHVPXv2AKgdCf3HP/4BX1/feuP/9ddf8ejRI4wdO1alzy+++EIYnXVxcUFFRQXOnDmDzMxMIYFVjrZmZmYKt8/rU1lZCQMDgzr709LS4OHhAalUig4dOmDWrFm4c+cOHj16BABYuHAhVq1ahZEjR2L58uXIz88XXjt37lzs3bsX9vb2iIiIwIkTJxo8f3PaKpWVlWH27NmwtbWFiYkJjI2N8eDBgzqfryFDhgjfSyQSGBsb4+bNm8/tXywWA4BwrX+WRmV9X3/9NXx8fCCXy2FjY4N+/foxMSUiopde9+7dVUZPO3XqhGvXrqGwsFBlrqPywSUdHR0UFBQgODgY06dPV+mnpVhYWKiUiwRqkxjlMQDo1q0bpFKpykNL/fv3h0KhwI0bN+Do6KhyXc+O1D6PRCJR2X7w4AHmzJmDhQsX1mmrfEhu5syZ+PDDD5GXl4fKykoUFxfDx8en3v6Vc0QPHz5cZwqhvr4+gNoRcDs7O2RkZODkyZMYO3YsXF1d4ePjgytXruDq1auNjqyamZmhvLxcZV9hYSEmTpyIuXPnYvXq1ejUqROys7Px/vvvo7q6GoaGhggKCsL48eNx+PBhHDt2DHFxcVi/fj0WLFiACRMmoKioCEeOHEFqaio8PDwQEhKiMrdWqTltlfz9/XHnzh0kJibCxsYG+vr6cHZ2FuYqKylXFFUSiURNerju7t27AP4Y2f2zNCoTXLFiBcRiMb777rs6Q9REREStqVevXtDV1cVPP/0kJEb37t3DlStX4OrqqtL21KlTdbafnrOoq6urMoKoo6NT5za1oaEhzp8/r7Jv2bJlqKioQGJiIqysrKCnpyfcbm1pzs7OWL16NW7evIkuXboAAFJTU2FsbIwBAwYAqJ3usH//fjx48ECYT3nlyhVoaWnB0tISYrG4wbmcP/74o8q2cm7ks8+jPG3o0KG4ePFig30CgKWlJdzc3LB7925UVlZi7NixQvzPGjBgAPT19SGTyRpNON3c3JCeno7c3Fwhuezfvz9Wr16Nbt26oW/fvg2+1sHBAaWlpSgvLxceCj99+jTkcjnWr18vTA/Yt29fnddaWVkhODgYwcHBiIyMxPbt27FgwQIAtYmev78//P394eLigiVLljSYgDbUVlld4enPIlC7vP1nn30GLy8vAEBxcXGz6x831DcA/PLLL7C0tGxSea2m0KhktaCgALNmzWKiSkT0CmurVQibe54OHTrA398fS5YsQadOndClSxcsX74cWlpaKrezgdpf9mvWrMGUKVOQmpqK/fv34/Dhw8LxHj164Pjx4xg5ciT09fXrVLYBAAMDAwwaNEhln3Lu37P767u20tJS4Qn18+fPo0OHDrC2thaSW5lMhrt370Imk6GmpkYYAe3Tpw+MjIwwbtw4DBgwALNmzcKaNWtQWlqKZcuWISQkRBh1fPfdd7Fy5UoEBgYiJiYGt2/fxpIlS/Dee+8Jt3obIpPJEBYWhjlz5iAvLw8bN27E+vXrG33Nhx9+iBEjRmD+/PkICgqCRCLBxYsXkZqaik2bNgntfH19sXz5clRXVyMhIaHB/jp06IDw8HCEhoZCLpfjjTfewL1795CTkwNjY2P4+/sDqK1esHHjRpibm6Nfv37Cvk2bNuGdd95pNGYHBweYmZkhJydHmO/Zp08fPHnyBBs3bsSkSZOQk5ODrVu3qrxu8eLFmDBhAvr27Yvy8nKkp6cLf/BER0dj2LBhGDhwIKqqqnDo0KE6D3ApNda2S5cuEIvFOHr0KCwtLWFgYAATExPY2triyy+/hKOjI+7fv48lS5Y899/zWTY2NhCJRDh06BC8vLwgFouFP2iysrIwbty4ZvXXGI1KVjt37gxDQ0N1h0FERK3AzMwMYrEYKSkpbXZOsVjcrNGd+Ph4BAcHY+LEiTA2NkZERASKi4vrzEn84IMP8PPPPyMmJgbGxsaIj4/H+PHjhePr169HWFgYtm/fDqlUisLCwpa6JADA1q1bERMTI2wrR36Tk5OFEkLR0dEq77WDgwMAID09He7u7tDW1sahQ4cwd+5cODs7QyKRwN/fXygBBQBGRkZITU3FggUL4OjoiM6dO2P69OlYtWrVc2P08/NDZWUlnJycoK2tjUWLFgnlqRoyZMgQZGZm4m9/+xtcXFygUCjQu3fvOrf5vb29MX/+fGhraz934YWVK1fC3NwccXFxuH79OkxNTTF06FB89NFHQhsXFxfI5XKV0Vd3d3ckJiY2Ol8