app.py

import gradio as gr
from huggingface_hub import InferenceClient
import spaces
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers import BitsAndBytesConfig
import torch

# پیکربندی quantization به صورت 4 بیتی
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.float16,
    bnb_4bit_quant_type="nf4",
    bnb_4bit_use_double_quant=True,
)

@spaces.GPU
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 = ""
    
    MODEL_PATH = "THUDM/GLM-Z1-9B-0414"
    
    tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
    model = AutoModelForCausalLM.from_pretrained(
        MODEL_PATH,
        device_map="auto",
        quantization_config=quantization_config,
        torch_dtype=torch.float16
    )
    
    inputs = tokenizer.apply_chat_template(
        messages,  # تغییر از message به messages
        return_tensors="pt",
        add_generation_prompt=True,
        return_dict=True,
    ).to(model.device)
    
    generate_kwargs = {
        "input_ids": inputs["input_ids"],
        "attention_mask": inputs["attention_mask"],
        "max_new_tokens": max_tokens,
        "temperature": temperature,
        "top_p": top_p,
        "do_sample": True if temperature > 0 else False,
    }
    
    out = model.generate(**generate_kwargs)
    response = tokenizer.decode(out[0][inputs["input_ids"].shape[1]:], skip_special_tokens=True)
    
    yield response

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()