File size: 10,282 Bytes
3aabe25 5177a4e 3e065db 5177a4e 3aabe25 938a41c 789f6c7 e9d8fd0 eedc15d e9d8fd0 06dd8c4 e9d8fd0 789f6c7 e9d8fd0 789f6c7 e9d8fd0 789f6c7 eedc15d e9d8fd0 5177a4e e9d8fd0 938a41c eedc15d 3aabe25 5177a4e 3605342 bb24da0 938a41c 789f6c7 e9d8fd0 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 |
# import gradio as gr
# from huggingface_hub import InferenceClient
# """
# 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
# """
# client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
# def respond(
# message,
# history: list[tuple[str, str]],
# system_message,
# max_tokens,
# temperature,
# top_p,
# ):
# messages = [{"role": "system", "content": system_message}]
# for val in history:
# if val[0]:
# messages.append({"role": "user", "content": val[0]})
# if val[1]:
# messages.append({"role": "assistant", "content": val[1]})
# messages.append({"role": "user", "content": message})
# response = ""
# for message in client.chat_completion(
# messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# token = message.choices[0].delta.content
# response += token
# yield response
# """
# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
# """
# demo = gr.ChatInterface(
# respond,
# additional_inputs=[
# gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
# gr.Slider(minimum=1, maximum=2048, value=2048, step=1, label="Max new tokens"),
# gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
# gr.Slider(
# minimum=0.1,
# maximum=1.0,
# value=0.95,
# step=0.05,
# label="Top-p (nucleus sampling)",
# ),
# ],
# )
# if __name__ == "__main__":
# demo.launch()
# import gradio as gr
# from huggingface_hub import InferenceClient
"""
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
"""
# client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
# def respond(message, history: list[tuple[str, str]]):
# system_message = (
# "You are a helpful and experienced coding assistant specialized in web development. "
# "Help the user by generating complete and functional code for building websites. "
# "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) based on their requirements. "
# "Break down the tasks clearly if needed, and be friendly and supportive in your responses.")
# max_tokens = 2048
# temperature = 0.7
# top_p = 0.95
# messages = [{"role": "system", "content": system_message}]
# for val in history:
# if val[0]:
# messages.append({"role": "user", "content": val[0]})
# if val[1]:
# messages.append({"role": "assistant", "content": val[1]})
# messages.append({"role": "user", "content": message})
# response = ""
# for message in client.chat_completion(
# messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# token = message.choices[0].delta.content
# response += token
# yield response
# """
# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
# """
# demo = gr.ChatInterface(respond)
# if __name__ == "__main__":
# demo.launch()
# import gradio as gr
# from huggingface_hub import InferenceClient
# """
# 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
# """
# client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
# def respond(message, history: list[tuple[str, str]]):
# system_message = (
# "You are a helpful and experienced coding assistant specialized in web development. "
# "Help the user by generating complete and functional code for building websites. "
# "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) based on their requirements. "
# "Break down the tasks clearly if needed, and be friendly and supportive in your responses."
# )
# max_tokens = 2048
# temperature = 0.7
# top_p = 0.95
# messages = [{"role": "system", "content": system_message}]
# for val in history:
# if val[0]:
# messages.append({"role": "user", "content": val[0]})
# if val[1]:
# messages.append({"role": "assistant", "content": val[1]})
# messages.append({"role": "user", "content": message})
# response = ""
# for message in client.chat_completion(
# messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# token = message.choices[0].delta.content
# response += token
# yield response
# """
# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
# """
# demo = gr.ChatInterface(respond)
# if __name__ == "__main__":
# demo.launch()
# import gradio as gr
# from huggingface_hub import InferenceClient
# # 1. Instantiate with named model param
# client = InferenceClient(model="Qwen/Qwen2.5-Coder-32B-Instruct")
# def respond(message, history: list[tuple[str, str]]):
# system_message = (
# "You are a helpful and experienced coding assistant specialized in web development. "
# "Help the user by generating complete and functional code for building websites. "
# "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) "
# "based on their requirements."
# )
# max_tokens = 2048
# temperature = 0.7
# top_p = 0.95
# # Build messages in OpenAI-compatible format
# messages = [{"role": "system", "content": system_message}]
# for user_msg, assistant_msg in history:
# if user_msg:
# messages.append({"role": "user", "content": user_msg})
# if assistant_msg:
# messages.append({"role": "assistant", "content": assistant_msg})
# messages.append({"role": "user", "content": message})
# response = ""
# # 2. Use named parameters and alias if desired
# for chunk in client.chat.completions.create(
# model="Qwen/Qwen2.5-Coder-32B-Instruct",
# messages=messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# # 3. Extract token content
# token = chunk.choices[0].delta.content or ""
# response += token
# yield response
# # 4. Wire up Gradio chat interface
# demo = gr.ChatInterface(respond, type="messages")
# if __name__ == "__main__":
# demo.launch()
# import gradio as gr
# from huggingface_hub import InferenceClient
# hf_token = "HF_TOKEN"
# # Ensure token is available
# if hf_token is None:
# raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set in .env file or environment.")
# # Instantiate Hugging Face Inference Client with token
# client = InferenceClient(
# model="Qwen/Qwen2.5-Coder-32B-Instruct",
# token=hf_token
# )
# def respond(message, history: list[tuple[str, str]]):
# system_message = (
# "You are a helpful and experienced coding assistant specialized in web development. "
# "Help the user by generating complete and functional code for building websites. "
# "You can provide HTML, CSS, JavaScript, and backend code (like Flask, Node.js, etc.) "
# "based on their requirements."
# )
# max_tokens = 2048
# temperature = 0.7
# top_p = 0.95
# # Build conversation history
# messages = [{"role": "system", "content": system_message}]
# for user_msg, assistant_msg in history:
# if user_msg:
# messages.append({"role": "user", "content": user_msg})
# if assistant_msg:
# messages.append({"role": "assistant", "content": assistant_msg})
# messages.append({"role": "user", "content": message})
# response = ""
# # Stream the response from the model
# for chunk in client.chat.completions.create(
# model="Qwen/Qwen2.5-Coder-32B-Instruct",
# messages=messages,
# max_tokens=max_tokens,
# stream=True,
# temperature=temperature,
# top_p=top_p,
# ):
# token = chunk.choices[0].delta.content or ""
# response += token
# yield response
# # Gradio UI
# demo = gr.ChatInterface(respond, type="messages")
# if __name__ == "__main__":
# demo.launch()
import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
# Load once globally
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Coder-32B-Instruct")
model = AutoModelForCausalLM.from_pretrained(
"Qwen/Qwen2.5-Coder-32B-Instruct",
device_map="auto",
torch_dtype=torch.float16,
)
def respond(message, history):
system_prompt = (
"You are a helpful coding assistant specialized in web development. "
"Provide complete code snippets for HTML, CSS, JS, Flask, Node.js etc."
)
# Build input prompt including chat history
chat_history = ""
for user_msg, bot_msg in history:
chat_history += f"User: {user_msg}\nAssistant: {bot_msg}\n"
prompt = f"{system_prompt}\n{chat_history}User: {message}\nAssistant:"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
**inputs,
max_new_tokens=512,
temperature=0.7,
do_sample=True,
top_p=0.95,
eos_token_id=tokenizer.eos_token_id,
)
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
# Extract only the new response part after the prompt
response = generated_text[len(prompt):].strip()
# Append current Q/A to history
history.append((message, response))
return "", history
demo = gr.ChatInterface(respond, type="messages")
if __name__ == "__main__":
demo.launch()
|