README.md

---
license: cc
language:
- en
library_name: transformers
pipeline_tag: text-generation
tags:
- medical
---
# Medguanaco LoRA 33b 8bit


## Table of Contents

[Model Description](#model-description)  
- [Architecture](#architecture)    
- [Training Data](#trainig-data)  
[Model Usage](#model-usage)  
[Limitations](#limitations)  

## Model Description
### Architecture
`nmitchko/medguanaco-lora-33b-8bit` is a large language model LoRa specifically fine-tuned for medical domain tasks.
It is based on the Guanaco LORA of LLaMA weighing in at 33B parameters. 
The primary goal of this model is to improve question-answering and medical dialogue tasks.
It was trained using [LoRA](https://arxiv.org/abs/2106.09685) and reduced to 8bit, to reduce memory footprint. 

Steps to load this model:
1. Load Guanaco-33b-merged https://huggingface.co/timdettmers/guanaco-33b-merged **in 8-bit**
    * I recommend using text-generation-ui to test it out: https://github.com/oobabooga/text-generation-webui/tree/main
2. Apply this LoRA to the model, this was trainied in 8-bit mode and results may vary in higher dimensions.


```python
# Some llama or alpaca model 65b
base_model = "timdettmers/guanaco-33b-merged"
model = LlamaForCausalLM.from_pretrained(
    base_model,    
    load_in_8bit=load_8bit,
    torch_dtype=torch.float16
)
# Load the LORA on top
lora_weights = "nmitchko/medguanaco-lora-33b-8bit"
model = PeftModel.from_pretrained(
    model,
    lora_weights,
    torch_dtype=torch.float16
)
```

---

> The following README is taken from the source page [medalpaca](https://huggingface.co/medalpaca/medalpaca-lora-13b-8bit)

### Training Data
The training data for this project was sourced from various resources. 
Firstly, we used Anki flashcards to automatically generate questions, 
from the front of the cards and anwers from the back of the card. 
Secondly, we generated medical question-answer pairs from [Wikidoc](https://www.wikidoc.org/index.php/Main_Page). 
We extracted paragraphs with relevant headings, and used Chat-GPT 3.5 
to generate questions from the headings and using the corresponding paragraphs 
as answers. This dataset is still under development and we believe 
that approximately 70% of these question answer pairs are factual correct. 
Thirdly, we used StackExchange to extract question-answer pairs, taking the 
top-rated question from five categories: Academia, Bioinformatics, Biology, 
Fitness, and Health. Additionally, we used a dataset from [ChatDoctor](https://arxiv.org/abs/2303.14070) 
consisting of 200,000 question-answer pairs, available at https://github.com/Kent0n-Li/ChatDoctor.

| Source                      | n items |
|------------------------------|--------|
| ChatDoc large                | 200000 |
| wikidoc                      | 67704  |
| Stackexchange academia       | 40865  |
| Anki flashcards              | 33955  |
| Stackexchange biology        | 27887  |
| Stackexchange fitness        | 9833   |
| Stackexchange health         | 7721   |
| Wikidoc patient information  | 5942   |
| Stackexchange bioinformatics | 5407   |


## Limitations
The model may not perform effectively outside the scope of the medical domain.
The training data primarily targets the knowledge level of medical students, 
which may result in limitations when addressing the needs of board-certified physicians.
The model has not been tested in real-world applications, so its efficacy and accuracy are currently unknown. 
It should never be used as a substitute for a doctor's opinion and must be treated as a research tool only.