app.py

import json
import subprocess
from threading import Thread

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

#subprocess.run('pip install flash-attn --no-build-isolation', env={'FLASH_ATTENTION_SKIP_CUDA_BUILD': "TRUE"}, shell=True)

MODEL_ID = "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B"
CHAT_TEMPLATE = "َAuto"
MODEL_NAME = MODEL_ID.split("/")[-1]
CONTEXT_LENGTH = 16000


COLOR = "black"  
EMOJI = "🤖"  
DESCRIPTION = f"This is  {MODEL_NAME} model designed for testing thinking for general AI tasks."  # Descripción predeterminada

latex_delimiters_set = [{
        "left": "\\(",
        "right": "\\)",
        "display": False 
    }, {
        "left": "\\begin{equation}",
        "right": "\\end{equation}",
        "display": True 
    }, {
        "left": "\\begin{align}",
        "right": "\\end{align}",
        "display": True
    }, {
        "left": "\\begin{alignat}",
        "right": "\\end{alignat}",
        "display": True
    }, {
        "left": "\\begin{gather}",
        "right": "\\end{gather}",
        "display": True
    }, {
        "left": "\\begin{CD}",
        "right": "\\end{CD}",
        "display": True
    }, {
        "left": "\\[",
        "right": "\\]",
        "display": True
    }]


@spaces.GPU()
def predict(message, history, system_prompt, temperature, max_new_tokens, top_k, repetition_penalty, top_p):
    # Format history with a given chat template
    
    stop_tokens = [tokenizer.eos_token_id]
    pad_token_id=[tokenizer.eos_token_id] #151643
    instruction = system_prompt + "\n\n"
    for user, assistant in history:
        instruction += f"<｜User｜>{user}<｜Assistant｜>{assistant}\n"
    instruction += f"<｜User｜>{message}<｜Assistant｜>"
    
    print(instruction)
    
    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
    enc = tokenizer(instruction, return_tensors="pt", padding=True, truncation=True)
    input_ids, attention_mask = enc.input_ids, enc.attention_mask

    if input_ids.shape[1] > CONTEXT_LENGTH:
        input_ids = input_ids[:, -CONTEXT_LENGTH:]
        attention_mask = attention_mask[:, -CONTEXT_LENGTH:]

    generate_kwargs = dict(
        input_ids=input_ids.to(device),
        attention_mask=attention_mask.to(device),
        streamer=streamer,
        do_sample=True,
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_k=top_k,
        repetition_penalty=repetition_penalty,
        top_p=top_p
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()
    outputs = []
    for new_token in streamer:
        outputs.append(new_token)
        if new_token in stop_tokens:
            break
        yield "".join(outputs)


# Load model
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
quantization_config = BitsAndBytesConfig(
    load_in_4bit=True,
    bnb_4bit_compute_dtype=torch.bfloat16
)
tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    device_map="auto",
    #quantization_config=quantization_config,
    #attn_implementation="flash_attention_2",
    
)

# Create Gradio interface
gr.ChatInterface(
    predict,
    title=EMOJI + " " + MODEL_NAME,
    description=DESCRIPTION,
    

     
    additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False),
    additional_inputs=[
        gr.Textbox("You are a useful assistant. first recognize user request and then reply carfuly and thinking", label="System prompt"),
        gr.Slider(0, 1, 0.3, label="Temperature"),
        gr.Slider(4000, 4096, 1024, label="Max new tokens"),
        gr.Slider(1, 80, 40, label="Top K sampling"),
        gr.Slider(0, 2, 1.1, label="Repetition penalty"),
        gr.Slider(0, 1, 0.95, label="Top P sampling"),
    ],
    #theme=gr.themes.Soft(primary_hue=COLOR),
).queue().launch()