print(f"已生成：{name}")
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "microsoft/Phi-4"
tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
model_id, torch_dtype=torch.bfloat16, device_map="auto", trust_remote_code=True
)
def chat(message, history, system_prompt, temperature):
messages = [{"role": "system", "content": system_prompt}]
for h in history:
messages.append({"role": "user", "content": h[0]})
messages.append({"role": "assistant", "content": h[1]})
messages.append({"role": "user", "content": message})
inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
outputs = model.generate(inputs, max_new_tokens=512, temperature=temperature, do_sample=True)
return tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True)
demo = gr.ChatInterface(
fn=chat,
additional_inputs=[
gr.Textbox(value="You are a helpful assistant.", label="System"),
gr.Slider(0.1, 1.5, value=0.7, label="Temperature")
],
title="Phi-4 Chat"
)
demo.launch(server_name="0.0.0.0", server_port=7860)
