app.py

from huggingface_hub import InferenceClient

import gradio as gr

model_path = "ibm-granite/granite-34b-code-instruct-8k"
model_path="ibm-granite/granite-3b-code-instruct-2k"

import os
hftoken = os.environ["hftoken"]
client = InferenceClient(model=model_path, token=hftoken)


def format_prompt(system, message, history):
    prompt = [{"role": "system", "content": system}] 
    for user_prompt, bot_response in history:
        prompt += {"role": "user", "content": user_prompt}
        prompt += {"role": "assistant", "content": bot_response}
    prompt += {"role": "user", "content": message}
    return prompt

def generate(
    prompt, history, system_message=None, temperature=0.9, max_new_tokens=256, top_p=0.95, repetition_penalty=1.0):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=42,
    )

    formatted_prompt = format_prompt(system_message, prompt, history)

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output


additional_inputs=[
    gr.TextArea(
        label="System message",
        value="",
        interactive=True,
        info="context",
    ),
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=256,
        minimum=0,
        maximum=1048,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]



gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
    additional_inputs=additional_inputs,
    title=model_path
).launch(show_api=True)