Skip to content

armgit / camel

Public Imported from GitHub
0

๐Ÿซ CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

docs: model speed (#1102)

Wendong-Fan21672c6fe997
diff --git a/camel/workforce/task_channel.py b/camel/workforce/task_channel.py
index cc371172b..cc881f131 100644
--- a/camel/workforce/task_channel.py
+++ b/camel/workforce/task_channel.py
@@ -21,12 +21,13 @@ from camel.tasks import Task
class PacketStatus(Enum):
r"""The status of a packet. The packet can be in one of the following
states:
+
- ``SENT``: The packet has been sent to a worker.
- ``RETURNED``: The packet has been returned by the worker, meaning that
- the status of the task inside has been updated.
+ the status of the task inside has been updated.
- ``ARCHIVED``: The packet has been archived, meaning that the content of
- the task inside will not be changed. The task is considered
- as a dependency.
+ the task inside will not be changed. The task is considered
+ as a dependency.
"""
SENT = "SENT"
diff --git a/docs/camel.workforce.rst b/docs/camel.workforce.rst
index 896caaa03..977c8116a 100644
--- a/docs/camel.workforce.rst
+++ b/docs/camel.workforce.rst
@@ -12,32 +12,32 @@ camel.workforce.base module
:undoc-members:
:show-inheritance:
-camel.workforce.manager\_node module
-------------------------------------
+camel.workforce.prompts module
+---------------------------
-.. automodule:: camel.workforce.manager_node
+.. automodule:: camel.workforce.prompts
:members:
:undoc-members:
:show-inheritance:
-camel.workforce.role\_playing\_node module
-------------------------------------------
+camel.workforce.role\_playing\_worker module
+------------------------------------
-.. automodule:: camel.workforce.role_playing_node
+.. automodule:: camel.workforce.role_playing_worker
:members:
:undoc-members:
:show-inheritance:
-camel.workforce.single\_agent\_node module
+camel.workforce.single\_agent\_worker module
------------------------------------------
-.. automodule:: camel.workforce.single_agent_node
+.. automodule:: camel.workforce.single_agent_worker
:members:
:undoc-members:
:show-inheritance:
camel.workforce.task\_channel module
-------------------------------------
+------------------------------------------
.. automodule:: camel.workforce.task_channel
:members:
@@ -52,10 +52,10 @@ camel.workforce.utils module
:undoc-members:
:show-inheritance:
-camel.workforce.worker\_node module
+camel.workforce.worker module
-----------------------------------
-.. automodule:: camel.workforce.worker_node
+.. automodule:: camel.workforce.worker
:members:
:undoc-members:
:show-inheritance:
@@ -68,14 +68,6 @@ camel.workforce.workforce module
:undoc-members:
:show-inheritance:
-camel.workforce.workforce\_prompt module
-----------------------------------------
-
-.. automodule:: camel.workforce.workforce_prompt
- :members:
- :undoc-members:
- :show-inheritance:
-
Module contents
---------------
diff --git a/docs/cookbooks/model_speed_comparison.ipynb b/docs/cookbooks/model_speed_comparison.ipynb
new file mode 100644
index 000000000..75513eb7e
--- /dev/null
+++ b/docs/cookbooks/model_speed_comparison.ipynb
@@ -0,0 +1,216 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "APw8wDolb0L9"
+ },
+ "source": [
+ "# Model Speed Comparison Cookbook"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "vLCfmNtRb-jR"
+ },
+ "source": [
+ "You can also check this cookbook in colab [here](https://colab.research.google.com/drive/1oZfsgYfPPLVtMeA6DhsCd5jbdiAzEQSW?usp=sharing)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "jHQhWNnhcOch"
+ },
+ "source": [
+ "## Overview\n",
+ "In this section, we'll explore the speed of different AI models by creating instances of `ChatAgent` and measuring their response times to user prompts."
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "XuZwbB1IIuUi"
+ },
+ "source": [
+ "### Installation"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "gIJK4Lu5Iwm0"
+ },
+ "source": [
+ "Ensure you have CAMEL AI installed in your Python environment:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "UtcC3c-KVZmU"
+ },
+ "outputs": [],
+ "source": [
+ "%pip install \"camel-ai[all]==0.2.3a\""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "MyTTCe3IR_Lr"
+ },
+ "source": [
+ "### Setting Up API Keys"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "REqzgGL9SEaD"
+ },
+ "source": [
+ "You'll need to set up your API keys for OpenAI and SambaNova."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "id": "PNBFEXc-R-0s",
+ "outputId": "bba35874-c5a0-49a8-c1b3-3070958845ef"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Enter your OpenAI API key: ยทยทยทยทยทยทยทยทยทยท\n",
+ "Enter your SambaNova API key: ยทยทยทยทยทยทยทยทยทยท\n"
+ ]
+ }
+ ],
+ "source": [
+ "import os\n",
+ "from getpass import getpass\n",
+ "\n",
+ "# Prompt for the API key securely\n",
+ "openai_api_key = getpass('Enter your OpenAI API key: ')\n",
+ "os.environ[\"OPENAI_API_KEY\"] = openai_api_key\n",
+ "\n",
+ "sambanova_api_key = getpass('Enter your SambaNova API key: ')\n",
+ "os.environ[\"SAMBA_API_KEY\"] = sambanova_api_key"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 564
+ },
+ "id": "ZT2tYqYh6EDj",
+ "outputId": "bf30ee06-c0bf-4b57-8352-7d1809361836"
+ },
+ "outputs": [
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAA88AAAIjCAYAAAA9eimOAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB5yElEQVR4nOzdeXwNZ///8feRSEJWBEFJkIRILLE2tNZobClql9prraKlLW1tVUUXS1Hau6mttqKLWymhtQVVKqqS2lPu2lpbEmuTzO8Pv8zXkTCJIl1ez8fjPO6ea66Z+cx1JnG/c83MsRmGYQgAAAAAANxRntwuAAAAAACAvzrCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwDgL8Nms2nMmDE5Xi8xMVE2m01z58697zX9lfj5+al79+65XcbfQvfu3eXn55fbZTx0GzdulM1m0/Lly3O7FPyF3OvvVgD2CM8AADtz586VzWaTzWbT1q1bMy03DEMlS5aUzWZTixYtcqHCPycxMVE9evRQ2bJl5eLiIh8fH9WtW1ejR4/O7dLuq2vXrmnKlCmqVauWPD095eLiosDAQA0cOFAHDx7M7fJwi4zAm50XHox9+/apbdu28vX1lYuLi0qUKKHGjRtr+vTpuV0agL8Qx9wuAADw1+Ti4qJFixbpscces2vftGmT/ve//8nZ2TmXKrt3hw8fVo0aNZQvXz717NlTfn5+OnXqlH744QdNmjRJY8eOze0S74vff/9dTZo00e7du9WiRQt17txZbm5uOnDggJYsWaIPP/xQN27cyO0yH6j//Oc/Sk9Pz+0ysiUoKEgLFiywaxsxYoTc3Nz06quv5lJV/x7btm1TgwYNVKpUKfXu3Vs+Pj46ceKEduzYoWnTpum5557L7RIB/EUQngEAWWrWrJmWLVum9957T46O//fPxaJFi1StWjX9/vvvuVjdvZkyZYpSUlIUFxcnX19fu2Vnz57Nparuv+7du2vPnj1avny52rRpY7ds3Lhx/+hAdvnyZbm6uipv3ry5XUq2FS1aVE8//bRd28SJE+Xt7Z2pHfcm47zIyvjx4+Xp6anvv/9eXl5edsv+Sb8XAPx5XLYNAMhSp06ddO7cOcXExJhtN27c0PLly9W5c+cs17l8+bKGDh2qkiVLytnZWeXKldM777wjwzDs+l2/fl3PP/+8ChcuLHd3dz355JP63//+l+U2f/31V/Xs2VNFixaVs7OzgoOD9fHHH9/TMR05ckSPPPJIpuAsSUWKFLF77+fnpxYtWmjdunWqUqWKXFxcVKFCBX322WeZ1r148aKGDBliHre/v78mTZqUaeYzPT1dU6dOVXBwsFxcXFS0aFH17dtXFy5csOtnGIbeeOMNPfLII8qfP78aNGig/fv3Z+sYv/vuO3311Vfq1atXpuAsSc7OznrnnXfs2r755hs9/vjjcnV1lZeXl1q2bKmEhAS7PmPGjJHNZtPBgwf19NNPy9PTU4ULF9bIkSNlGIZOnDihli1bysPDQz4+Pnr33Xft1s+4NHnp0qV65ZVX5OPjI1dXVz355JM6ceKEXd8tW7aoXbt2KlWqlJydnVWyZEk9//zzunr1ql2/7t27y83NTUeOHFGzZs3k7u6uqKgoc9nt9zwvWbJE1apVk7u7uzw8PFSxYkVNmzbNrs/Ro0fVrl07FSxYUPnz59ejjz6qr776Kstj+fTTTzV+/Hg98sgjcnFxUaNGjXT48GG7vleuXNHPP/98X/7YlJ3asnL9+nW1aNFCnp6e2rZtm6Tsn4sZPwdbt25VzZo15eLiojJlymj+/Pl2/f744w+NHTtWAQEBcnFxUaFChfTYY4/Z/f7ISsZtIps3b1bfvn1VqFAheXh4qGvXrplqkaQ1a9aY56q7u7uaN2+e6WfjbudFVo4cOaLg4OBMwVnK/HtBkj755BNVq1ZN+fLlU8GCBdWxY8dM57B082exWbNmKlCggFxdXVWpUqVM51tOfvYOHz6s7t27y8vLS56enurRo4euXLli1zcnv1sB5BzhGQCQJT8/P4WFhWnx4sVm25o1a3Tp0iV17NgxU3/DMPTkk09qypQpatKkiSZPnqxy5crpxRdf1AsvvGDX95lnntHUqVP1xBNPaOLEicqbN6+aN2+eaZtnzpzRo48+qvXr12vgwIGaNm2a/P391atXL02dOjXHx+Tr66sTJ07om2++yVb/Q4cOqUOHDmratKkmTJggR0dHtWvXzi4QXLlyRfXq1dMnn3yirl276r333lOdOnU0YsSITMfdt29fvfjii6pTp46mTZumHj16aOHChYqIiNAff/xh9hs1apRGjhypypUr6+2331aZMmX0xBNP6PLly5Y1r1y5UpLUpUuXbB3j+vXrFRERobNnz2rMmDF64YUXtG3bNtWpU0eJiYmZ+nfo0EHp6emaOHGiatWqpTfeeENTp05V48aNVaJECU2aNEn+/v4aNmyYNm/enGn98ePH66uvvtLLL7+sQYMGKSYmRuHh4XbBeNmyZbpy5Yr69++v6dOnKyIiQtOnT1fXrl0zbS81NVUREREqUqSI3nnnnSz/YCBJMTEx6tSpkwoUKKBJkyZp4sSJql+/vmJjY80+Z86cUe3atbV27VoNGDBA48eP17Vr1/Tkk0/q888/z7TNiRMn6vPPP9ewYcM0YsQI7dixI1NI27lzp4KCgjRjxow7fgbZkdPaMly9elWRkZHatm2b1q9fr9q1a0vK/rko3bzdoW3btmrcuLHeffddFShQQN27d7cLrWPGjNHYsWPVoEEDzZgxQ6+++qpKlSqlH374IVvHN3DgQCUkJGjMmDHq2rWrFi5cqFatWtn94W3BggVq3ry53NzcNGnSJI0cOVLx8fF67LHHMp2r2T0vpJu/F3bv3q2ffvrJss7x48era9euCggI0OTJkzVkyBBt2LBBdevW1cWLF81+MTExqlu3ruLj4zV48GC9++67atCggVatWmX2yenPXvv27ZWcnKwJEyaoffv2mjt3bqZbTbL7uxXAPTIAALjFnDlzDEnG999/b8yYMcNwd3c3rly5YhiGYbRr185o0KCBYRiG4evrazRv3txc74svvjAkGW+88Ybd9tq2bWvYbDbj8OHDhmEYRlxcnCHJGDBggF2/zp07G5KM0aNHm229evUyihUrZvz+++92fTt27Gh4enqadR07dsyQZMyZM+eux/bTTz8Z+fLlMyQZVapUMQYPHmx88cUXxuXLlzP19fX1NSQZK1asMNsuXbpkFCtWzAgNDTXbxo0bZ7i6uhoHDx60W3/48OGGg4ODcfz4ccMwDGPLli2GJGPhwoV2/b7++mu79rNnzxpOTk5G8+bNjfT0dLPfK6+8YkgyunXrdtdjbN26tSHJuHDhwl37ZahSpYpRpEgR49y5c2bb3r17jTx58hhdu3Y120aPHm1IMvr06WO2paamGo888ohhs9mMiRMnmu0XLlww8uXLZ1frt99+a0gySpQoYSQlJZntn376qSHJmDZtmtmW8bneasKECYbNZjN++eUXs61bt26GJGP48OGZ+nfr1s3w9fU13w8ePNjw8PAwUlNT7zgWQ4YMMSQZW7ZsMduSk5ON0qVLG35+fkZaWprdsQQFBRnXr183+06bNs2QZOzbty/Tcd96XmdHcHCwUa9evXuubdmyZUZycrJRr149w9vb29izZ4+5XnbPRcP4v5+DzZs3m21nz541nJ2djaFDh5ptlStXtvt9kF0Zv2+qVatm3Lhxw2x/6623DEnGl19+aR6rl5eX0bt3b7v1T58+bXh6etq13+28yMq6desMBwcHw8HBwQgLCzNeeuklY+3atXb1GIZhJCYmGg4ODsb48ePt2vft22c4Ojqa7ampqUbp0qUNX1/fTD+Ht/5M5/Rnr2fPnnbbat26tVGoUCHzfU5+twK4N8w8AwDuqH379rp69apWrVql5ORkrVq16o6XbK9evVoODg4aNGiQXfvQoUNlGIbWrFlj9pOUqd+QIUPs3huGoRUrVigyMlKGYej33383XxEREbp06VK2Z7UyBAcHKy4uTk8//bQSExM1bdo0tWrVSkWLFtV//vOfTP2LFy+u1q1bm+8zLifds2ePTp8+LenmLOnjjz+uAgUK2NUYHh6utLQ0c/Z12bJl8vT0VOPGje36VatWTW5ubvr2228l3ZyNunHjhp577jm7pyvfPj53kpSUJElyd3e37Hvq1CnFxcWpe/fuKliwoNleqVIlNW7c2PysbvXMM8+Y/+3g4KDq1avLMAz16tXLbPfy8lK5cuV09OjRTOt37drVrra2bduqWLFidvvKly+f+d+XL1/W77//rtq1a8swDO3ZsyfTNvv37295rF5eXrp8+fJdLyNevXq1atasafeQPDc3N/Xp00eJiYmKj4+369+jRw85OTmZ7x9//HFJsjvu+vXryzCMP/01QTmt7dKlS3riiSf0888/a+PGjapSpYq5LLvnYoYKFSqYxyZJhQsXzvT5enl5af/+/Tp06NA9HV+fPn3s7lPv37+/HB0dzfMiJiZGFy9eVKdOnexqdnBwUK1atTLVnLGN7GjcuLG2b9+uJ598Unv37tVbb72liIgIlShRwrySQ5I+++wzpaenq3379nY1+Pj4KCAgwKxhz549OnbsmIYMGZLpUvCMn+l7+dnr16+f3fvHH39c586dM3/ms/u7FcC944FhAIA7Kly4sMLDw7Vo0SJduXJFaWlpatu2bZZ9f/nlFxUvXjxTaAsKCjKXZ/xvnjx5VLZsWbt+5cqVs3v/22+/6eLFi/rwww/14YcfZrnPe3mYT2BgoBYsWKC0tDTFx8dr1apVeuutt9SnTx+VLl1a4eHhZl9/f/9MXw8UGBgo6eZXXvn4+OjQoUP68ccfVbhw4bvWeOjQIV26dCnLeyhv7ZcxTgEBAXbLCxcurAIFClgen4eHhyQpOTk5y3s4b5Wxr9vHXrr5ua1duzbTg5ZKlSpl1y/ja7C8vb0ztZ87dy7Tdm8/LpvNJn9/f7vLVI8fP65Ro0Zp5cqVme57vXTpkt17R0dHPfLII3c5ypsGDBigTz/9VE2bNlWJEiX0xBNPqH379mrSpInZ55dfflGtWrUyrXvrORwSEmK23z4WGZ9PVvfq/lk5rW3IkCG6du2a9uzZo+DgYLt1snsuZrj9OKWbx3rrcb7++utq2bKlAgMDFRISoiZNmqhLly6qVKlSto7v9vPCzc1NxYoVM8+LjFDesGHDLNfPOO8zZPe8yFCjRg199tlnunHjhvbu3avPP/9cU6ZMUdu2bRUXF6cKFSro0KFDMgwjU60ZMsL/kSNHJMnu87jd/fjZu/V88/DwyPbvVgD3jvAMALirzp07q3fv3jp9+rSaNm1qGcjul4yHbT399NPq1q1bln2y+3/Ms+Lg4KCKFSuqYsWKCgsLU4MGDbRw4UK78JzdOhs3bqyXXnopy+UZYTs9PV1FihTRwoULs+x3p/CdU+XLl5d083trb50tvF8cHByy1SYp04PisiMtLU2NGzfW+fPn9fLLL6t8+fJydXXVr7/+qu7du2d6CJuzs7Py5LG+kK5IkSKKi4vT2rVrtWbNGq1Zs0Zz5sxR165dNW/evBzXKd3f477fWrZsqSVLlmjixImaP3++3Rjl9FzMznHWrVtXR44c0Zdffql169bpo48+0pQpUzR79my7qxXuVcbnvmDBAvn4+GRafus3AkjZPy9u5+TkpBo1aqhGjRoKDAxUjx49tGzZMo0ePVrp6emy2Wxas2ZNlmPi5uaW4/3lxF/5fAP+LQjPAIC7at26tfr27asdO3Zo6dKld+zn6+ur9evXKzk52W72+eeffzaXZ/xvenq6jhw5YjcjcuDAAbvtZTwtNi0tLceBNqeqV68u6eallLc6fPiwDMOwm30+ePCgJJlPci5btqxSUlIsayxbtqzWr1+vOnXq2F2WfLuMcTp06JDKlCljtv/222/ZmtGMjIzUhAkT9Mknn1iG54x93T720s3Pzdvb+45f73Ovbr+s1zAMHT582PxDyL59+3Tw4EHNmzfP7gFhVk9tzg4nJydFRkYqMjJS6enpGjBggD744AONHDlS/v7+8vX1veNYSMryKe0PS05ra9WqlZ544gl1795d7u7umjVrlrksu+diThUsWFA9evRQjx49lJKSorp162rMmDHZCs+HDh1SgwYNzPcpKSk6deqUmjVrZtYs3fwjyIP+fZDh9t8LZcuWlWEYKl26tPlHsaxk1PrTTz/dsdYH8bOX3d+tAO4d9zwDAO7Kzc1Ns2bN0pgxYxQZGXnHfs2aNVNaWlqmpwpPmTJFNptNTZs2lSTzf9977z27frc/PdvBwUFt2rTRihUrsnwK7m+//ZbjY9myZUumJwlL/3ev4O2XN548edLuScZJSUmaP3++qlSpYs5+tW/fXtu3b9fatWszbffixYtKTU01+6WlpWncuHGZ+qWmpppP6g0PD1fevHk1ffp0uxml7D5dPCwsTE2aNNFHH32kL774ItPyGzduaNiwYZKkYsWKqUqVKpo3b57dk4J/+uknrVu3zgwu99P8+fOVnJxsvl++fLlOnTplnhcZs2u3HrthGJm+4ienbr+EPE+ePGZgv379uqSb5/DOnTu1fft2s9/ly5f14Ycfys/PTxUqVMjxfu/XV1XdS20ZT3+fPXu2Xn75ZbM9u+diTtw+vm5ubvL39zfH1sqHH35o97M5a9YspaammudFRESEPDw89Oabb2b5M3wvvw8yfPvtt1nO3t7+e+Gpp56Sg4ODxo4dm6m/YRjmGFStWlWlS5fW1KlTM41lxnoP4mcvu79bAdw7Zp4BAJbudNn0rSIjI9WgQQO9+uqrSkxMVOXKlbVu3Tp9+eWXGjJkiDkbU6VKFXXq1Envv/++Ll26pNq1a2vDhg2Zvh9XuvlVQN9++61q1aql3r17q0KFCjp//rx++OEHrV+/XufPn8/RcUyaNEm7d+/WU089ZQanH374QfPnz1fBggUzPVgnMDBQvXr10vfff6+iRYvq448/1pkzZzRnzhyzz4svvqiVK1eqRYsW6t69u6pVq6bLly9r3759Wr58uRITE+Xt7a169eqpb9++mjBhguLi4vTEE08ob968OnTokJYtW6Zp06apbdu2Kly4sIYNG6YJEyaoRYsWatasmfbs2aM1a9Zkuq/4TubPn68nnnhCTz31lCIjI9WoUSO5urrq0KFDWrJkiU6dOmV+1/Pbb7+tpk2bKiwsTL169dLVq1c1ffp0eXp6/umHXGWlYMGCeuyxx9SjRw+dOXNGU6dOlb+/v3r37i3p5mXnZcuW1bBhw/Trr7/Kw8NDK