app.py

from transformers import AutoConfig, AutoTokenizer, AutoModelForSeq2SeqLM, AutoModelForCausalLM, MistralForCausalLM
from peft import PeftModel, PeftConfig
import torch
import gradio as gr
import random
from textwrap import wrap

# Functions to Wrap the Prompt Correctly
def wrap_text(text, width=90):
    lines = text.split('\n')
    wrapped_lines = [textwrap.fill(line, width=width) for line in lines]
    wrapped_text = '\n'.join(wrapped_lines)
    return wrapped_text

def multimodal_prompt(user_input, system_prompt="You are an expert medical analyst:"):
    # Combine user input and system prompt
    formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"

    # Encode the input text
    encodeds = tokenizer(formatted_input, return_tensors="pt", add_special_tokens=False)
    model_inputs = encodeds.to(device)

    # Generate a response using the model
    output = model.generate(
        **model_inputs,
        max_length=max_length,
        use_cache=True,
        early_stopping=True,
        bos_token_id=model.config.bos_token_id,
        eos_token_id=model.config.eos_token_id,
        pad_token_id=model.config.eos_token_id,
        temperature=0.1,
        do_sample=True
    )

    # Decode the response
    response_text = tokenizer.decode(output[0], skip_special_tokens=True)

    return response_text

# Define the device
device = "cuda" if torch.cuda.is_available() else "cpu"

# Use the base model's ID
base_model_id = "HuggingFaceH4/zephyr-7b-beta"
model_directory = "pseudolab/K23_MiniMed"

# Instantiate the Tokenizer
tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-7b-beta", trust_remote_code=True, padding_side="left")
# tokenizer = AutoTokenizer.from_pretrained("pseudolab/K23_MiniMed", trust_remote_code=True, padding_side="left")
tokenizer.pad_token = tokenizer.eos_token
tokenizer.padding_side = 'left'

# Specify the configuration class for the model
#model_config = AutoConfig.from_pretrained(base_model_id)

# Load the PEFT model with the specified configuration
#peft_model = AutoModelForCausalLM.from_pretrained(base_model_id, config=model_config)

# Load the PEFT model
peft_config = PeftConfig.from_pretrained("pseudolab/K23_MiniMed")
peft_model = MistralForCausalLM.from_pretrained("HuggingFaceH4/zephyr-7b-beta", trust_remote_code=True)
peft_model = PeftModel.from_pretrained(peft_model, "pseudolab/K23_MiniMed")

class ChatBot:
    def __init__(self):
        self.history = []

class ChatBot:
    def __init__(self):
        # Initialize the ChatBot class with an empty history
        self.history = []

    def predict(self, user_input, system_prompt="You are an expert medical analyst:"):
        # Combine the user's input with the system prompt
        formatted_input = f"<s>[INST]{system_prompt} {user_input}[/INST]"

        # Encode the formatted input using the tokenizer
        user_input_ids = tokenizer.encode(formatted_input, return_tensors="pt")

        # Generate a response using the PEFT model
        response = peft_model.generate(input_ids=user_input_ids, max_length=512, pad_token_id=tokenizer.eos_token_id)

        # Decode the generated response to text
        response_text = tokenizer.decode(response[0], skip_special_tokens=True)
        
        return response_text  # Return the generated response

bot = ChatBot()

title = "👋🏻토닉의 미스트랄메드 채팅에 오신 것을 환영합니다🚀👋🏻Welcome to Tonic's MistralMed Chat🚀"
description = "이 공간을 사용하여 현재 모델을 테스트할 수 있습니다. [pseudolab/K23_MiniMed](https://huggingface.co/pseudolab/K23_MiniMed) 또는 이 공간을 복제하고 로컬 또는 🤗HuggingFace에서 사용할 수 있습니다. [Discord에서 함께 만들기 위해 Discord에 가입하십시오](https://discord.gg/VqTxc76K3u). You can use this Space to test out the current model [pseudolab/K23_MiniMed](https://huggingface.co/pseudolab/K23_MiniMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
examples = [["[Question:] What is the proper treatment for buccal herpes?", "You are a medicine and public health expert, you will receive a question, answer the question, and provide a complete answer"]]

iface = gr.Interface(
    fn=bot.predict,
    title=title,
    description=description,
    examples=examples,
    inputs=["text", "text"],  # Take user input and system prompt separately
    outputs="text",
    theme="ParityError/Anime"
)

iface.launch()