File size: 1,749 Bytes
865e55c 104d147 82f01bf 865e55c 104d147 82f01bf 865e55c 104d147 865e55c 104d147 865e55c 104d147 82f01bf 07f9f12 a58d727 07f9f12 104d147 865e55c 82f01bf 104d147 865e55c 104d147 865e55c 104d147 865e55c |
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 |
import spaces
import gradio as gr
from llama_cpp import Llama
import os
# 初始化LLM
llm = Llama.from_pretrained(
repo_id="matteogeniaccio/phi-4",
filename="phi-4-Q4_K_M.gguf",
verbose=True,
main_gpu=0,
n_gpu_layers=-1
)
# 响应函数
@spaces.GPU
def respond(
message,
history: list[tuple[str, str]],
system_message,
max_tokens,
temperature,
top_p,
):
# 构造消息内容
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})
# 使用llama-cpp-python的方式生成响应
response = llm.create_chat_completion(
messages=messages,
max_tokens=max_tokens,
temperature=temperature,
top_p=top_p,
stream=False
)
# 返回流式响应
for chunk in response:
if chunk and chunk.get("choices") and chunk["choices"][0].get("delta", {}).get("content"):
yield chunk["choices"][0]["delta"]["content"]
# Gradio 界面
demo = gr.ChatInterface(
respond,
additional_inputs=[
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
gr.Slider(minimum=1, maximum=2048, value=512, 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() |