app.py

import gradio as gr
from huggingface_hub import InferenceClient

"""
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
"""
model = InferenceClient("abdfajar707/rkp_lora_model")

def get_completion(query: str, model, tokenizer) -> str:
  device = "cuda:0"
  prompt_template = """
  <start_of_turn>user
  Below is an instruction that describes a task. Write a response that appropriately completes the request.
  {query}
  <end_of_turn>\\n<start_of_turn>model
  
  """
  prompt = prompt_template.format(query=query)
  encodeds = tokenizer(prompt, return_tensors="pt", add_special_tokens=True)
  model_inputs = encodeds.to(device)
  generated_ids = model.generate(**model_inputs, max_new_tokens=1000, do_sample=True, pad_token_id=tokenizer.eos_token_id)
  # decoded = tokenizer.batch_decode(generated_ids)
  decoded = tokenizer.decode(generated_ids[0], skip_special_tokens=True)
  return (decoded)

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 model.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(
    get_completion,
    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()