app.py

import gradio as gr
from huggingface_hub import InferenceClient

"""
Copied from inference in colab notebook
"""
# import torch

# # Monkey-patch to avoid CUDA initialization issues
# torch.cuda.get_device_capability = lambda *args, **kwargs: (0, 0)

# from unsloth.chat_templates import get_chat_template
# from unsloth import FastLanguageModel

# # IMPORTING MODEL AND TOKENIZER ————————

# max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
# dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
# load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.

# model, tokenizer = FastLanguageModel.from_pretrained(
#     model_name = "llama_lora_model_1",
#     max_seq_length = max_seq_length,
#     dtype = dtype,
#     load_in_4bit = load_in_4bit,
# )

# tokenizer = get_chat_template(
#     tokenizer,
#     chat_template = "llama-3.1",
# )
# FastLanguageModel.for_inference(model) # Enable native 2x faster inference

# # RUNNING INFERENCE ————————————————————————

# 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})

#     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 = 1.5, min_p = 0.1)
#     response = tokenizer.batch_decode(outputs)

#     yield response

"""
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(model="https://huggingface.co/Heit39/llama_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


"""
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()