app.py

import gradio as gr
from huggingface_hub import InferenceClient
import spaces
import torch
import os
from huggingface_hub import login
from PIL import Image

"""
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")

duration=None

login(token = os.getenv('deepseekv2'))

ckpt = "google/gemma-3-4b-it"
model = Gemma3ForConditionalGeneration.from_pretrained(
    ckpt, device_map="auto", torch_dtype=torch.bfloat16,
)
processor = AutoProcessor.from_pretrained(ckpt)

# image = Image.open(requests.get(url, stream=True).raw)
# prompt = "<start_of_image> in this image, there is"
# model_inputs = processor(text=prompt, images=image, return_tensors="pt")
# input_len = model_inputs["input_ids"].shape[-1]

# with torch.inference_mode():
#     generation = model.generate(**model_inputs, max_new_tokens=100, do_sample=False)
#     generation = generation[0][input_len:]

@spaces.GPU(duration=duration)
def respond(message, history: list[tuple[str, str]], system_message, max_tokens, temperature, top_p,):
    # messages = [{"role": "system", "content": system_message}]
    
    messages = [{
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/spaces/big-vision/paligemma-hf/resolve/main/examples/password.jpg"},
            {"type": "text", "text": "What is the password?"}
        ]}]

    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,
    textbox=gr.MultimodalTextbox()
    multimodal=True,
    stop_btn="Stop generation",
    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()