Spaces:
Sleeping
Sleeping
File size: 3,495 Bytes
a947ce2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "6797ba2e-ef94-42d6-9e64-a1559b507173",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\singl\\anaconda3\\envs\\pshcy\\lib\\site-packages\\tqdm\\auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n"
]
}
],
"source": [
"import gradio as gr\n",
"from huggingface_hub import InferenceClient\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "f50cbd8a-777f-440c-8b7f-8eca9e611e12",
"metadata": {},
"outputs": [],
"source": [
"\"\"\"\n",
"For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference\n",
"\"\"\"\n",
"client = InferenceClient(\"HuggingFaceH4/zephyr-7b-beta\")\n",
"\n",
"\n",
"def respond(\n",
" message,\n",
" history: list[tuple[str, str]],\n",
" system_message,\n",
" max_tokens,\n",
" temperature,\n",
" top_p,\n",
"):\n",
" messages = [{\"role\": \"system\", \"content\": system_message}]\n",
"\n",
" for val in history:\n",
" if val[0]:\n",
" messages.append({\"role\": \"user\", \"content\": val[0]})\n",
" if val[1]:\n",
" messages.append({\"role\": \"assistant\", \"content\": val[1]})\n",
"\n",
" messages.append({\"role\": \"user\", \"content\": message})\n",
"\n",
" response = \"\"\n",
"\n",
" for message in client.chat_completion(\n",
" messages,\n",
" max_tokens=max_tokens,\n",
" stream=True,\n",
" temperature=temperature,\n",
" top_p=top_p,\n",
" ):\n",
" token = message.choices[0].delta.content\n",
"\n",
" response += token\n",
" yield response\n",
"\n",
"\n",
"\"\"\"\n",
"For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface\n",
"\"\"\"\n",
"demo = gr.ChatInterface(\n",
" respond,\n",
" additional_inputs=[\n",
" gr.Textbox(value=\"You are a friendly Chatbot.\", label=\"System message\"),\n",
" gr.Slider(minimum=1, maximum=2048, value=512, step=1, label=\"Max new tokens\"),\n",
" gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label=\"Temperature\"),\n",
" gr.Slider(\n",
" minimum=0.1,\n",
" maximum=1.0,\n",
" value=0.95,\n",
" step=0.05,\n",
" label=\"Top-p (nucleus sampling)\",\n",
" ),\n",
" ],\n",
")\n",
"\n",
"\n",
"if __name__ == \"__main__\":\n",
" demo.launch()\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python (Psych)",
"language": "python",
"name": "pshcy"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.18"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|