app.py

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

model_id = "yuvrajpant56/Mistral_Posttrain_SFT"

# Load model & tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.float16, device_map="auto")

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=100)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=generate_text,
             inputs="text",
             outputs="text",
             title="Mistral SFT Text Generator",
             description="Type a prompt and let the fine-tuned Mistral model generate the rest."
).launch()