K23 MiniMed ๋ชจ๋ธ ์นด๋
K23 MiniMed๋ Krew x Huggingface 2023 ํด์ปคํค์์ ์ํ์ ๋ฉํ ์ ์ง๋ํ์ ๊ฐ๋ฐ๋ Mistral 7b Beta Medical Fine Tune ๋ชจ๋ธ์ ๋๋ค.
๋ชจ๋ธ ์ธ๋ถ์ฌํญ
๊ฐ๋ฐ์: Tonic
ํ์: Tonic
๊ณต์ ์: K23-Krew-Hackathon
๋ชจ๋ธ ์ ํ: Mistral 7B-Beta Medical Fine Tune
์ธ์ด (NLP): ์์ด
๋ผ์ด์ผ์ค: MIT
Fine-tuning ๊ธฐ๋ฐ ๋ชจ๋ธ: Zephyr 7B-Beta
๋ชจ๋ธ ์ถ์ฒ
- ์ ์ฅ์: github
- ๋ฐ๋ชจ: pseudolab/K23MiniMed
์ฌ์ฉ๋ฒ
์ด ๋ชจ๋ธ์ ๊ต์ก ๋ชฉ์ ์ผ๋ก๋ง ์ํ ์ง๋ฌธ ๋ต๋ณ์ ์ํ ๋ํํ ์ ํ๋ฆฌ์ผ์ด์ ์ฉ์ ๋๋ค.
์ง์ ์ฌ์ฉ
Gradio ์ฑ๋ด ์ฑ์ ๋ง๋ค์ด ์ํ์ ์ง๋ฌธ์ ํ๊ณ ๋ํ์์ผ๋ก ๋ต๋ณ์ ๋ฐ์ต๋๋ค.
ํ๋ฅ ์ฌ์ฉ
์ด ๋ชจ๋ธ์ ๊ต์ก์ฉ์ผ๋ก๋ง ์ฌ์ฉ๋ฉ๋๋ค. ์ถ๊ฐ์ ์ธ Fine-tuning๊ณผ ์ฌ์ฉ ์์๋ก๋ ๊ณต์ค ๋ณด๊ฑด & ์์, ๊ฐ์ธ ๋ณด๊ฑด & ์์, ์ํ Q & A๊ฐ ์์ต๋๋ค.
์ถ์ฒ์ฌํญ
์ฌ์ฉ ์ ์ ํญ์ ์ด ๋ชจ๋ธ์ ํ๊ฐํ๊ณ ๋ฒค์น๋งํนํ์ญ์์ค. ์ฌ์ฉ ์ ์ ํธํฅ์ ํ๊ฐํ์ญ์์ค. ๊ทธ๋๋ก ์ฌ์ฉํ์ง ๋ง์๊ณ ์ถ๊ฐ์ ์ผ๋ก Fine-tuningํ์ญ์์ค.
ํ๋ จ ์ธ๋ถ์ฌํญ
๋ชจ๋ธ์ ํ๋ จ ์์ค์ ๋ค์๊ณผ ๊ฐ์ต๋๋ค:
๋จ๊ณ | ํ๋ จ ์์ค |
---|---|
50 | 0.993800 |
100 | 0.620600 |
150 | 0.547100 |
200 | 0.524100 |
250 | 0.520500 |
300 | 0.559800 |
350 | 0.535500 |
400 | 0.505400 |
ํ๋ จ ๋ฐ์ดํฐ
๋ชจ๋ธ์ ํ์ต ๊ฐ๋ฅํ ๋งค๊ฐ๋ณ์: 21260288, ๋ชจ๋ ๋งค๊ฐ๋ณ์: 3773331456, ํ์ต ๊ฐ๋ฅํ %: 0.5634354746703705.
๊ฒฐ๊ณผ
global_step=400์์์ ํ๋ จ ์์ค์ 0.6008514881134033์ ๋๋ค.
ํ๊ฒฝ ์ํฅ
๋ชจ๋ธ์ ํ๊ฒฝ ์ํฅ์ ๋จธ์ ๋ฌ๋ ์ํฅ ๊ณ์ฐ๊ธฐ๋ฅผ ์ฌ์ฉํ์ฌ ๊ณ์ฐํ ์ ์์ต๋๋ค. ์ถ์ ์ ์ ๊ณตํ๊ธฐ ์ํด์๋ ๋ ๋ง์ ์ธ๋ถ ์ ๋ณด๊ฐ ํ์ํฉ๋๋ค.
๊ธฐ์ ์ฌ์
๋ชจ๋ธ ์ํคํ ์ฒ์ ๋ชฉํ
๋ชจ๋ธ์ ํน์ ์ค์ ์ ๊ฐ์ง PeftModelForCausalLM์ ์ฌ์ฉํฉ๋๋ค.
์ปดํจํ ์ธํ๋ผ
ํ๋์จ์ด
๋ชจ๋ธ์ A100 ํ๋์จ์ด์์ ํ๋ จ๋์์ต๋๋ค.
์ํํธ์จ์ด
์ฌ์ฉ๋ ์ํํธ์จ์ด์๋ peft, torch, bitsandbytes, python, ๊ทธ๋ฆฌ๊ณ huggingface๊ฐ ํฌํจ๋ฉ๋๋ค.
๋ชจ๋ธ ์นด๋ ์์ฑ์
๋ชจ๋ธ ์นด๋ ์ฐ๋ฝ์ฒ
Model Card for K23 MiniMed
This is a Mistral 7b Beta Medical Fine Tune with a short number of steps , inspired by Wonhyeong Seo great mentorship during Krew x Huggingface 2023 hackathon.
