# medalpaca-13B-GGML
This is GGML format quantised 4-bit, 5-bit and 8-bit GGML models of [Medalpaca 13B](https://huggingface.co/medalpaca/medalpaca-13b).
This repo is the result of quantising to 4-bit, 5-bit and 8-bit GGML for CPU (+CUDA) inference using [llama.cpp](https://github.com/ggerganov/llama.cpp).
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/medalpaca-13B-GPTQ-4bit).
* [4-bit, 5-bit 8-bit GGML models for llama.cpp CPU (+CUDA) inference](https://huggingface.co/TheBloke/medalpaca-13B-GGML).
* [medalpaca's float32 HF format repo for GPU inference and further conversions](https://huggingface.co/medalpaca/medalpaca-13b).
## THE FILES IN MAIN BRANCH REQUIRES LATEST LLAMA.CPP (May 19th 2023 - commit 2d5db48)!
llama.cpp recently made another breaking change to its quantisation methods - https://github.com/ggerganov/llama.cpp/pull/1508
I have quantised the GGML files in this repo with the latest version. Therefore you will require llama.cpp compiled on May 19th or later (commit `2d5db48` or later) to use them.
For files compatible with the previous version of llama.cpp, please see branch `previous_llama_ggmlv2`.
## Provided files
| Name | Quant method | Bits | Size | RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
`medalpaca-13B.ggmlv3.q4_0.bin` | q4_0 | 4bit | 8.14GB | 10.5GB | 4-bit. |
`medalpaca-13B.ggmlv3.q4_1.bin` | q4_1 | 4bit | 8.14GB | 10.5GB | 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
`medalpaca-13B.ggmlv3.q5_0.bin` | q5_0 | 5bit | 8.95GB | 11.0GB | 5-bit. Higher accuracy, higher resource usage and slower inference. |
`medalpaca-13B.ggmlv3.q5_1.bin` | q5_1 | 5bit | 9.76GB | 12.25GB | 5-bit. Even higher accuracy, and higher resource usage and slower inference. |
`medalpaca-13B.ggmlv3.q8_0.bin` | q8_0 | 8bit | 14.6GB | 17GB | 8-bit. Almost indistinguishable from float16. Huge resource use and slow. Not recommended for normal use. |
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 8 -m medalpaca-13B.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: write a story about llamas ### Response:"
```
Change `-t 8` to the number of physical CPU cores you have.
## How to run in `text-generation-webui`
GGML models can be loaded into text-generation-webui by installing the llama.cpp module, then placing the ggml model file in a model folder as usual.
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
Note: at this time text-generation-webui may not support the new May 19th llama.cpp quantisation methods for q4_0, q4_1 and q8_0 files.
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
# Original model card: MedAlpaca 13b
## Table of Contents
[Model Description](#model-description)
- [Architecture](#architecture)
- [Training Data](#trainig-data)
[Model Usage](#model-usage)
[Limitations](#limitations)
## Model Description
### Architecture
`medalpaca-13b` is a large language model specifically fine-tuned for medical domain tasks.
It is based on LLaMA (Large Language Model Meta AI) and contains 13 billion parameters.
The primary goal of this model is to improve question-answering and medical dialogue tasks.
### 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 |
## Model Usage
To evaluate the performance of the model on a specific dataset, you can use the Hugging Face Transformers library's built-in evaluation scripts. Please refer to the evaluation guide for more information.
Inference
You can use the model for inference tasks like question-answering and medical dialogues using the Hugging Face Transformers library. Here's an example of how to use the model for a question-answering task:
```python
from transformers import pipeline
qa_pipeline = pipeline("question-answering", model="medalpaca/medalpaca-7b", tokenizer="medalpaca/medalpaca-7b")
question = "What are the symptoms of diabetes?"
context = "Diabetes is a metabolic disease that causes high blood sugar. The symptoms include increased thirst, frequent urination, and unexplained weight loss."
answer = qa_pipeline({"question": question, "context": context})
print(answer)
```
## 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.