1as+NP3ET/zzDM6f/68GjZsqEceeUS//PKLpk+fripVqpj3DQ8fPlyLFy9W06ZNNWjQIBUsWFDz5s3TsWPHtGLFinu6DHjnzp1q0KCBRo8e/afG815rGzhwoJKSkvTqq6/K09NTr7zySrbPxZyoUKGC6tevr2rVqqlgwYLatWuXli9froEDB2Zr/Rs3bqhRo0Zq3769Dhw4oPfff1+PPfaYnnzySUk372meNWuWunTpoqpVq6pjx44qXLiwjh8/rq+++kp16tS5568De+6553TlyhW1bt1a5cuX140bN7Rt2zYtXbpUfn5+6tGjh6SbM8pvvPGGRowYocTERLVq1Uru7u46duyYPv/8c/Xp00fDhg1Tnjx5NGvWLEVGRqpKlSrq0aOHihUrpp9//ln79+83/9B2v3/2cvK7FcA9eqjP9gYA/OXd+lVVd3P7V1UZxs2vk3n++eeN4sWLG3nz5jUCAgKMt99+2+7rWQzDMK5evWoMGjTIKFSokOHq6mpERkYaJ06cyPLrVM6cOWM8++yzRsmSJY28efMaPj4+RqNGjYwPP/zQ7JPdr6qKjY01nn32WSMkJMTw9PQ08ubNa5QqVcro3r27ceTIkSyPb+3atUalSpUMZ2dno3z58sayZcsybTc5OdkYMWKE4e/vbzg5ORne3t5G7dq1jXfeeSfT1918+OGHRrVq1Yx8+fIZ7u7uRsWKFY2XXnrJOHnypNknLS3NGDt2rFGsWDEjX758Rv369Y2ffvrJ8PX1tfyqqgxXrlwx3nnnHaNGjRqGm5ub4eTkZAQEBBjPPfec+bVhGdavX2/UqVPHyJcvn+Hh4WFERkYa8fHxdn0yvi7nt99+s2vv1q2b4erqmmn/9erVM4KDg833GV+htHjxYmPEiBFGkSJFjHz58hnNmze3+/opwzCM+Ph4Izw83HBzczO8vb2N3r17G3v37s30Gd9p3xnLbv2qquXLlxtPPPGEUaRIEcPJyckoVaqU0bdvX+PUqVN26x05csRo27at4eXlZbi4uBg1a9Y0Vq1aZdfn1q+DulVW5+H9+qqqP1vbSy+9ZEgyZsyYYbZl51zM6ufcMG5+vrfW98Ybbxg1a9Y0vLy8jHz58hnly5c3xo8fn+n8v13G75tNmzYZffr0MQoUKGC4ubkZUVFRdl/hdOvxRUREGJ6enoaLi4tRtmxZo3v37sauXbvMPnc7L7KyZs0ao2fPnkb58uXNnxV/f3/jueeeM86cOZOp/4oVK4zHHnvMcHV1NVxdXY3y5csbzz77rHHgwAG7flu3bjUaN25suLu7G66urkalSpWM6dOn2/X5Mz97GWN37Ngxsy0nv1sB5JzNMHjKAAAAt/Pz81NISIhWrVqV26X8I2zcuFENGjTQsmXLcjyriX+uuXPnqkePHvr+++/Ne4wB4K+Ke54BAAAAALBAeAYAAAAAwALhGQAAAAAAC9zzDAAAAACABWaeAQAAAACwQHgGAAAAAMCCY24XAOSG9PR0nTx5Uu7u7rLZbLldDgAAAIBcYhiGkpOTVbx4ceXJc+f5ZcIz/pVOnjypkiVL5nYZAAAAAP4iTpw4oUceeeSOywnP+Fdyd3eXdPMHxMPDI5erAQAAAJBbkpKSVLJkSTMj3AnhGf9KGZdqe3h4EJ4BAAAAWN7OyQPDAAAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMCCY24XAOSmyXvPycXtRm6X8bc2PNQ7t0sAAAAAHjhmngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGf85XTv3l2tWrXK0To2m01ffPHFA6kHAAAAAP524fnEiRPq2bOnihcvLicnJ/n6+mrw4ME6d+5crta1fft2OTg4qHnz5pmWJSYmymazKS4u7q7bOHz4sHr27KlSpUrJ2dlZJUqUUKNGjbRw4UKlpqaa/Ww2m/ny9PRUnTp19M0332RaltVrzJgxd61hyZIlstlsWYbX/fv3q3379ipcuLCcnZ0VGBioUaNG6cqVK3fd5pgxY2Sz2dSkSZNMy95++23ZbDbVr1/fbJs2bZrmzp17123e7tSpU2ratGmO1gEAAACA7PpbheejR4+qevXqOnTokBYvXqzDhw9r9uzZ2rBhg8LCwnT+/Plcqy06OlrPPfecNm/erJMnT+Z4/Z07d6pq1apKSEjQzJkz9dNPP2njxo165plnNGvWLO3fv9+u/5w5c3Tq1CnFxsbK29tbLVq00NGjR3Xq1CnzNXXqVHl4eNi1DRs27I41JCYmatiwYXr88cczLduxY4dq1aqlGzdu6KuvvtLBgwc1fvx4zZ07V40bN9aNGzfuenzFihXTt99+q//973927R9//LFKlSpl1+bp6SkvLy+LEbPn4+MjZ2fnHK0DAAAAANn1twrPzz77rJycnLRu3TrVq1dPpUqVUtOmTbV+/Xr9+uuvevXVV82+fn5+GjdunDp16iRXV1eVKFFCM2fOtNvexYsX9cwzz6hw4cLy8PBQw4YNtXfvXnP5mDFjVKVKFS1YsEB+fn7y9PRUx44dlZycbLedlJQULV26VP3791fz5s1zPGtqGIa6d++uwMBAxcbGKjIyUgEBAQoICFCnTp20detWVapUyW4dLy8v+fj4KCQkRLNmzdLVq1cVExMjHx8f8+Xp6SmbzWbX5ubmlmUNaWlpioqK0tixY1WmTJlM9fXq1UtBQUH67LPPVLNmTfn6+qpdu3b673//q+3bt2vKlCl3PcYiRYroiSee0Lx588y2bdu26ffff880W3/7Zdv169fXoEGD9NJLL6lgwYLy8fHJNIPOZdsAAAAAHqS/TXg+f/681q5dqwEDBihfvnx2y3x8fBQVFaWlS5fKMAyz/e2331blypW1Z88eDR8+XIMHD1ZMTIy5vF27djp79qzWrFmj3bt3q2rVqmrUqJHdDPaRI0f0xRdfaNWqVVq1apU2bdqkiRMn2u3/008/Vfny5VWuXDk9/fTT+vjjj+3qsBIXF6eEhAQNGzZMefJk/ZHYbLY7rp8xHlazv3fz+uuvq0iRIurVq1eW9cXHx+uFF17IVF/lypUVHh6uxYsXW+6jZ8+edn9Y+PjjjxUVFSUnJyfLdefNmydXV1d99913euutt/T666/bfZZWrl+/rqSkJLsXAAAAAGTX3yY8Hzp0SIZhKCgoKMvlQUFBunDhgn777TezrU6dOho+fLgCAwP13HPPqW3btuYM6datW7Vz504tW7ZM1atXV0BAgN555x15eXlp+fLl5jbS09M1d+5chYSE6PHHH1eXLl20YcMGu31HR0fr6aefliQ1adJEly5d0qZNm7J9bAcPHpQklStXzmw7e/as3NzczNf777+f5bpXrlzRa6+9JgcHB9WrVy/b+7zV1q1bFR0drf/85z93re9uY5/R525atGihpKQkbd68WZcvX9ann36qnj17ZqvGSpUqafTo0QoICFDXrl1VvXr1TJ/D3UyYMEGenp7mq2TJktleFwAAAAD+NuE5Q05mdMPCwjK9T0hIkCTt3btXKSkpKlSokF1IPXbsmI4cOWKu4+fnJ3d3d/N9sWLFdPbsWfP9gQMHtHPnTnXq1EmS5OjoqA4dOig6Ovqeji9DoUKFFBcXp7i4OHl5eWWaVe7UqZPc3Nzk7u6uFStWKDo6OtOl3bc7fvy43bG++eabSk5OVpcuXfSf//xH3t7ed10/J2Oflbx58+rpp5/WnDlztGzZMgUGBlrWnOH2frd/DlZGjBihS5cuma8TJ07kqHYAAAAA/26OuV1Advn7+8tmsykhIUGtW7fOtDwhIUEFChRQ4cKFs7W9lJQUFStWTBs3bsy07NaHVeXNm9dumc1mU3p6uvk+OjpaqampKl68uNlmGIacnZ01Y8YMeXp6WtYSEBAg6WYQDw0NlSQ5ODjI399f0s1AfrspU6YoPDxcnp6e2T7m4sWL2z3xu2DBgjpy5IgSExMVGRlptmccn6Ojow4cOKDAwEBJN8c4o75bJSQkmH2s9OzZU7Vq1dJPP/2U7VlnyfpzsOLs7MwDxQAAAADcs79NeC5UqJAaN26s999/X88//7zdfc+nT5/WwoUL1bVrV7t7g3fs2GG3jR07dpiXHletWlWnT5+Wo6Oj/Pz87qmm1NRUzZ8/X++++66eeOIJu2WtWrXS4sWL1a9fP8vthIaGqnz58nrnnXfUvn37O973fCsfHx8zXGeXo6NjpnXy58+vffv22bW99tprSk5O1rRp01SyZEnlzZtX5cuX15QpU9SxY0e7+vbu3av169drwoQJ2aohODhYwcHB+vHHH9W5c+cc1Q8AAAAAueVvddn2jBkzdP36dUVERGjz5s06ceKEvv76azVu3FglSpTQ+PHj7frHxsbqrbfe0sGDBzVz5kwtW7ZMgwcPliSFh4crLCxMrVq10rp165SYmKht27bp1Vdf1a5du7JVz6pVq3ThwgX16tVLISEhdq82bdpk+9Jtm82mOXPm6MCBA6pTp45WrlypQ4cOKT4+XrNnz9Zvv/0mBweHnA1WNrm4uGSq3cvLS+7u7goJCZGTk5NsNpuio6MVHx+vNm3aaOfOnTp+/LiWLVumyMhIhYWFaciQIdne5zfffKNTp07l+OuoAAAAACC3/K3Cc0BAgHbt2qUyZcqoffv2Klu2rPr06aMGDRpo+/btKliwoF3/oUOHateuXQoNDdUbb7yhyZMnKyIiQtLNwLp69WrVrVtXPXr0UGBgoDp27KhffvlFRYsWzVY90dHR5qXTt2vTpo127dqlH3/8MVvbevTRR7V7926VK1dOzz77rCpUqKDatWtr8eLFmjJlivr375+t7TwotWvX1o4dO+Tg4KCmTZvK399fI0aMULdu3RQTE5OjS6JdXV0JzgAAAAD+VmzGn30K1F+Un5+fhgwZkqMZUfx7JCUlydPTU6M3H5WLm7v1Crij4aF3f9AcAAAA8FeWkQ0uXbokDw+PO/b7W808AwAAAACQGwjPAAAAAABY+Ns8bTunEhMTc7sEAAAAAMA/BDPPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXH3C4AyE0vVC4kDw+P3C4DAAAAwF8cM88AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFhwzO0CgNw0ee85ubjdyO0yHojhod65XQIAAADwj8HMMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXC8z04ceKEevbsqeLFi8vJyUm+vr4aPHiwzp07l6t1bd++XQ4ODmrevHmmZYmJibLZbIqLi7vrNg4fPqyePXuqVKlScnZ2VokSJdSoUSMtXLhQqampZj+bzWa+PD09VadOHX3zzTeZlmX1GjNmzF1rWLJkiWw2m1q1apVp2f79+9W+fXsVLlxYzs7OCgwM1KhRo3TlyhXL8QEAAACAe0V4zqGjR4+qevXqOnTokBYvXqzDhw9r9uzZ2rBhg8LCwnT+/Plcqy06OlrPPfecNm/erJMnT+Z4/Z07d6pq1apKSEjQzJkz9dNPP2njxo165plnNGvWLO3fv9+u/5w5c3Tq1CnFxsbK29tbLVq00NGjR3Xq1CnzNXXqVHl4eNi1DRs27I41JCYmatiwYXr88cczLduxY4dq1aqlGzdu6KuvvtLBgwc1fvx4zZ07V40bN9aNGzdyfMwAAAAAkB2E5xx69tln5eTkpHXr1qlevXoqVaqUmjZtqvXr1+vXX3/Vq6++avb18/PTuHHj1KlTJ7m6uqpEiRKaOXOm3fYuXryoZ555RoULF5aHh4caNmyovXv3msvHjBmjKlWqaMGCBfLz85Onp6c6duyo5ORku+2kpKRo6dKl6t+/v5o3b665c+fm6LgMw1D37t0VGBio2NhYRUZGKiAgQAEBAerUqZO2bt2qSpUq2a3j5eUlHx8fhYSEaNasWbp69apiYmLk4+Njvjw9PWWz2eza3NzcsqwhLS1NUVFRGjt2rMqUKZOpvl69eikoKEifffaZatasKV9fX7Vr107//e9/tX37dk2ZMiVHxwwAAAAA2UV4zoHz589r7dq1GjBggPLly2e3zMfHR1FRUVq6dKkMwzDb3377bVWuXFl79uzR8OHDNXjwYMXExJjL27Vrp7Nnz2rNmjXavXu3qlatqkaNGtnNYB85ckRffPGFVq1apVWrVmnTpk2aOHGi3f4//fRTlS9fXuXKldPTTz+tjz