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):
    """
    Generates text using a large language model, given a user input and a system prompt.
    Args:
        user_input: The user's input text to generate a response for.
        system_prompt: Optional system prompt.
    Returns:
        A string containing the generated text in the Falcon-like format.
    """
    # Combine user input and system prompt
    formatted_input = f"{{{{ {system_prompt} }}}}\nUser: {user_input}\nFalcon:"

    # 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 = peft_model.generate(
        **model_inputs,
        max_length=400,
        use_cache=True,
        early_stopping=False,
        bos_token_id=peft_model.config.bos_token_id,
        eos_token_id=peft_model.config.eos_token_id,
        pad_token_id=peft_model.config.eos_token_id,
        temperature=0.4,
        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 = "tiiuae/falcon-7b-instruct"
model_directory = "Tonic/GaiaMiniMed"

# Instantiate the Tokenizer
tokenizer = AutoTokenizer.from_pretrained(base_model_id, trust_remote_code=True, padding_side="left")
# tokenizer = AutoTokenizer.from_pretrained("Tonic/mistralmed", trust_remote_code=True, padding_side="left")
# tokenizer.pad_token = tokenizer.eos_token
# tokenizer.padding_side = 'left'

# Load the GaiaMiniMed model with the specified configuration
# Load the Peft model with a specific configuration
# 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(model_directory, config=model_config)
peft_model = PeftModel.from_pretrained(peft_model, model_directory)

# 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("Tonic/mistralmed")
# peft_model = MistralForCausalLM.from_pretrained("mistralai/Mistral-7B-v0.1", trust_remote_code=True)
# peft_model = PeftModel.from_pretrained(peft_model, "Tonic/mistralmed")

class ChatBot:
    def __init__(self, system_prompt="You are an expert medical analyst:"):
        self.system_prompt = system_prompt
        self.history = []

    def predict(self, user_input, system_prompt):
        # Combine the user's input with the system prompt in Falcon format
        formatted_input = f"{{{{ {self.system_prompt} }}}}\nUser: {user_input}\nFalcon:"

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

        # Generate a response using the model
        response = peft_model.generate(input_ids=input_ids, max_length=500, use_cache=False, early_stopping=False, bos_token_id=peft_model.config.bos_token_id, eos_token_id=peft_model.config.eos_token_id, pad_token_id=peft_model.config.eos_token_id, temperature=0.4, do_sample=True)

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

        # Append the Falcon-like conversation to the history
        self.history.append(formatted_input)
        self.history.append(response_text)

        return response_text

bot = ChatBot()

title = "👋🏻Welcome to Tonic's GaiaMiniMed Chat🚀"
description = "You can use this Space to test out the current model [(Tonic/GaiaMiniMed)](https://huggingface.co/Tonic/GaiaMiniMed) or duplicate this Space and use it locally or on 🤗HuggingFace. [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
examples = [["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()