app.py

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

# Load model from Hugging Face Hub (replace with your username/model name)
model_name = "hari7261/TechChat"

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

# Chat function
def chat(prompt, max_new_tokens=200, temperature=0.7, top_p=0.9):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    with torch.no_grad():
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            temperature=temperature,
            top_p=top_p,
            pad_token_id=tokenizer.eos_token_id
        )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Gradio UI
with gr.Blocks() as demo:
    gr.Markdown("# 💬 TechChat - Domain Chatbot")
    gr.Markdown("Fine-tuned from Mistral-7B for technical Q&A")

    with gr.Row():
        with gr.Column(scale=3):
            user_input = gr.Textbox(lines=3, placeholder="Ask me something technical...", label="Your Question")
            max_tokens = gr.Slider(50, 500, value=200, step=10, label="Max New Tokens")
            temperature = gr.Slider(0.1, 1.5, value=0.7, step=0.1, label="Temperature")
            top_p = gr.Slider(0.1, 1.0, value=0.9, step=0.05, label="Top-p Sampling")
            submit_btn = gr.Button("Generate Answer")

        with gr.Column(scale=5):
            output_box = gr.Textbox(label="TechChat Response")

    submit_btn.click(
        fn=chat,
        inputs=[user_input, max_tokens, temperature, top_p],
        outputs=output_box
    )

demo.launch()