app.py

import gradio as gr
import torch  # Add this import
from transformers import pipeline

model_name = "EleutherAI/gpt-neo-1.3B"
generator = pipeline("text-generation", model=model_name)

def generate_text(prompt):
    return generator(
        prompt,
        max_length=50,           # Reduced max length
        temperature=0.5,          # Lower temperature for predictable output
        top_k=20,                 # Smaller token pool for quicker responses
        top_p=0.8,                # Adjusted nucleus sampling
        repetition_penalty=1.4,   # Increased to reduce redundancy
        do_sample=True
    )[0]["generated_text"]




interface = gr.Interface(fn=generate_text, inputs="text", outputs="text")
interface.launch()


client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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()