app.py

# Inference

import gradio as gr
from huggingface_hub import InferenceClient

model = "google/gemma-2-27b-it"
client = InferenceClient(model)

def fn_text(
    prompt,
    history,
    #system_prompt,
    max_tokens,
    temperature,
    top_p,
):
    #messages = [{"role": "system", "content": system_prompt}]
    #history.append(messages[0])
    
    #messages.append({"role": "user", "content": prompt})
    #history.append(messages[1])

    messages = [{"role": "user", "content": prompt}]
    history.append(messages[0])
    
    stream = client.chat.completions.create(
        model = model,
        messages = history,
        max_tokens = max_tokens,
        temperature = temperature,
        top_p = top_p,
        stream = True
    )
    
    chunks = []
    for chunk in stream:
        chunks.append(chunk.choices[0].delta.content or "")
        yield "".join(chunks)

app_text = gr.ChatInterface(
    fn = fn_text,
    type = "messages",
    additional_inputs = [
        #gr.Textbox(value="You are a helpful assistant.", label="System Prompt"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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"),
    ],
    title = "Google Gemma",
    description = model,
)

app = gr.TabbedInterface(
    [app_text],
    ["Text"]
).launch()

#if __name__ == "__main__":
#    app.launch()

"""
# Inference

import gradio as gr
from huggingface_hub import InferenceClient

model = "google/gemma-2-27b-it"
#model = "google/gemma-2-9b-it"
#model = "google/gemma-2-2b-it"
client = InferenceClient(model)

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

    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": "bot", "content": val[1]})

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

    response = ""

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

        response += token
        yield response

app = gr.ChatInterface(
    fn = fn,
    #type = "messages",
    additional_inputs = [
        #gr.Textbox(value="You are a helpful assistant.", label="System Message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max 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"),
    ],
    title = "Google Gemma",
    description = model,
)

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