app.py

import gradio as gr
from huggingface_hub import InferenceClient
from unsloth import FastLanguageModel
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 = "minhnguyen5293/lora_model", # YOUR MODEL YOU USED FOR TRAINING
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster inference

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

model, tokenizer = FastLanguageModel.from_pretrained(
    model_name = "lora_model", # YOUR MODEL YOU USED FOR TRAINING
    max_seq_length = max_seq_length,
    dtype = dtype,
    load_in_4bit = load_in_4bit,
)
FastLanguageModel.for_inference(model) # Enable native 2x faster 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})

    from transformers import TextIteratorStreamer

    inputs = tokenizer.apply_chat_template(
        messages,
        tokenize = True,
        add_generation_prompt = True, # Must add for generation
        return_tensors = "pt",
    ).to("cuda")

    text_streamer = TextIteratorStreamer(tokenizer, skip_prompt = True)
    _ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128,
                      use_cache = True, temperature = 1.5, min_p = 0.1)


    response = ""

    for message in text_streamer:
        # remove <|eot_id|>
        response += message.split("<|eot_id|>")[0]
        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()