app.py

import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

# Your fine-tuned model
model_id = "Mike369williams/sanchari-gpt2-finetuned"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# Chat function
def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(
        **inputs,
        max_new_tokens=80,
        do_sample=True,
        temperature=0.8,
        top_p=0.9
    )
    reply = tokenizer.decode(output[0], skip_special_tokens=True)
    return reply

# UI
ui = gr.Interface(
    fn=chat,
    inputs=gr.Textbox(label="Your prompt"),
    outputs=gr.Textbox(label="Sanchari Response"),
    title="Sanchari — AI Demo",
    description="Demo of the fine-tuned Sanchari GPT-2 model."
)

ui.launch()