/+2K4OK3FxcUpISNCwYcOUJ0/Wp4XNZrvj+hnj8Wdmf19//XUVKVJEvXr1yrK++Ph4vfDCC5nqq1y5ssLDw7V48eI7bvv69etKSkqyewEAAABAdhGec+DQoUMyDENBQUFZLg8KCtKFCxf022+/mW116tTR8OHDFRgYqOeee05t27Y1Z0i3bt2qnTt3atmyZapevboCAgL0zjvvyMvLS8uXLze3kZ6errlz5yokJESPP/64unTpog0bNtjtOzo6Wk8//bQkqUmTJrp06ZI2bdqU7WM7ePCgJKlcuXJm29mzZ+Xm5ma+3n///SzXvXLlil577TU5ODioXr162d7nrbZu3aro6Gj95z//uWt9dxv7jD5ZmTBhgjw9Pc1XyZIl76lOAAAAAP9OhOd7kJMZ3bCwsEzvExISJEl79+5VSkqKChUqZBdSjx07piNHjpjr+Pn5yd3d3XxfrFgxnT171nx/4MAB7dy5U506dZIkOTo6qkOHDoqOjr6n48tQqFAhxcXFKS4uTl5eXplmlTt16iQ3Nze5u7trxYoVio6OznRp9+2OHz9ud6xvvvmmkpOT1aVLF/3nP/+Rt7f3XdfPydjfasSIEbp06ZL5OnHixD1tBwAAAMC/k2NuF/B34u/vL5vNpoSEBLVu3TrT8oSEBBUoUECFCxfO1vZSUlJUrFgxbdy4MdMyLy8v87/z5s1rt8xmsyk9Pd18Hx0drdTUVBUvXtxsMwxDzs7OmjFjhjw9PS1rCQgIkHQziIeGhkqSHBwc5O/vL+lmIL/dlClTFB4eLk9Pz2wfc/Hixe2e+F2wYEEdOXJEiYmJioyMNNszjs/R0VEHDhxQYGCgpJtjnFHfrRISEsw+WXF2dpazs3O2agQAAACA2xGec6BQoUJq3Lix3n//fT3//PN29z2fPn1aCxcuVNeuXe3uDd6xY4fdNnbs2GFeely1alWdPn1ajo6O8vPzu6eaUlNTNX/+fL377rt64okn7Ja1atVKixcvVr9+/Sy3ExoaqvLly+udd95R+/bt73jf8618fHzMcJ1djo6OmdbJnz+/9u3bZ9f22muvKTk5WdOmTVPJkiWVN29elS9fXlOmTFHHjh3t6tu7d6/Wr1+vCRMm5KgWAAAAAMguLtvOoRkzZuj69euKiIjQ5s2bdeLECX399ddq3LixSpQoofHjx9v1j42N1VtvvaWDBw9q5syZWrZsmQYPHixJCg8PV1hYmFq1aqV169YpMTFR27Zt06uvvqpdu3Zlq55Vq1bpwoUL6tWrl0JCQuxebdq0yfal2zabTXPmzNGBAwdUp04drVy5UocOHVJ8fLxmz56t3377TQ4ODjkbrGxycXHJVLuXl5fc3d0VEhIiJycn2Ww2RUdHKz4+Xm3atNHOnTt1/PhxLVu2TJGRkQoLC9OQIUMeSH0AAAAAQHjOoYCAAO3atUtlypRR+/btVbZsWfXp00cNGjTQ9u3bVbBgQbv+Q4cO1a5duxQaGqo33nhDkydPVkREhKSbgXX16tWqW7euevToocDAQHXs2FG//PKLihYtmq16oqOjzUunb9emTRvt2rVLP/74Y7a29eijj2r37t0qV66cnn32WVWoUEG1a9fW4sWLNWXKFPXv3z9b23lQateurR07dsjBwUFNmzaVv7+/RowYoW7duikmJobLsgEAAAA8MDbjXp/ABEt+fn4aMmQIM6J/QUlJSfL09NTozUfl4uZuvcLf0PDQuz98DQAAAMD/ZYNLly7Jw8Pjjv2YeQYAAAAAwALhGQAAAAAACzxt+wFKTEzM7RIAAAAAAPcBM88AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcfcLgDITS9ULiQPD4/cLgMAAADAXxwzzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABgwTG3CwBy0+S95+TidiO3y/jHGB7qndslAAAAAA8EM88AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIzcsXcuXPl5eWV22UAAAAAQLb8Y8LziRMn1LNnTxUvXlxOTk7y9fXV4MGDde7cuVyta/v27XJwcFDz5s0zLUtMTJTNZlNcXNxdt7F//361b99ehQsXlrOzswIDAzVq1ChduXLFrt+HH36o+vXry8PDQzabTRcvXrSsr3v37rLZbLLZbHJycpK/v79ef/11paam5uQwc6xDhw46ePDgA90HAAAAANwv/4jwfPToUVWvXl2HDh3S4sWLdfjwYc2ePVsbNmxQWFiYzp8/n2u1RUdH67nnntPmzZt18uTJHK+/Y8cO1apVSzdu3NBXX32lgwcPavz48Zo7d64aN26sGzdumH2vXLmiJk2a6JVXXsnRPpo0aaJTp07p0KFDGjp0qMaMGaO33347y7637u/PyJcvn4oUKXJftgUAAAAAD9o/Ijw/++yzcnJy0rp161SvXj2VKlVKTZs21fr16/Xrr7/q1VdfNfv6+flp3Lhx6tSpk1xdXVWiRAnNnDnTbnsXL17UM888o8KFC8vDw0MNGzbU3r17zeVjxoxRlSpVtGDBAvn5+cnT01MdO3ZUcnKy3XZSUlK0dOlS9e/fX82bN9fcuXNzdFyGYahXr14KCgrSZ599ppo1a8rX11ft2rXTf//7X23fvl1Tpkwx+w8ZMkTDhw/Xo48+mqP9ODs7y8fHR76+vurfv7/Cw8O1cuVKSTdnplu1aqXx48erePHiKleunKSbM/3t27eXl5eXChYsqJYtWyoxMVGStG7dOrm4uGSa+R48eLAaNmwoKevLtr/88ktVrVpVLi4uKlOmjMaOHWvOgA8bNkwtWrQw+06dOlU2m01ff/212ebv76+PPvooR8cOAAAAANnxtw/P58+f19q1azVgwADly5fPbpmPj4+ioqK0dOlSGYZhtr/99tuqXLmy9uzZo+HDh2vw4MGKiYkxl7dr105nz57VmjVrtHv3blWtWlWNGjWym8E+cuSIvvjiC61atUqrVq3Spk2bNHHiRLv9f/rppypfvrzKlSunp59+Wh9//LFdHVbi4uIUHx+vF154QXny2H9UlStXVnh4uBYvXpzt7WVXvnz57GaYN2zYoAMHDigmJkarVq3SH3/8oYiICLm7u2vLli2KjY2Vm5ubmjRpohs3bqhRo0by8vLSihUrzG2kpaVp6dKlioqKynKfW7ZsUdeuXTV48GDFx8frgw8+0Ny5czV+/HhJUr169bR161alpaVJkjZt2iRvb29t3LhRkvTrr7/qyJEjql+/fpbbv379upKSkuxeAAAAAJBdf/vwfOjQIRmGoaCgoCyXBwUF6cKFC/rtt9/Mtjp16mj48OEKDAzUc889p7Zt25ozuFu3btXOnTu1bNkyVa9eXQEBAXrnnXfk5eWl5cuXm9tIT0/X3LlzFRISoscff1xdunTRhg0b7PYdHR2tp59+WtLNS6MvXbqkTZs2ZfvYMu4Jvtux3c/7hg3D0Pr167V27VpzhliSXF1d9dFHHyk4OFjBwcFaunSp0tPT9dFHH6lixYoKCgrSnDlzdPz4cW3cuFEODg7q2LGjFi1aZG5jw4YNunjxotq0aZPlvseOHavhw4erW7duKlOmjBo3bqxx48bpgw8+kCQ9/vjjSk5O1p49e2QYhjZv3qyhQ4ea4Xnjxo0qUaKE/P39s9z+hAkT5Onpab5Klix5n0YNAAAAwL+BY24XcL/kZEY3LCws0/upU6dKkvbu3auUlBQVKlTIrs/Vq1d15MgR872fn5/c3d3N98WKFdPZs2fN9wcOHNDOnTv1+eefS5IcHR3VoUMHRUdH33F29E5ycmz3YtWqVXJzc9Mff/yh9PR0de7cWWPGjDGXV6xYUU5OTub7vXv36vDhw3bHL0nXrl0zxygqKkqPPvqoTp48qeLFi2vhwoVq3rz5HZ+wvXfvXsXGxpozzdLN2epr167pypUr8vLyUuXKlbVx40Y5OTnJyclJffr00ejRo5WSkqJNmzapXr16dzzGESNG6IUXXjDfJyUlEaABAAAAZNvfPjz7+/vLZrMpISFBrVu3zrQ8ISFBBQoUUOHChbO1vZSUFBUrVsyc0bzVrcEvb968dstsNpvS09PN99HR0UpNTVXx4sXNNsMw5OzsrBkzZsjT09OylsDAQPMYQkNDMy1PSEgw+/wZDRo00KxZs+Tk5KTixYvL0dH+tHB1dbV7n5KSomrVqmnhwoWZtpUxzjVq1FDZsmW1ZMkS9e/fX59//vld7/lOSUnR2LFj9dRTT2Va5uLiIkmqX7++Nm7cKGdnZ9WrV08FCxZUUFCQtm7dqk2bNmno0KF33L6zs7OcnZ3vuBwAAAAA7uZvH54LFSqkxo0b6/3339fzzz9vd9/z6dOntXDhQnXt2lU2m81s37Fjh902duzYYV4aXbVqVZ0+fVqOjo7y8/O7p5pSU1M1f/58vfvuu3riiSfslrVq1UqLFy9Wv379LLdTpUoVlS9fXlOmTFHHjh3t7nveu3ev1q9frwkTJtxTjbdydXW94+XOWalataqWLl2qIkWKyMPD4479oqKitHDhQj3yyCPKkydPll/Xdes2Dxw4cNc66tWrp48//liOjo5q0qSJpJuBevHixTp48GCOZ/QBAAAAILv+9vc8S9KMGTN0/fp1RUREaPPmzTpx4oS+/vprNW7cWCVKlLC7FFiSYmNj9dZbb+ngwYOaOXOmli1bpsGDB0uSwsPDFRYWplatWmndunVKTEzUtm3b9Oqrr2rXrl3ZqmfVqlW6cOGCevXqpZCQELtXmzZtFB0dna3t2Gw2RUdHKz4+Xm3atNHOnTt1/PhxLVu2TJGRkQoLC9OQIUPM/qdPn1ZcXJwOHz4sSdq3b5/i4uLu+1d1RUVFydvbWy1bttSWLVt07Ngxbdy4UYMGDdL//vc/u34//PCDxo8fr7Zt29515nfUqFGaP3++xo4dq/379yshIUFLlizRa6+9ZvapW7eukpOTtWrVKjMo169fXwsXLlSxYsXuyyw8AAAAAGTlHxGeAwICtGvXLpUpU0bt27dX2bJl1adPHzVo0EDbt29XwYIF7foPHTpUu3btUmhoqN544w1NnjxZERERkm4G1tWrV6tu3brq0aOHAgMD1bFjR/3yyy8qWrRotuqJjo5WeHh4lpdmt2nTRrt27dKPP/6YrW3Vrl1bO3bskIODg5o2bSp/f3+NGDFC3bp1U0xMjF0gnT17tkJDQ9W7d29JN8NmaGio+bVT90v+/Pm1efNmlSpVSk899ZSCgoLUq1cvXbt2zW4m2t/fXzVr1tSPP/54x6dsZ4iIiNCqVau0bt061ahRQ48++qimTJkiX19fs0+BAgVUsWJFFS5cWOXLlzePMT09/a73OwMAAADAn2UzHvTTqP5i/Pz8NGTIELsZW/z7JCUlydPTU6M3H5WLm7v1CsiW4aHeuV0CAAAAkCMZ2eDSpUt3vS31HzHzDAAAAADAg0R4BgAAAADAwt/+ads5lZiYmNslAAAAAAD+Zph5BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALjrldAJCbXqhcSB4eHrldBgAAAIC/OGaeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMCCY24XAOSmyXvPycXtRm6XAQAAAPxrDA/1zu0S7gkzzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAICFf1V49vPz09SpU3O7jFw1ZswYValSJbfLAAAAAIC/lYcenn/77Tf1799fpUqVkrOzs3x8fBQREaHY2NiHXco92bhxo2w2m4KDg5WWlma3zMvLS3Pnzs2dwv6/xMRE2Ww2xcXF5Wod92rhwoWqXLmy8ufPr2LFiqlnz546d+6cuXzMmDGy2Wzmy9PTU48//rg2bdqUi1UDAAAA+Kd76OG5TZs22rNnj+bNm6eDBw9q5cqVql+/vl1A+js4evSo5s+fn9tl/KPExsaqa9eu6tWrl/bv369ly5Zp586d6t27t12/4OBgnTp1SqdOndL27dsVEBCgFi1a6NKlS7lUOQAAAIB/uocani9evKgtW7Zo0qRJatCggXx9fVWzZk2NGDFCTz75pNlv8uTJqlixolxdXVWyZEkNGDBAKSkp5vK5c+fKy8tLq1atUrly5ZQ/f361bdtWV65c0bx58+Tn56cCBQpo0KBBmWaHk5OT1alTJ7m6uqpEiRKaOXOm3XKrfWd47rnnNHr0aF2/fv2Ox3v8+HG1bNlSbm5u8vDwUPv27XXmzBlJ0sGDB2Wz2fTzzz/brTNlyhSVLVtWkpSWlqZevXqpdOnSypcvn8qVK6dp06Zlc7Sz5/vvv1fjxo3l7e0tT09P1atXTz/88INdH5vNpg8++EAtWrRQ/vz5FRQUpO3bt+vw4cOqX7++XF1dVbt2bR05csRc58iRI2rZsqWKFi0qNzc31ahRQ+vXr79rLdu3b5efn58GDRqk0qVL67HHHlPfvn21c+dOu36Ojo7y8fGRj4+PKlSooNdff10pKSk6ePDg/RsYAAAAALjFQw3Pbm5ucnNz0xdffHHX0JknTx6999572r9/v+bNm6dvvvlGL730kl2fK1eu6L333tOSJUv09ddfa+PGjWrdurVWr16t1atXa8GCBfrggw+0fPlyu/XefvttVa5cWXv27NHw4cM1ePBgxcTE5GjfkjRkyBClpqZq+vTpWR5Denq6WrZsqfPnz2vTpk2KiYnR0aNH1aFDB0lSYGCgqlevroULF9qtt3DhQnXu3NncxiOPPKJly5YpPj5eo0aN0iuvvKJPP/30LqOcM8nJyerWrZu2bt2qHTt2KCAgQM2aNVNycrJdv3Hjxqlr166Ki4tT+fLl1blzZ/Xt21cjRozQrl27ZBiGBg4caPZPSUlRs2bNtGHDBu3Zs0dNmjRRZGSkjh8/fsdawsLCdOLECa1evVqGYejMmTNavny5mjVrdsd1rl+/rjlz5sjLy0vlypW7a7+kpCS7FwAAAABkl80wDONh7nDFihXq3bu3rl69qqpVq6pevXrq2LGjKlWqdMd1li9frn79+un333+XdHPmuUePHjp8+LA5S9uvXz8tWLBAZ86ckZubmySpSZMm8vPz0+zZsyXdfGBYUFCQ1qxZY267Y8eOSkpK0urVq7O1740bN6pBgwa6cOGCli5dqldeeUVHjx6Vp6envLy8NHXqVHXv3l0xMTFq2rSpjh07ppIlS0qS4uPjFRwcrJ07d6pGjRqaOnWqZsyYocOHD0u6ORtdrlw5JSQkqHz58lnWM3DgQJ0+fTrTHwUyJCYmqnTp0tqzZ0+WDwYbM2aMvvjiizveE52eni4vLy8tWrRILVq0kHRz5vm1117TuHHjJEk7duxQWFiYoqOj1bNnT0nSkiVL1KNHD129ejXL7UpSSEiI+vXrZxeyb7ds2TL17NlT165dU2pqqiIjI7VixQrlzZvXrH/cuHHKly+fpJt/RHF3d9fSpUvVpEmTO253zJgxGjt2bKb20ZuPysXN/Y7rAQAAALi/hod653YJdpKSkuTp6alLly7Jw8Pjjv1y5Z7nkydPauXKlWrSpIk2btyoqlWr2j1oa/369WrUqJFKlCghd3d3denSRefOndOVK1fMPvnz5zeDsyQVLVpUfn5+ZnDOaDt79qzd/sPCwjK9T0hIyNG+M/Tq1UuFChXSpEmTMi1LSEhQyZIlzeAsSRUqVJCXl5e5v44dOyoxMVE7duyQdHPWuWrVqnbBeebMmapWrZoKFy4sNzc3ffjhh3edvc2pM2fOqHfv3goICJCnp6c8PDyUkpKSaR+3/nGjaNGikqSKFSvatV27ds2c0U1JSdGwYcMUFBQkLy8vubm5KSEh4a61x8fHa/DgwRo1apR2796tr7/+WomJierXr59dv3LlyikuLk5xcXHavXu3+vfvr3bt2mnXrl133PaIESN06dIl83XixInsDxIAAACAf71c+aoqFxcXNW7cWCNHjtS2bdvUvXt3jR49WtLNmdMWLVqoUqVKWrFihXbv3m3el3zjxg1zGxkzkRlsNluWbenp6dmuK7v7zuDo6Kjx48dr2rRpOnnyZLb3k8HHx0cNGzbUokWLJEmLFi1SVFSUuXzJkiUaNmyYevXqpXXr1ikuLk49evTIspZ71a1bN8XFxWnatGnatm2b4uLiVKhQoUz7uHVsbTbbHdsyxnvYsGH6/PPP9eabb2rLli2Ki4tTxYoV71r7hAkTVKdOHb344ouqVKmSIiIi9P777+vjjz/WqVOnzH5OTk7y9/eXv7+/QkNDNXHiRJUoUeKuX0Pm7OwsDw8PuxcAAAAAZNdf4nueK1SooMuXL0uSdu/erfT0dL377rt69NFHFRgYeE/B9E4yZnlvfR8UFHTP+27Xrp2Cg4MzXRIcFBSkEydO2M1wxsfH6+LFi6pQoYLZFhUVpaVLl2r79u06evSoOnbsaC6LjY1V7dq1NWDAAIWGhsrf39/uoVz3Q2xsrAYNGqRmzZopODhYzs7O5iXqf3a73bt3V+vWrVWxYkX5+PgoMTHxrutcuXJFefLYn5IODg6SJKu7CxwcHO56yTgAAAAA/BmOD3Nn586dU7t27dSzZ09VqlRJ7u7u2rVrl9566y21bNlSkuTv768//vhD06dPV2RkpGJjY817lu+H2NhYvfXWW2rVqpViYmK0bNkyffXVV39q3xMnTlRERIRdW3h4uCpWrKioqChNnTpVqampGjBggOrVq6fq1aub/Z566in1799f/fv3V4MGDVS8eHFzWUBAgObPn6+1a9eqdOnSWrBggb7//nuVLl3asqYDBw5kagsODs7UFhAQoAULFqh69epKSkrSiy++aN5P/GcEBATos88+U2RkpGw2m0aOHGl5FUBkZKR69+6tWbNmKSIiQqdOndKQIUNUs2ZNu3FJTU3V6dOnJd184NnSpUsVHx+vl19++U/XDQAAAABZeehP265Vq5amTJmiunXrKiQkRCNHjlTv3r01Y8YMSVLlypU1efJkTZo0SSEhIVq4cKEmTJhw32oYOnSodu3apdDQUL3xxhuaPHmyGXzvdd8NGzZUw4YNlZqaarbZbDZ9+eWXKlCggOrWravw8HCVKVNGS5cutVvX3d1dkZGR2rt3r90l25LUt29fPfXUU+rQoYNq1aqlc+fOacCAAdk6zo4dOyo0NNTulfE1WbeKjo7WhQsXVLVqVXXp0kWDBg1SkSJFsrWPu5k8ebIKFCig2rVrKzIyUhEREapatepd1+nevbsmT56sGTNmKCQkRO3atVO5cuX02Wef2fXbv3+/ihUrpmLFiqlKlSr69NNPNWvWLHXt2vVP1w0AAAAAWXnoT9sG/goynqjH07YBAACAh4unbQMAAAAA8A9FeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwIJjbhcA5KYXKheSh4dHbpcBAAAA4C+OmWcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACw45nYBQG6avPecXNxu5HYZAPC3NzzUO7dLAADggWLmGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALBAeAYAAAAAwALhGQAAAAAAC4RnAAAAAAAsEJ4BAAAAALDwjwrPfn5+mjp1am6XkavGjBmjKlWq5HYZAAAAAPCPct/D82+//ab+/furVKlScnZ2lo+PjyIiIhQbG3u/d/VAbNy4UTabTcHBwUpLS7Nb5uXlpblz5+ZOYf9fYmKibDab4uLicrWOe9G9e3fZbLZMr+DgYLt+M2fOlJ+fn1xcXFSrVi3t3LnTbrmfn5+5roODg4oXL65evXrpwoULD/NwAAAAAPyL3Pfw3KZNG+3Zs0fz5s3TwYMHtXLlStWvX1/nzp2737t6oI4ePar58+fndhn/KNOmTdOpU6fM14kTJ1SwYEG1a9fO7LN06VK98MILGj16tH744QdVrlxZEREROnv2rN22Xn/9dZ06dUrHjx/XwoULtXnzZg0aNOhhHxIAAACAf4n7Gp4vXryoLVu2aNKkSWrQoIF8fX1Vs2ZNjRgxQk8++aTZb/LkyapYsaJcXV1VsmRJDRgwQCkpKebyuXPnysvLS6tWrVK5cuWUP39+tW3bVleuXNG8efPk5+enAgUKaNCgQZlmh5OTk9WpUye5urqqRIkSmjlzpt1yq31neO655zR69Ghdv379jsd7/PhxtWzZUm5ubvLw8FD79u115swZSdLBgwdls9n0888/260zZcoUlS1bVpKUlpamXr16qXTp0sqXL5/KlSunadOmZXO0s+f7779X48aN5e3tLU9PT9WrV08//PCDXR+bzaYPPvhALVq0UP78+RUUFKTt27fr8OHDql+/vlxdXVW7dm0dOXLEXOfIkSNq2bKlihYtKjc3N9WoUUPr16+/ay2enp7y8fExX7t27dKFCxfUo0cPs8/kyZPVu3dv9ejRQxUqVNDs2bOVP39+ffzxx3bbcnd3l4+Pj0qUKKEGDRqoW7dumY4LAAAAAO6X+xqe3dzc5Obmpi+++OKuoTNPnjx67733tH//fs2bN0/ffPONXnrpJbs+V65c0XvvvaclS5bo66+/1saNG9W6dWutXr1aq1ev1oIFC/TBBx9o+fLlduu9/fbbqly5svbs2aPhw4dr8ODBiomJydG+JWnIkCFKTU3V9OnTszyG9PR0tWzZUufPn9emTZsUExOjo0ePqkOHDpKkwMBAVa9eXQsXLrRbb+HChercubO5jUceeUTLli1TfHy8Ro0apVdeeUWffvrpXUY5Z5KTk9WtWzdt3bpVO3bsUEBAgJo1a6bk5GS7fuPGjVPXrl0VFxen8uXLq3Pnzurbt69GjBihXbt2yTAMDRw40OyfkpKiZs2aacOGDdqzZ4+aNGmiyMhIHT9+PNu1RUdHKzw8XL6+vpKkGzduaPfu3QoPDzf75MmTR+Hh4dq+ffsdt/Prr7/qv//9r2rVqnXHPtevX1dSUpLdCwAAAACyy2YYhnE/N7hixQr17t1bV69eVdWqVVWvXj117NhRlSpVuuM6y5cvV79+/fT7779Lujnz3KNHDx0+fNicpe3Xr58WLFigM2fOyM3NTZLUpEkT+fn5afbs2ZJu3gsbFBSkNWvWmNvu2LGjkpKStHr16mzte+PGjWrQoIEuXLigpUuX6pVXXtHRo0fl6ekpLy8vTZ06Vd27d1dMTIyaNm2qY8eOqWTJkpKk+Ph4BQcHa+fOnapRo4amTp2qGTNm6PDhw5JuzkaXK1dOCQkJKl++fJb1DBw4UKdPn870R4EMiYmJKl26tPbs2ZPlg8HGjBmjL7744o73RKenp8vLy0uLFi1SixYtJN2ceX7ttdc0btw4SdKOHTsUFham6Oho9ezZU5K0ZMkS9ejRQ1evXs1yu5IUEhKifv362YXsOzl58qRKlSqlRYsWqX379mZbiRIltG3bNoWFhZl9X3rpJW3atEnfffedpJuf86lTp5Q3b16lpaXp2rVrqlWrlr7++mt5eXllub8xY8Zo7NixmdpHbz4qFzd3y3oBAHc3PNQ7t0sAAOCeJCUlydPTU5cuXZKHh8cd+z2Qe55PnjyplStXqkmTJtq4caOqVq1q96Ct9evXq1GjRipRooTc3d3VpUsXnTt3TleuXDH75M+f3wzOklS0aFH5+fmZwTmj7fZ7YW8NXRnvExIScrTvDL169VKhQoU0adKkTMsSEhJUsmRJMzhLUoUKFeTl5WXur2PHjkpMTNSOHTsk3Zx1rlq1ql1wnjlzpqpVq6bChQvLzc1NH374YY5mb62cOXNGvXv3VkBAgDw9PeXh4aGUlJRM+7j1jxtFixaVJFWsWNGu7dq1a+aMbUpKioYNG6agoCB5eXnJzc1NCQkJ2a593rx58vLyUqtWre7puF588UXFxcXpxx9/1IYNGyRJzZs3z3QZf4YRI0bo0qVL5uvEiRP3tF8AAAAA/04P5KuqXFxc1LhxY40cOVLbtm1T9+7dNXr0aEk3Z05btGihSpUqacWKFdq9e7d5X/KNGzfMbeTNm9dumzabLcu29PT0bNeV3X1ncHR01Pjx4zVt2jSdPHky2/vJ4OPjo4YNG2rRokWSpEWLFikqKspcvmTJEg0bNky9evXSunXrFBcXpx49emRZy73q1q2b4uLiNG3aNG3btk1xcXEqVKhQpn3cOrY2m+2ObRnjPWzYMH3++ed68803tWXLFsXFxalixYrZqt0wDH388cfq0qWLnJyczHZvb285ODiY941nOHPmjHx8fOzavL295e/vr4CAADVs2FBTp07Vtm3b9O2332a5T2dnZ3l4eNi9AAAAACC7Hsr3PFeoUEGXL1+WJO3evVvp6el699139eijjyowMPCegumdZMzy3vo+KCjonvfdrl07BQcHZ7rkNygoSCdOnLCbwYyPj9fFixdVoUIFsy0qKkpLly7V9u3bdfToUXXs2NFcFhsbq9q1a2vAgAEKDQ2Vv7+/3UO57ofY2FgNGjRIzZo1U3BwsJydnc1L1P/sdrt3767WrVurYsWK8vHxUWJiYrbW3bRpkw4fPqxevXrZtTs5OalatWrmTLJ0M6xv2LAh0xUFt3NwcJCku15WDgAAAAD3yvF+buzcuXNq166devbsqUqVKsnd3V27du3SW2+9pZYtW0qS/P399ccff2j69OmKjIxUbGysec/y/RAbG6u33npLrVq1UkxMjJYtW6avvvrqT+174sSJioiIsGsLDw9XxYoVFRUVpalTpyo1NVUDBgxQvXr1VL16dbPfU089pf79+6t///5q0KCBihcvbi4LCAjQ/PnztXbtWpUuXVoLFizQ999/r9KlS1vWdODAgUxtt39fcsY+FixYoOrVqyspKUkvvvii8uXLZ7l9KwEBAfrss88UGRkpm82mkSNHZvsqgOjoaNWqVUshISGZlr3wwgvq1q2bqlevrpo1a2rq1Km6fPmy3RO5pZsPQjt9+rQMw9CJEyf00ksvqXDhwqpdu/afPjYAAAAAuN19f9p2rVq1NGXKFNWtW1chISEaOXKkevfurRkzZkiSKleurMmTJ2vSpEkKCQnRwoULNWHChPtWw9ChQ7Vr1y6FhobqjTfe0OTJk83ge6/7btiwoRo2bKjU1FSzzWaz6csvv1SBAgVUt25dhYeHq0yZMlq6dKnduu7u7oqMjNTevXvtLtmWpL59++qpp55Shw4dVKtWLZ07d04DBgzI1nF27NhRoaGhdq/bL3eWbgbVCxcuqGrVqurSpYsGDRqkIkWKZGsfdzN58mQVKFBAtWvXVmRkpCIiIlS1alXL9S5duqQVK1ZkmnXO0KFDB73zzjsaNWqUqlSpori4OH399dfmfdgZRo0apWLFiql48eJq0aKFXF1dtW7dOhUqVOhPHxsAAAAA3O6+P20b+DvIeKIeT9sGgPuDp20DAP6ucu1p2wAAAAAA/NMQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsEB4BgAAAADAAuEZAAAAAAALhGcAAAAAACwQngEAAAAAsOCY2wUAuemFyoXk4eGR22UAAAAA+Itj5hkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALBCeAQAAAACwQHgGAAAAAMAC4RkAAAAAAAuEZwAAAAAALDjmdgFAbpq895xc3G7kdhn/GsNDvXO7BAAAAOCeMPMMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWPjbhGc/Pz9NnTo1t8vIVWPGjFGVKlVyuwwAAAAA+NfJUXj+7bff1L9/f5UqVUrOzs7y8fFRRESEYmNjH1R999XGjRtls9kUHBystLQ0u2VeXl6aO3du7hT2/yUmJspmsykuLi5X6/izYmNj5ejomGXQnzlzpvz8/OTi4qJatWpp586ddsvr168vm81m9+rXr5+5PGOMMl5OTk7y9/fXG2+8IcMwHvShAQAAAPiXcsxJ5zZt2ujGjRuaN2+eypQpozNnzmjDhg06d+7cg6rvgTh69Kjmz5+vHj165HYp/zgXL15U165d1ahRI505c8Zu2dKlS/XCCy9o9uzZqlWrlqZOnaqIiAgdOHBARYoUMfv17t1br7/+uvk+f/78mfazfv16BQcH6/r169q6daueeeYZFStWTL169XpwBwcAAADgXyvbM88XL17Uli1bNGnSJDVo0EC+vr6qWbOmRowYoSeffNLsN3nyZFWsWFGurq4qWbKkBgwYoJSUFHP53Llz5eXlpVWrVqlcuXLKnz+/2rZtqytXrmjevHny8/NTgQIFNGjQoEyzw8nJyerUqZNcXV1VokQJzZw502651b4zPPfccxo9erSuX79+x+M9fvy4WrZsKTc3N3l4eKh9+/ZmGDx48KBsNpt+/vlnu3WmTJmismXLSpLS0tLUq1cvlS5dWvny5VO5cuU0bdq0bI529nz//fdq3LixvL295enpqXr16umHH36w62Oz2fTBBx+oRYsWyp8/v4KCgrR9+3YdPnxY9evXl6urq2rXrq0jR46Y6xw5ckQtW7ZU0aJF5ebmpho1amj9+vXZqqlfv37q3LmzwsLCMi2bPHmyevfurR49eqhChQqaPXu28ufPr48//tiuX/78+eXj42O+PDw8Mm2rUKFC8vHxka+vr6KiolSnTp1Mxw4AAAAA90u2w7Obm5vc3Nz0xRdf3DV05smTR++9957279+vefPm6ZtvvtFLL71k1+fKlSt67733tGTJEn399dfauHGjWrdurdWrV2v16tVasGCBPvjgAy1fvtxuvbfffluVK1fWnj17NHz4cA0ePFgxMTE52rckDRkyRKmpqZo+fXqWx5Cenq6WLVvq/Pnz2rRpk2JiYnT06FF16NBBkhQYGKjq1atr4cKFdustXLhQnTt3NrfxyCOPaNmyZYqPj9eoUaP0yiuv6NNPP73LKOdMcnKyunXrpq1bt2rHjh0KCAhQs2bNlJycbNdv3Lhx6tq1q+Li4lS+fHl17txZffv21YgRI7Rr1y4ZhqGBAwea/VNSUtSsWTNt2LBBe/bsUZMmTRQZGanjx4/ftZ45c+bo6NGjGj16dKZlN27c0O7duxUeHm625cmTR+Hh4dq+fbtd34ULF8rb21shISEaMWKErly5ctf97tq1S7t371atWrXu2Of69etKSkqyewEAAABAdmX7sm1HR0fNnTtXvXv31uzZs1W1alXVq1dPHTt2VKVKlcx+Q4YMMf/bz89Pb7zxhvr166f333/fbP/jjz80a9Ysc5a2bdu2WrBggc6cOSM3NzdVqFBBDRo00LfffmsGVkmqU6eOhg8fLulmgI2NjdWUKVPUuHHjbO9bujmzOXr0aL3yyivq3bu3PD097ZZv2LBB+/bt07Fjx1SyZElJ0vz58xUcHKzvv/9eNWrUUFRUlGbMmKFx48ZJujkbvXv3bn3yySeSpLx582rs2LHmNkuXLq3t27fr008/Vfv27bM77HfVsGFDu/cffvihvLy8tGnTJrVo0cJs79Gjh7nPl19+WWFhYRo5cqQiIiIkSYMHD7a7hL1y5cqqXLmy+X7cuHH6/PPPtXLlSruQfatDhw5p+PDh2rJlixwdM59Wv//+u9LS0lS0aFG79qJFi9rN4Hfu3Fm+vr4qXry4fvzxR7388ss6cOCAPvvsM7v1ateurTx58ujGjRv6448/1KdPH3Xt2vWOYzVhwgS7zwMAAAAAciJHDwxr06aNTp48qZUrV6pJkybauHGjqlatavegrfXr16tRo0YqUaKE3N3d1aVLF507d85u9jB//vxmcJZuBig/Pz+5ubnZtZ09e9Zu/7dfChwWFqaEhIQc7TtDr169VKhQIU2aNCnTsoSEBJUsWdIMzpJUoUIFeXl5mfvr2LGjEhMTtWPHDkk3Z0urVq2q8uXLm+vMnDlT1apVU+HCheXm5qYPP/zQcvY2J86cOaPevXsrICBAnp6e8vDwUEpKSqZ93PrHjYzwWrFiRbu2a9eumbOxKSkpGjZsmIKCguTl5SU3NzclJCTcsfa0tDR17txZY8eOVWBg4J86pj59+igiIkIVK1ZUVFSU5s+fr88//9zusnLp5v3TcXFx2rt3rz799FN9+eWX5h9WsjJixAhdunTJfJ04ceJP1QkAAADg3yXHX1Xl4uKixo0ba+TIkdq2bZu6d+9uXqabmJioFi1aqFKlSlqxYoV2795t3pd848YNcxt58+a126bNZsuyLT09Pdt1ZXffGRwdHTV+/HhNmzZNJ0+ezPZ+Mvj4+Khhw4ZatGiRJGnRokWKiooyly9ZskTDhg1Tr169tG7dOsXFxalHjx5Z1nKvunXrpri4OE2bNk3btm1TXFycChUqlGkft46tzWa7Y1vGeA8bNkyff/653nzzTW3ZskVxcXGqWLHiHWtPTk7Wrl27NHDgQDk6OsrR0VGvv/669u7dK0dHR33zzTfy9vaWg4NDpoeInTlzRj4+Pnc8xoxLsQ8fPmzXXrJkSfn7+ysoKEjt2rXTkCFD9O677+ratWtZbsfZ2VkeHh52LwAAAADIrj/9Pc8VKlTQ5cuXJUm7d+9Wenq63n33XT366KMKDAy8p2B6JxmzvLe+DwoKuud9t2vXTsHBwZku5w0KCtKJEyfsZifj4+N18eJFVahQwWyLiorS0qVLtX37dh09elQdO3Y0l8XGxqp27doaMGCAQkND5e/vn2n29M+KjY3VoEGD1KxZMwUHB8vZ2Vm///77fdlu9+7d1bp1a1WsWFE+Pj5KTEy8Y38PDw/t27dPcXFx5qtfv34qV66c4uLiVKtWLTk5OalatWrasGGDuV56ero2bNiQ5cPFMmR8bVexYsXuWrODg4NSU1Pv6x8nAAAAACBDtu95PnfunNq1a6eePXuqUqVKcnd3165du/TWW2+pZcuWkiR/f3/98ccfmj59uiIjIxUbG6vZs2fft2JjY2P11ltvqVWrVoqJidGyZcv01Vdf/al9T5w40bz3N0N4eLh52fDUqVOVmpqqAQMGqF69eqpevbrZ76mnnlL//v3Vv39/NWjQQMWLFzeXBQQEaP78+Vq7dq1Kly6tBQsW6Pvvv1fp0qUtazpw4ECmtuDg4ExtAQEBWrBggapXr66kpCS9+OKLypcvn+X2rQQEBOizzz5TZGSkbDabRo4cederAPLkyaOQkBC7tiJFisjFxcWu/YUXXlC3bt1UvXp11axZU1OnTtXly5fN+62PHDmiRYsWqVmzZipUqJB+/PFHPf/886pbt67dpefSzfPx9OnTSk1N1b59+zRt2jQ1aNCAGWUAAAAAD0SOnrZdq1YtTZkyRXXr1lVISIhGjhyp3r17a8aMGZJuPmhq8uTJmjRpkkJCQrRw4UJNmDDhvhU7dOhQ7dq1S6GhoXrjjTc0efJkM/je674bNmyohg0bKjU11Wyz2Wz68ssvVaBAAdWtW1fh4eEqU6aMli5dareuu7u7IiMjtXfvXrtLtiWpb9++euqpp9ShQwfVqlVL586d04ABA7J1nB07dlRoaKjd6/bLnSUpOjpaFy5cUNWqVdWlSxcNGjTI7vuS79XkyZNVoEAB1a5dW5GRkYqIiFDVqlX/9HY7dOigd955R6NGjVKVKlUUFxenr7/+2rwP28nJSevXr9cTTzyh8uXLa+jQoWrTpo3++9//ZtpWeHi4ihUrJj8/P/Xp00fNmjXL9PkAAAAAwP1iMwzDyO0igIctKSlJnp6eGr35qFzc3HO7nH+N4aHeuV0CAAAAYCcjG1y6dOmuV7L+6XueAQAAAAD4pyM8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABgwTG3CwBy0wuVC8nDwyO3ywAAAADwF8fMMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGCB8AwAAAAAgAXCMwAAAAAAFgjPAAAAAABYIDwDAAAAAGDBMbcLAHKDYRiSpKSkpFyuBAAAAEBuysgEGRnhTgjP+Fc6d+6cJKlkyZK5XAkAAACAv4Lk5GR5enrecTnhGf9KBQsWlCQdP378rj8g+POSkpJUsmRJnThxQh4eHrldzj8e4/3wMNYPF+P98DDWDxfj/fAw1g/X32m8DcNQcnKyihcvftd+hGf8K+XJc/N2f09Pz7/8D/M/hYeHB2P9EDHeDw9j/XAx3g8PY/1wMd4PD2P9cP1dxjs7E2o8MAwAAAAAAAuEZwAAAAAALBCe8a/k7Oys0aNHy9nZObdL+cdjrB8uxvvhYawfLsb74WGsHy7G++FhrB+uf+J42wyr53EDAAAAAPAvx8wzAAAAAAAWCM8AAAAAAFggPAMAAAAAYIHwDAAAAACABcIz/nVmzpwpPz8/ubi4qFatWtq5c2dul/S3tHnzZkVGRqp48eKy2Wz64osv7JYbhqFRo0apWLFiypcvn8LDw3Xo0CG7PufPn1dUVJQ8PDzk5eWlXr16KSUl5SEexd/DhAkTVKNGDbm7u6tIkSJq1aqVDhw4YNfn2rVrevbZZ1WoUCG5ubmpTZs2OnPmjF2f48ePq3nz5sqfP7+KFCmiF198UampqQ/zUP7yZs2apUqVKsnDw0MeHh4KCwvTmjVrzOWM84MzceJE2Ww2DRkyxGxjvO+fMWPGyGaz2b3Kly9vLmes779ff/1VTz/9tAoVKqR8+fKpYsWK2rVrl7mcfyfvDz8/v0znts1m07PPPiuJc/t+S0tL08iRI1W6dGnly5dPZcuW1bhx43TrM6j/0ee2AfyLLFmyxHBycjI+/vhjY//+/Ubv3r0NLy8v48yZM7ld2t/O6tWrjVdffdX47LPPDEnG559/brd84sSJhqenp/HFF18Ye/fuNZ588kmjdOnSxtWrV80+TZo0MSpXrmzs2LHD2LJli+Hv72906tTpIR/JX19ERIQxZ84c46effjLi4uKMZs2aGaVKlTJSUlLMPv369TNKlixpbNiwwdi1a5fx6KOPGrVr1zaXp6amGiEhIUZ4eLixZ88eY/Xq1Ya3t7cxYsSI3Dikv6yVK1caX331lXHw4EHjwIEDxiuvvGLkzZvX+OmnnwzDYJwflJ07dxp+fn5GpUqVjMGDB5vtjPf9M3r0aCM4ONg4deqU+frtt9/M5Yz1/XX+/HnD19fX6N69u/Hdd98ZR48eNdauXWscPnzY7MO/k/fH2bNn7c7rmJgYQ5Lx7bffGobBuX2/jR8/3ihUqJCxatUq49ixY8ayZcsMNzc3Y9q0aWaff/K5TXjGv0rNmjWNZ5991nyflpZmFC9e3JgwYUIuVvX3d3t4Tk9PN3x8fIy3337bbLt48aLh7OxsLF682DAMw4iPjzckGd9//73ZZ82aNYbNZjN+/fXXh1b739HZs2cNScamTZsMw7g5tnnz5jWWLVtm9klISDAkGdu3bzcM4+YfO/LkyWOcPn3a7DNr1izDw8PDuH79+sM9gL+ZAgUKGB999BHj/IAkJycbAQEBRkxMjFGvXj0zPDPe99fo0aONypUrZ7mMsb7/Xn75ZeOxxx6743L+nXxwBg8ebJQtW9ZIT0/n3H4AmjdvbvTs2dOu7amnnjKioqIMw/jnn9tcto1/jRs3bmj37t0KDw832/LkyaPw8HBt3749Fyv75zl27JhOnz5tN9aenp6qVauWOdbbt2+Xl5eXqlevbvYJDw9Xnjx59N133z30mv9OLl26JEkqWLCgJGn37t36448/7Ma7fPnyKlWqlN14V6xYUUWLFjX7REREKCkpSfv373+I1f99pKWlacmSJbp8+bLCwsIY5wfk2WefVfPmze3GVeK8fhAOHTqk4sWLq0yZMoqKitLx48clMdYPwsqVK1W9enW1a9dORYoUUWhoqP7zn/+Yy/l38sG4ceOGPvnkE/Xs2VM2m41z+wGoXbu2NmzYoIMHD0qS9u7dq61bt6pp06aS/vnntmNuFwA8LL///rvS0tLsfjlKUtGiRfXzzz/nUlX/TKdPn5akLMc6Y9np06dVpEgRu+WOjo4qWLCg2QeZpaena8iQIapTp45CQkIk3RxLJycneXl52fW9fbyz+jwyluH/7Nu3T2FhYbp27Zrc3Nz0+eefq0KFCoqLi2Oc77MlS5bohx9+0Pfff59pGef1/VWrVi3NnTtX5cqV06lTpzR27Fg9/vjj+umnnxjrB+Do0aOaNWuWXnjhBb3yyiv6/vvvNWjQIDk5Oalbt278O/mAfPHFF7p48aK6d+8uid8jD8Lw4cOVlJSk8uXLy8HBQWlpaRo/fryioqIk/fP/PyDhGQD+Rp599ln99NNP2rp1a26X8o9Vrlw5xcXF6dKlS1q+fLm6deumTZs25XZZ/zgnTpzQ4MGDFRMTIxcXl9wu5x8vY1ZIkipVqqRatWrJ19dXn376qfLly5eLlf0zpaenq3r16nrzzTclSaGhofrpp580e/ZsdevWLZer++eKjo5W06ZNVbx48dwu5R/r008/1cKFC7Vo0SIFBwcrLi5OQ4YMUfHixf8V5zaXbeNfw9vbWw4ODpmesHjmzBn5+PjkUlX/TBnjebex9vHx0dmzZ+2Wp6am6vz583wedzBw4ECtWrVK3377rR555BGz3cfHRzdu3NDFixft+t8+3ll9HhnL8H+cnJzk7++vatWqacKECapcubKmTZvGON9nu3fv1tmzZ1W1alU5OjrK0dFRmzZt0nvvvSdHR0cVLVqU8X6AvLy8FBgYqMOHD3NuPwDFihVThQoV7NqCgoLMS+X5d/L+++WXX7R+/Xo988wzZhvn9v334osvavjw4erYsaMqVqyoLl266Pnnn9eECRMk/fPPbcIz/jWcnJxUrVo1bdiwwWxLT0/Xhg0bFBYWlouV/fOULl1aPj4+dmOdlJSk7777zhzrsLAwXbx4Ubt37zb7fPPNN0pPT1etWrUees1/ZYZhaODAgfr888/1zTffqHTp0nbLq1Wrprx589qN94EDB3T8+HG78d63b5/dP1YxMTHy8PDI9H/wYC89PV3Xr19nnO+zRo0aad++fYqLizNf1atXV1RUlPnfjPeDk5KSoiNHjqhYsWKc2w9AnTp1Mn2l4MGDB+Xr6yuJfycfhDlz5qhIkSJq3ry52ca5ff9duXJFefLYR0gHBwelp6dL+hec27n9xDLgYVqyZInh7OxszJ0714iPjzf69OljeHl52T1hEdmTnJxs7Nmzx9izZ48hyZg8ebKxZ88e45dffjEM4+bXFHh5eRlffvml8eOPPxotW7bM8msKQkNDje+++87YunWrERAQ8Lf4moKHrX///oanp6exceNGu6/juHLlitmnX79+RqlSpYxvvvnG2LVrlxEWFmaEhYWZyzO+iuOJJ54w4uLijK+//tooXLgwX8Vxm+HDhxubNm0yjh07Zvz444/G8OHDDZvNZqxbt84wDMb5Qbv1aduGwXjfT0OHDjU2btxoHDt2zIiNjTXCw8MNb29v4+zZs4ZhMNb3286dOw1HR0dj/PjxxqFDh4yFCxca+fPnNz755BOzD/9O3j9paWlGqVKljJdffjnTMs7t+6tbt25GiRIlzK+q+uyzzwxvb2/jpZdeMvv8k89twjP+daZPn26UKlXKcHJyMmrWrGns2LEjt0v6W/r2228NSZle3bp1Mwzj5lcVjBw50ihatKjh7OxsNGrUyDhw4IDdNs6dO2d06tTJcHNzMzw8PIwePXoYycnJuXA0f21ZjbMkY86cOWafq1evGgMGDDAKFChg5M+f32jdurVx6tQpu+0kJiYaTZs2NfLly2d4e3sbQ4cONf7444+HfDR/bT179jR8fX0NJycno3DhwkajRo3M4GwYjPODdnt4Zrzvnw4dOhjFihUznJycjBIlShgdOnSw+85hxvr+++9//2uEhIQYzs7ORvny5Y0PP/zQbjn/Tt4/a9euNSRlGj/D4Ny+35KSkozBgwcbpUqVMlxcXIwyZcoYr776qt3Xev2Tz22bYRhGrkx5AwAAAADwN8E9zwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAAAAAAWCA8AwAAAABggfAMAAAAAIAFwjMAAAAAABYIzwAA4J4kJibKZrMpLi4ut0tBDvHZAUDOEZ4BAPgXs9lsd32NGTMmt0v8S/v888/16KOPytPTU+7u7goODtaQIUNyuywAwAPgmNsFAACA3HPq1Cnzv5cuXapRo0bpwIEDZpubm1tulPWXkpaWJpvNpjx57OccNmzYoA4dOmj8+PF68sknZbPZFB8fr5iYmFyqFADwIDHzDADAv5iPj4/58vT0lM1mM98XKVJEkydP1iOPPCJnZ2dVqVJFX3/99R23lZaWpp49e6p8+fI6fvy4JOnLL79U1apV5eLiojJlymjs2LFKTU0117HZbProo4/UunVr5c+fXwEBAVq5cqW5/MKFC4qKilLhwoWVL18+BQQEaM6cOXesoX79+ho4cKAGDhwoT09PeXt7a+TIkTIMw+xz/fp1DRs2TCVKlJCrq6tq1aqljRs3msvnzp0rLy8vrVy5UhUqVJCzs7N5PLf673//qzp16ujFF19UuXLlFBgYqFatWmnmzJl2/azG4OLFi+rbt6+KFi0qFxcXhYSEaNWqVebyFStWKDg4WM7OzvLz89O7775rt30/Pz+9+eab6tmzp9zd3VWqVCl9+OGHdn127typ0NBQubi4qHr16tqzZ88dxxAAkDXCMwAAyNK0adP07rvv6p133tGPP/6oiIgIPfnkkzp06FCmvtevX1e7du0UFxenLVu2qFSpUtqyZYu6du2qwYMHKz4+Xh988IHmzp2r8ePH2607duxYtW/fXj/++KOaNWumqKgonT9/XpI0cuRIxcfHa82aNUpISNCsWbPk7e1917rnzZsnR0dH7dy5U9OmTdPkyZP10UcfmcsHDhyo7du3a8mSJfrxxx/Vrl07NWnSxO64rly5okmTJumjjz7S/v37VaRIkUz78fHx0f79+/XTTz/dsRarMUhPT1fTpk0VGxurTz75RPHx8Zo4caIcHBwkSbt371b79u3VsWNH7du3T2PGjNHIkSM1d+5cu/28++67ZigeMGCA+vfvb15BkJKSohYtWqhChQravXu3xowZo2HDht11DAEAWTAAAAAMw5gzZ47h6elpvi9evLgxfvx4uz41atQwBgwYYBiGYRw7dsyQZGzZssVo1KiR8dhjjxkXL140+zZq1Mh488037dZfsGCBUaxYMfO9JOO1114z36ekpBiSjDVr1hiGYRiRkZFGjx49sn0M9erVM4KCgoz09HSz7eWXXzaCgoIMwzCMX375xXBwcDB+/fVXu/UaNWpkjBgxwhwHSUZcXNxd95WSkmI0a9bMkGT4+voaHTp0MKKjo41r165lewzWrl1r5MmTxzhw4ECW++jcubPRuHFju7YXX3zRqFChgvne19fXePrpp8336enpRpEiRYxZs2YZhmEYH3zwgVGoUCHj6tWrZp9Zs2YZkow9e/bc9RgBAP+HmWcAAJBJUlKSTp48qTp16ti116lTRwkJCXZtnTp10uXLl7Vu3Tp5enqa7Xv37tXrr78uNzc389W7d2+dOnVKV65cMftVqlTJ/G9XV1d5eHjo7NmzkqT+/ftryZIlqlKlil566SVt27bNsvZHH31UNpvNfB8WFqZDhw4pLS1N+/btU1pamgIDA+3q2rRpk44cOWKu4+TkZFdXVlxdXfXVV1/p8OHDeu211+Tm5qahQ4eqZs2a5vFZjUFcXJweeeQRBQYGZrmPhISELD+DjOPJagwzLr3PGMOEhARVqlRJLi4udmMCAMgZHhgGAAD+lGbNmumTTz7R9u3b1bBhQ7M9JSVFY8eO1VNPPZVpnVuDXN68ee2W2Ww2paenS5KaNm2qX375RatXr1ZMTIwaNWqkZ599Vu+888491ZqSkiIHBwft3r3bvDQ6w60PR8uXL59dAL+bsmXLqmzZsnrmmWf06quvKjAwUEuXLlWPHj0sxyBfvnz3dBy3u9sYAgDuD8IzAADIxMPDQ8WLF1dsbKzq1atntsfGxqpmzZp2ffv376+QkBA9+eST+uqrr8z+VatW1YEDB+Tv7/+nailcuLC6deumbt266fHHH9eLL7541/D83Xff2b3fsWOHAgIC5ODgoNDQUKWlpens2bN6/PHH/1RdWfHz81P+/Pl1+fJlSdZjUKlSJf3vf//TwYMHs5x9DgoKUmxsrF1bbGysAgMDM4X/OwkKCtKCBQt07do1848WO3bsyMlhAQBEeAYAAHfw4osvavTo0SpbtqyqVKmiOXPmKC4uTgsXLszU97nnnlNaWppatGihNWvW6LHHHtOoUaPUokULlSpVSm3btlWePHm0d+9e/fTTT3rjjTeyVcOoUaNUrVo1BQcH6/r161q1apWCgoLuus7x48f1wgsvqG/fvvrhhx80ffp08wnVgYGBioqKUteuXfXuu+8qNDRUv/32mzZs2KBKlSqpefPm2R6fMWPG6MqVK2rWrJl8fX118eJFvffee/rjjz/UuHFjs/67jUG9evVUt25dtWnTRpMnT5a/v79+/vln2Ww2NWnSREOHDlWNGjU0btw4dejQQdu3b9eMGTP0/vvvZ7vOzp0769VXX1Xv3r01YsQIJSYm3vPMPQD8mxGeAQBAlgYNGqRLly5p6NChOnv2rCpUqKCVK1cqICAgy/5DhgxRenq6mjVrpq+//loRERFatWqVXn/9dU2aNEl58+ZV+fLl9cwzz2S7BicnJzPw5cuXT48//riWLFly13W6du2qq1evqmbNmnJwcNDgwYPVp08fc/mcOf+vvTvETSCKwjD612NIMHgSEhTjcLAAHJ4g8aARgAA3ZnQ9CQrHfhCsAkSTpu5R1bQ9ZwV3xn258968Z7/fZ7Va5Xa7pdPpZDQaZTqdvjxXkozH4zRNk/l8nvv9nna7naqqcr1e0+/3k+Sld3A+n7Nerz/Pjvd6vRwOhyQfm+vT6ZTNZpPdbpdut5vtdpvFYvHynK1WK5fLJcvlMlVVZTAY5Hg8Zjabfet5Af67t8fjy48PAQB+sclkkuFwmLquf3oUAP4Yt20DAABAgXgGAACAAp9tAwAAQIHNMwAAABSIZwAAACgQzwAAAFAgngEAAKBAPAMAAECBeAYAAIAC8QwAAAAF4hkAAAAKnmFNL0ho5cq8AAAAAElFTkSuQmCC",
