app.py

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


from huggingface_hub import login
import os

# Use a secret token stored in your Space settings
hf_token = os.environ.get("HF_TOKEN")
if hf_token:
    login(token=hf_token)

    
# Load model and tokenizer
model_name = "google/gemma-3-270m" 
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
    device_map="auto"
)

# Chat function
def chat_with_gamma(history, message):
    inputs = tokenizer.encode(message, return_tensors="pt").to(model.device)
    outputs = model.generate(
        inputs,
        max_length=256,
        do_sample=True,
        top_p=0.9,
        temperature=0.7,
        pad_token_id=tokenizer.eos_token_id
    )
    reply = tokenizer.decode(outputs[0], skip_special_tokens=True)
    history.append((message, reply))
    return history, ""

# Gradio Chat UI
with gr.Blocks(theme=gr.themes.Soft()) as demo:
    gr.Markdown("## 🚀 Chat with Gamma3-270M")
    gr.Markdown("Professional demo of **Gamma3 270M**, an open-source LLM.")

    chatbot = gr.Chatbot(height=400)
    msg = gr.Textbox(placeholder="Type your message...")
    clear = gr.Button("Clear Chat")

    state = gr.State([])

    msg.submit(chat_with_gamma, [state, msg], [chatbot, msg])
    clear.click(lambda: ([], ""), None, [chatbot, msg])

demo.launch()