app.py

from threading import Thread

import gradio as gr
from huggingface_hub import InferenceClient
import spaces
from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer

"""
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 = "CohereForAI/aya-expanse-8b"
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}]

#     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt")

#     gen_tokens = model.generate(
#         input_ids, 
#         max_new_tokens=max_tokens, 
#         do_sample=True, 
#         temperature=temperature,
#         top_p=top_p
#     )

# gen_text = tokenizer.decode(gen_tokens[0])

#     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

@spaces.GPU
def generate(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p):
    
    conversation = [{"role": "system", "content": system_message}]
    for user, assistant in history:
        conversation.extend([{"role": "user", "content": user}, {"role": "assistant", "content": assistant}])
    conversation.append({"role": "user", "content": message})

    input_ids = tokenizer.apply_chat_template(conversation, tokenize=True, add_generation_prompt=True, return_tensors="pt")

    # if input_ids.shape[1] > MAX_INPUT_TOKEN_LENGTH:
    #     input_ids = input_ids[:, -MAX_INPUT_TOKEN_LENGTH:]
    #     gr.Warning(f"Trimmed input from conversation as it was longer than {MAX_INPUT_TOKEN_LENGTH} tokens.")
    input_ids = input_ids.to(model.device)

    streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
            
    generate_kwargs = dict(
        {"input_ids": input_ids},
        streamer=streamer,
        max_new_tokens=max_tokens,
        do_sample=True,
        top_p=top_p,
        temperature=temperature,
    )
    t = Thread(target=model.generate, kwargs=generate_kwargs)
    t.start()

    outputs = []
    for text in streamer:
        outputs.append(text)
        yield "".join(outputs)


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    generate,
    additional_inputs=[
        gr.Textbox(value="Je bent een vriendelijke, behulpzame 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()