+ "text/plain": [
+ "<Figure size 1000x600 with 1 Axes>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import time\n",
+ "import matplotlib.pyplot as plt\n",
+ "from camel.agents import ChatAgent\n",
+ "from camel.configs import SambaCloudAPIConfig, ChatGPTConfig\n",
+ "from camel.messages import BaseMessage\n",
+ "from camel.models import ModelFactory\n",
+ "from camel.types import ModelPlatformType, ModelType\n",
+ "\n",
+ "# Create model instances\n",
+ "def create_models():\n",
+ " model_configs = [\n",
+ " (ModelPlatformType.OPENAI, ModelType.GPT_4O_MINI, ChatGPTConfig(temperature=0.0, max_tokens=2000), \"OpenAI GPT-4O Mini\"),\n",
+ " (ModelPlatformType.OPENAI, ModelType.GPT_4O, ChatGPTConfig(temperature=0.0, max_tokens=2000), \"OpenAI GPT-4O\"),\n",
+ " (ModelPlatformType.OPENAI, ModelType.O1_PREVIEW, ChatGPTConfig(temperature=0.0), \"OpenAI O1 Preview\"),\n",
+ " (ModelPlatformType.SAMBA, \"Meta-Llama-3.1-8B-Instruct\", SambaCloudAPIConfig(temperature=0.0, max_tokens=2000), \"SambaNova Llama 8B\"),\n",
+ " (ModelPlatformType.SAMBA, \"Meta-Llama-3.1-70B-Instruct\", SambaCloudAPIConfig(temperature=0.0, max_tokens=2000), \"SambaNova Llama 70B\"),\n",
+ " (ModelPlatformType.SAMBA, \"Meta-Llama-3.1-405B-Instruct\", SambaCloudAPIConfig(temperature=0.0, max_tokens=2000), \"SambaNova Llama 405B\")\n",
+ " ]\n",
+ "\n",
+ " models = [(ModelFactory.create(model_platform=platform, model_type=model_type, model_config_dict=config.as_dict(), url=\"https://api.sambanova.ai/v1\" if platform == ModelPlatformType.SAMBA else None), name)\n",
+ " for platform, model_type, config, name in model_configs]\n",
+ " return models\n",
+ "\n",
+ "# Define messages\n",
+ "def create_messages():\n",
+ " sys_msg = BaseMessage.make_assistant_message(role_name=\"Assistant\", content=\"You are a helpful assistant.\")\n",
+ " user_msg = BaseMessage.make_user_message(role_name=\"User\", content=\"Tell me a long story.\")\n",
+ " return sys_msg, user_msg\n",
+ "\n",
+ "# Initialize ChatAgent instances\n",
+ "def initialize_agents(models, sys_msg):\n",
+ " return [(ChatAgent(system_message=sys_msg, model=model), name) for model, name in models]\n",
+ "\n",
+ "# Measure response time for a given agent\n",
+ "def measure_response_time(agent, message):\n",
+ " start_time = time.time()\n",
+ " response = agent.step(message)\n",
+ " end_time = time.time()\n",
+ " tokens_per_second = response.info['usage'][\"completion_tokens\"] / (end_time - start_time)\n",
+ " return tokens_per_second\n",
+ "\n",
+ "# Visualize results\n",
+ "def plot_results(model_names, tokens_per_sec):\n",
+ " plt.figure(figsize=(10, 6))\n",
+ " plt.barh(model_names, tokens_per_sec, color='skyblue')\n",
+ " plt.xlabel(\"Tokens per Second\")\n",
+ " plt.title(\"Model Speed Comparison: Tokens per Second\")\n",
+ " plt.gca().invert_yaxis()\n",
+ " plt.show()\n",
+ "\n",
+ "# Main execution\n",
+ "models = create_models()\n",
+ "sys_msg, user_msg = create_messages()\n",
+ "agents = initialize_agents(models, sys_msg)\n",
+ "\n",
+ "# Measure response times and collect data\n",
+ "model_names = []\n",
+ "tokens_per_sec = []\n",
+ "\n",
+ "for agent, model_name in agents:\n",
+ " model_names.append(model_name)\n",
+ " tokens_per_sec.append(measure_response_time(agent, user_msg))\n",
+ "\n",
+ "# Visualize the results\n",
+ "plot_results(model_names, tokens_per_sec)"
+ ]
+ }
+ ],
+ "metadata": {
+ "colab": {
+ "provenance": []
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}
diff --git a/docs/index.rst b/docs/index.rst
index a9a915521..10ec5e8c9 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -55,6 +55,7 @@ Main Documentation
cookbooks/create_your_first_agent.ipynb
cookbooks/create_your_first_agents_society.ipynb
cookbooks/agents_society.ipynb
+ cookbooks/model_speed_comparison.ipynb
cookbooks/agents_message.ipynb
cookbooks/agents_with_tools.ipynb
cookbooks/agents_with_tools_from_Composio.ipynb
diff --git a/docs/key_modules/models.md b/docs/key_modules/models.md
index 01f7b3663..148c3aa03 100644
--- a/docs/key_modules/models.md
+++ b/docs/key_modules/models.md
@@ -204,7 +204,18 @@ assistant_response = agent.step(user_msg)
print(assistant_response.msg.content)
```
-## 5. Conclusion
+## 5. About Model Speed
+Model speed is a crucial factor in AI application performance. It affects both user experience and system efficiency, especially in real-time or interactive tasks. In [this notebook](../cookbooks/model_speed_comparison.ipynb), we compared several models, including OpenAIโ€™s GPT-4O Mini, GPT-4O, O1 Preview, and SambaNova's Llama series, by measuring the number of tokens each model processes per second.
+
+Key Insights:
+Smaller models like SambaNovaโ€™s Llama 8B and OpenAI's GPT-4O Mini typically offer faster responses.
+Larger models like SambaNovaโ€™s Llama 405B, while more powerful, tend to generate output more slowly due to their complexity.
+OpenAI models demonstrate relatively consistent performance, while SambaNova's Llama 8B significantly outperforms others in speed.
+The chart below illustrates the tokens per second achieved by each model during our tests:
+
+![Model Speed Comparison](https://i.postimg.cc/4xByytyZ/model-speed.png)
+
+## 6. Conclusion
In conclusion, CAMEL empowers developers to explore and integrate these diverse models, unlocking new possibilities for innovative AI applications. The world of large language models offers a rich tapestry of options beyond just the well-known proprietary solutions. By guiding users through model selection, environment setup, and integration, CAMEL bridges the gap between cutting-edge AI research and practical implementation. Its hybrid approach, combining in-house implementations with third-party integrations, offers unparalleled flexibility and comprehensive support for LLM-based development. Don't just watch this transformation that is happening from the sidelines.
Dive into the CAMEL documentation, experiment with different models, and be part of shaping the future of AI. The era of truly flexible and powerful AI is here - are you ready to make your mark?