VqK17GhgYiN27dwvJqp2dHeLj4/HJJ58gMjISrq6uiIuLg5+fn/C6mpoahISE4MaNGzA2Noanp6eQeOvp6SEyMhKFhYUQi8VwcXFpsBRUY211dHSwYcMGrFixAtHR0XBxcUFGRgaSkpLw17/+FUOHDoWVlRViY2MRHh7e6HU+SyqVIiYmBkuXLkVgYCD8/Pywc+dOPH78GAcOHMDRo0eb1V9jNCpZ9fb2RlpaGv73v/9xrioR0SvG2toaly9f1ujlVjt06KDykNDDhw8RExNTJ8kyNjau97au0qRJk+rU3WyKnTt3Nqndxx9/rLJoTkN9Pa8/GxsbobZnQ/r16yeU5WoOXV1dfPrpp9iyZUu9xxtK4F9//XUcO3as0b5NTU3x+PHjeo89e80ikQiLFi3CokWLGuyvU6dOdeZiTpkypckrYYWGhmLgwIEoKioSnn4PDQ1FaGioSrtZs2YJ32/cuLHB/pYtW4Zly5bVe6xHjx4qcTXWFqitsBAUFKSyz8HBoU5JNW9vb5Xt+q792VXQoqKihKoMSsnJyXBycmq0BnBzaVRGGBsbi59//hk+Pj5ISEjQ+BVHiIioeaytrTX6Z/uZM2dw+fJlODk54d69e8Io4+TJk9UcGWkyCwsLJCUlQSaTtUipppeZrq5uo4n4i9CoZHXw4MF48uQJTp06hQMHDsDU1LTeZdNEIpFKQWAiIqKWsm7dOhQUFEBPTw/Dhg1DVlZWiz0oQq+u501HaC+eHcVtCRqVrMrlcujo6Kj81V3fMHRTh+WJiIiaw8HBAadPn260TUvPP30VKWuUErUEjUpW+QOAiIiIiJ6mcStYNUVLrTVLRERERJrtpUpW8/LyEBIS0qIreBARERGR5tKoaQD1+f3337Fr1y4kJSUhPz8fCoWi2YVriYiIiOjlpLHJalpaGpKSkvDdd9+hqqoKCoUCzs7OCAwMbHANYCIiIiJ6tWhUslpcXIzk5GQkJydDJpNBoVBAKpXit99+Q0BAAHbs2KHuEImIiIioDak9WX3y5AkOHDiApKQkHD9+HDU1NZBIJPD19YWfnx9Gjx4NHR0drmhFRERE1A6pPQPs3r077t69C5FIhFGjRsHPzw9Tp06FRCJRd2hEREREpGZqT1bv3LkDLS0thIaGIiIiAubm5uoOiYiIiIg0hNpLVwUEBEAsFiM+Ph6WlpZ46623sH//flRXV6s7NCIiIiJSM7Unqzt27EBJSQm2bduGoUOH4tChQ5gxYwa6du2KOXPmIDs7W90hEhEREZGaqD1ZBQAjIyMEBQXh5MmTuHDhAhYvXgw9PT1s374dbm5uEIlEKCgoQFFRkbpDJSIiIqI2pBHJ6tP69++P9evX47fffsO+ffswbtw4iEQiZGVloXfv3vDw8MCXX36p7jCJiIiIqA1oXLKqpKOjA29vb3z//fcoLCxETEwMbGxskJ6ejoCAAHWHR0RERERtQGOT1adZWloiKioK165dQ2pqKmbMmKHukIiIiIioDai9dFVzeXh4wMPDQ91hEBEREVEbeClGVomIiIiofWKySkREREQai8kqEREREWksJqtEREREpLGYrBIRERGRxmKySkREREQai8kqEREREWksJqtEREREpLGYrBIRERGRxmKySkREREQai8kqEREREWksJqtEREREpLGYrBIRERGRxmKySkREREQaq90lq5s3b0aPHj1gYGCA4cOHIzc3V90hEREREVED2lWy+tVXXyEsLAzLly9HXl4e7OzsMH78eNy8eVPdoRERERFRPdpVshofH4/Zs2cjMDAQAwYMwNatW2FoaIgdO3aoOzQiIiIiqoeOugNoK9XV1Th9+jQiIyOFfVpaWhgzZgxOnjxZp31VVRWqqqqE7Xv37gEA7t+/36zzPnjwoPabsl+hqH78ApE3QfkN4VxNiU8Z0y835HhUJWqVkK7fUrxQTIrCMiiqqls+oJLyZsXzdEwX7wCPnrR8SIX3/zhPc96jS6VX8ai6suUDAlB098U+S5eL76CyqhXeJABFN++/UExnruXjweOHLR7P1d+uNSuep2OSyWQqP1daSllZWbNjAv74eaZQKFo8JiKiliJStJOfUv/9738hlUpx4sQJODs7C/sjIiKQmZmJH3/8UaX9xx9/jJiYmLYOk4iozRUXF8PS0lLdYRAR1avdjKw2V2RkJMLCwoRtuVyOu3fvonPnzhCJWmc0koioLSkUClRUVKB79+7qDoWIqEHtJlk1MzODtra2cLtMqaysDBYWFnXa6+vrQ19fX2Wfqalpa4ZIRNTmTExM1B0CEVGj2s0DVnp6ehg2bBiOHz8u7JPL5Th+/LjKtAAiIiIi0hztZmQVAMLCwuDv7w9HR0c4OTnh008/xcOHDxEYGKju0IiIiIioHu0qWfXx8cGtW7cQHR2N0tJS2Nvb4+jRo+jatau6QyMiIiKierSbagBERERE9PJpN3NWiYiIiOjlw2SViIiIiDQWk1UiIiIi0lhMVomIiIhIYzFZJSIiIiKNxWSViIiIiDQWk1UiIiIi0lhMVomIiIhIYzFZJSIiIiKNxWSViIiIiDQWk1UiIiIi0lj/B5XRVJdHLNfUAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 400x300 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "for idx, task in enumerate(tasks):\n",
+    "    fig, ax = plt.subplots(1, figsize=(4, 3))\n",
+    "    task_df = stats_df.set_index(\"task\").loc[task].reset_index().set_index(\"model\")\n",
+    "    existing_models = set(task_df.index.tolist())\n",
+    "    models_for_task = [model for model in models if model in existing_models]\n",
+    "    labels = list(models_for_task)\n",
+    "    colors = [model_to_color[model] for model in models_for_task]\n",
+    "    task_df = stats_df.set_index(\"task\").loc[task].reset_index().set_index(\"model\")\n",
+    "    ax.set_title(task.removeprefix(\"Tool Usage - \"))\n",
+    "    xs = np.arange(len(models_for_task)) * 0.3\n",
+    "\n",
+    "    # Plot the content\n",
+    "    yerrs = []\n",
+    "    values = []\n",
+    "    for model in models_for_task:\n",
+    "        record = task_df.loc[model]\n",
+    "        values.append(round(record[\"% correct\"], 2))\n",
+    "        yerrs.append(record[\"error\"])\n",
+    "        \n",
+    "    rects = ax.bar(\n",
+    "        xs,\n",
+    "        values,\n",
+    "        0.2,\n",
+    "        label=labels, \n",
+    "        yerr=yerrs,\n",
+    "        color=colors,\n",
+    "        edgecolor=\"black\",\n",
+    "        capsize=4,\n",
+    "    )\n",
+    "    ax.bar_label(rects, padding=0, label_type=\"edge\")\n",
+    "    ax.set_ylim(0, 1.1)\n",
+    "    ax.set_yticks([0, 1])\n",
+    "    ax.set_xticks([])\n",
+    "\n",
+    "    ax.set_ylabel(\"% Questions\\nAnswered Correctly\", fontdict={\"size\": 14})\n",
+    "    # ax.legend(loc = 'upper center', bbox_to_anchor = (0.5, 1.6), frameon=False)\n",
+    "    ax.legend(loc=\"center left\", bbox_to_anchor=(1.05, 0.5), frameon=False)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}