app.py

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

# Load your model and tokenizer
model_name = "rshaikh22/coachcarellm"  # Replace with your actual model repo
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Move model to appropriate device
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

def respond(message, history):
    input_text = message
    inputs = tokenizer.encode(input_text + tokenizer.eos_token, return_tensors="pt").to(device)
    outputs = model.generate(inputs, max_length=1000, pad_token_id=tokenizer.eos_token_id)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)

if __name__ == "__main__":
    demo.launch()