app.py

import gradio as gr
from huggingface_hub import InferenceClient

HF_TOKEN = "hf_your_access_token_here"  # Replace with your HF API token

def respond(message, history, system_message, max_tokens, temperature, top_p):
    client = InferenceClient(
        token=HF_TOKEN,
        model="Nikolester0/Gyaanchand-3B",
    )

    messages = [{"role": "system", "content": system_message}]
    messages.extend(history)
    messages.append({"role": "user", "content": message})

    response = ""
    for chunk in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        choices = chunk.choices
        if len(choices) and choices[0].delta.content:
            response += choices[0].delta.content
            yield response

chatbot = gr.ChatInterface(
    fn=respond,
    type="messages",
    additional_inputs=[
        gr.Textbox(value="You are a friendly assistant.", label="System message"),
        gr.Slider(1, 2048, 512, 1, label="Max new tokens"),
        gr.Slider(0.1, 4.0, 0.7, 0.1, label="Temperature"),
        gr.Slider(0.1, 1.0, 0.95, 0.05, label="Top-p"),
    ],
    title="🤖 Gyaanchand 3B (Hosted)",
    description="Inference powered by Hugging Face Hub.",
)

if __name__ == "__main__":
    chatbot.launch(share=True, ssr_mode=False)