app.py

from peft import AutoPeftModelForCausalLM
from transformers import AutoTokenizer, TextStreamer
import gradio as gr
"""
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("EITD/lora_model", token=os.getenv("HF_TOKEN"))

model = AutoPeftModelForCausalLM.from_pretrained(
        "EITD/lora_model_1", # YOUR MODEL YOU USED FOR TRAINING
        load_in_4bit = False,
    )
tokenizer = AutoTokenizer.from_pretrained("EITD/lora_model_1")

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
    
    inputs = tokenizer.apply_chat_template(
        messages,
        tokenize = True,
        add_generation_prompt = True, # Must add for generation
        return_tensors = "pt",
    )
    
    outputs = model.generate(input_ids = inputs, max_new_tokens = max_tokens, use_cache = True,
                         temperature = temperature, min_p = top_p)
    
    # text_streamer = TextStreamer(tokenizer, skip_prompt = True)
    # model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = max_tokens,
    #                 use_cache = True, temperature = temperature, min_p = top_p)
    response = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]

    if "assistant" in response:
        response = response.split("assistant")[-1].strip()
    
    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()