Model Details
Model Description
- Developed by: Tonic
- Funded by [optional]: Tonic
- Shared by [optional]: K23-Krew-Hackathon
- Model type: Mistral 7B-Beta Medical Fine Tune
- Language(s) (NLP): English
- License: MIT
- Finetuned from model [optional]: Zephyr 7B-Beta
Model Sources [optional]
- Repository: github
- Demo [optional]: pseudolab/K23MiniMed
Uses
Use this model for conversational applications for medical question and answering for educational purposes only !
Direct Use
Make a gradio chatbot app to ask medical questions and get answers conversationaly.
Downstream Use [optional]
This model is for educational use only .
Further fine tunes and uses would include :
- public health & sanitation
- personal health & sanitation
- medical Q & A
Recommendations
- always evaluate this model before use
- always benchmark this model before use
- always evaluate bias before use
- do not use as is, fine tune further
How to Get Started with the Model
Use the code below to get started with the model.
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("mistralai/Mistral-7B-v0.1", 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'
# 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("https://huggingface.co./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 = "๐๐ปํ ๋์ ๋ฏธ์คํธ๋๋ฉ๋ ์ฑํ
์ ์ค์ ๊ฒ์ ํ์ํฉ๋๋ค๐๐๐ปWelcome to Tonic's MistralMed Chat๐"
description = "์ด ๊ณต๊ฐ์ ์ฌ์ฉํ์ฌ ํ์ฌ ๋ชจ๋ธ์ ํ
์คํธํ ์ ์์ต๋๋ค. [(Tonic/MistralMed)](https://huggingface.co./Tonic/MistralMed) ๋๋ ์ด ๊ณต๊ฐ์ ๋ณต์ ํ๊ณ ๋ก์ปฌ ๋๋ ๐คHuggingFace์์ ์ฌ์ฉํ ์ ์์ต๋๋ค. [Discord์์ ํจ๊ป ๋ง๋ค๊ธฐ ์ํด Discord์ ๊ฐ์
ํ์ญ์์ค](https://discord.gg/VqTxc76K3u). You can use this Space to test out the current model [(Tonic/MistralMed)](https://huggingface.co./Tonic/MistralMed) or duplicate this Space and use it locally or on ๐คHuggingFace. [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()
Training Details
Step | Training Loss |
---|---|
50 | 0.993800 |
100 | 0.620600 |
150 | 0.547100 |
200 | 0.524100 |
250 | 0.520500 |
300 | 0.559800 |
350 | 0.535500 |
400 | 0.505400 |
Training Data
{trainable params: 21260288 || all params: 3773331456 || trainable%: 0.5634354746703705}
Training Procedure
Preprocessing [optional]
Lora32bits
Speeds, Sizes, Times [optional]
metrics={'train_runtime': 1700.1608, 'train_samples_per_second': 1.882, 'train_steps_per_second': 0.235, 'total_flos': 9.585300996096e+16, 'train_loss': 0.6008514881134033, 'epoch': 0.2})
Results
TrainOutput
global_step=400, training_loss=0.6008514881134033
Summary
Environmental Impact
Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).
- Hardware Type: {{ hardware | default("[More Information Needed]", true)}}
- Hours used: {{ hours_used | default("[More Information Needed]", true)}}
- Cloud Provider: {{ cloud_provider | default("[More Information Needed]", true)}}
- Compute Region: {{ cloud_region | default("[More Information Needed]", true)}}
- Carbon Emitted: {{ co2_emitted | default("[More Information Needed]", true)}}
Technical Specifications
Model Architecture and Objective
PeftModelForCausalLM(
(base_model): LoraModel(
(model): MistralForCausalLM(
(model): MistralModel(
(embed_tokens): Embedding(32000, 4096)
(layers): ModuleList(
(0-31): 32 x MistralDecoderLayer(
(self_attn): MistralAttention(
(q_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=4096, out_features=4096, bias=False)
)
(k_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=1024, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=4096, out_features=1024, bias=False)
)
(v_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=1024, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=4096, out_features=1024, bias=False)
)
(o_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=4096, out_features=4096, bias=False)
)
(rotary_emb): MistralRotaryEmbedding()
)
(mlp): MistralMLP(
(gate_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=14336, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=4096, out_features=14336, bias=False)
)
(up_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=14336, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=4096, out_features=14336, bias=False)
)
(down_proj): Linear4bit(
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=14336, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=4096, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
(base_layer): Linear4bit(in_features=14336, out_features=4096, bias=False)
)
(act_fn): SiLUActivation()
)
(input_layernorm): MistralRMSNorm()
(post_attention_layernorm): MistralRMSNorm()
)
)
(norm): MistralRMSNorm()
)
(lm_head): Linear(
in_features=4096, out_features=32000, bias=False
(lora_dropout): ModuleDict(
(default): Dropout(p=0.05, inplace=False)
)
(lora_A): ModuleDict(
(default): Linear(in_features=4096, out_features=8, bias=False)
)
(lora_B): ModuleDict(
(default): Linear(in_features=8, out_features=32000, bias=False)
)
(lora_embedding_A): ParameterDict()
(lora_embedding_B): ParameterDict()
)
)
)
)
Compute Infrastructure
Hardware
A100
Software
peft , torch, bitsandbytes, python, huggingface
Model Card Authors [optional]
Model Card Contact
- Downloads last month
- 10