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

model_name = "mistralai/Mistral-7B-Instruct-v0.1"  # Can switch to Llama later

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
    output = model.generate(**inputs, max_new_tokens=500)
    response = tokenizer.decode(output[0], skip_special_tokens=True)
    return response

demo = gr.Interface(fn=chat, inputs="text", outputs="text")

demo.launch()