app.py

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
import gradio as gr

model_id = "TheBloke/Mistral-7B-Instruct-v0.1-GPTQ"

tokenizer = AutoTokenizer.from_pretrained(model_id, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    trust_remote_code=True,
    revision="main"
)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=200, do_sample=True, temperature=0.7)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=chat, inputs="text", outputs="text", title="🧠 Mistral Chatbot").launch()