app.py

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

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

model_id = "GoToCompany/llama3-8b-cpt-sahabatai-v1-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

# 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()



# Function to generate text
def generate_text(prompt, max_length=100):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_length=max_length,
        num_return_sequences=1,
        no_repeat_ngram_size=2,
        do_sample=True,
        top_p=0.95,
        temperature=0.7
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Gradio frontend
def gradio_interface(prompt, max_length):
    if not prompt.strip():
        return "Please enter a prompt."
    try:
        output = generate_text(prompt, max_length=max_length)
        return output
    except Exception as e:
        return f"An error occurred: {str(e)}"

# Define Gradio components
with gr.Blocks() as demo:
    gr.Markdown("# LLaMA3 8B CPT Sahabatai Instruct")
    gr.Markdown("Generate text using the **LLaMA3 8B CPT Sahabatai Instruct** model.")
    
    with gr.Row():
        with gr.Column():
            prompt_input = gr.Textbox(
                label="Enter your prompt",
                placeholder="Type something...",
                lines=3,
            )
            max_length_slider = gr.Slider(
                label="Max Length",
                minimum=10,
                maximum=200,
                value=100,
                step=10,
            )
            generate_button = gr.Button("Generate")
        
        with gr.Column():
            output_text = gr.Textbox(
                label="Generated Text",
                lines=10,
                interactive=False,
            )
    
    # Link the button to the function
    generate_button.click(
        fn=gradio_interface,
        inputs=[prompt_input, max_length_slider],
        outputs=output_text,
    )

# Launch the Gradio app

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