---
language:
- en
license: other
tags:
- medical
datasets:
- starmpcc/Asclepius-Synthetic-Clinical-Notes
model_name: Asclepius 13B
inference: false
model_creator: Junu Kim
model_link: https://huggingface.co/starmpcc/Asclepius-13B
model_type: llama
pipeline_tag: text2text-generation
quantized_by: TheBloke
base_model: starmpcc/Asclepius-13B
---

<!-- header start -->
<!-- 200823 -->
<div style="width: auto; margin-left: auto; margin-right: auto">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
    <div style="display: flex; flex-direction: column; align-items: flex-start;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>
    </div>
    <div style="display: flex; flex-direction: column; align-items: flex-end;">
        <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
    </div>
</div>
<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>
<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
<!-- header end -->

# Asclepius 13B - GGUF
- Model creator: [Junu Kim](https://huggingface.co/starmpcc)
- Original model: [Asclepius 13B](https://huggingface.co/starmpcc/Asclepius-13B)

## Description

This repo contains GGUF format model files for [Junu Kim's Asclepius 13B](https://huggingface.co/starmpcc/Asclepius-13B).

<!-- README_GGUF.md-about-gguf start -->
### About GGUF

GGUF is a new format introduced by the llama.cpp team on August 21st 2023. It is a replacement for GGML, which is no longer supported by llama.cpp.

The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.

As of August 25th, here is a list of clients and libraries that are known to support GGUF:
* [llama.cpp](https://github.com/ggerganov/llama.cpp).
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
* [KoboldCpp](https://github.com/LostRuins/koboldcpp), now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
* [LM Studio](https://lmstudio.ai/), version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), should now work, choose the `c_transformers` backend. A great web UI with many interesting features. Supports CUDA GPU acceleration.
* [ctransformers](https://github.com/marella/ctransformers), now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
* [candle](https://github.com/huggingface/candle), added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.

The clients and libraries below are expecting to add GGUF support shortly:
<!-- README_GGUF.md-about-gguf end -->

<!-- repositories-available start -->
## Repositories available

* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/Asclepius-13B-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/Asclepius-13B-GGUF)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)](https://huggingface.co/TheBloke/Asclepius-13B-GGML)
* [Junu Kim's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/starmpcc/Asclepius-13B)
<!-- repositories-available end -->

<!-- prompt-template start -->
## Prompt template: Asclepius

```
You are an intelligent clinical languge model.
Below is a snippet of patient's discharge summary and a following instruction from healthcare professional.
Write a response that appropriately completes the instruction.
The response should provide the accurate answer to the instruction, while being concise.

[Discharge Summary Begin]
Notes go here
[Discharge Summary End]

[Instruction Begin]
{prompt}
[Instruction End] 

```

<!-- prompt-template end -->
<!-- compatibility_gguf start -->
## Compatibility

These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit [6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9](https://github.com/ggerganov/llama.cpp/commit/6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9)

They are now also compatible with many third party UIs and libraries - please see the list at the top of the README.

## Explanation of quantisation methods
<details>
  <summary>Click to see details</summary>

The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw

Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_gguf end -->

<!-- README_GGUF.md-provided-files start -->
## Provided files

| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| [asclepius-13b.Q2_K.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
| [asclepius-13b.Q3_K_S.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |
| [asclepius-13b.Q3_K_M.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |
| [asclepius-13b.Q3_K_L.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |
| [asclepius-13b.Q4_0.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
| [asclepius-13b.Q4_K_S.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |
| [asclepius-13b.Q4_K_M.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |
| [asclepius-13b.Q5_0.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
| [asclepius-13b.Q5_K_S.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |
| [asclepius-13b.Q5_K_M.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |
| [asclepius-13b.Q6_K.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |
| [asclepius-13b.Q8_0.gguf](https://huggingface.co/TheBloke/Asclepius-13B-GGUF/blob/main/asclepius-13b.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |

**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
<!-- README_GGUF.md-provided-files end -->

<!-- README_GGUF.md-how-to-run start -->
## How to run in `llama.cpp`

Make sure you are using `llama.cpp` from commit [6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9](https://github.com/ggerganov/llama.cpp/commit/6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9) or later.

For compatibility with older versions of llama.cpp, or for use with third-party clients and libaries, please use GGML files instead.

```
./main -t 10 -ngl 32 -m asclepius-13b.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "You are an intelligent clinical languge model.\nBelow is a snippet of patient's discharge summary and a following instruction from healthcare professional.\nWrite a response that appropriately completes the instruction.\nThe response should provide the accurate answer to the instruction, while being concise.\n\n[Discharge Summary Begin]\nNotes go here\n[Discharge Summary End]\n\n[Instruction Begin]\nWrite a story about llamas\n[Instruction End]"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.

Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

Change `-c 4096` to the desired sequence length for this model. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.

If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`

For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)

## How to run in `text-generation-webui`

Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).
<!-- README_GGUF.md-how-to-run end -->

<!-- footer start -->
<!-- 200823 -->
## Discord

For further support, and discussions on these models and AI in general, join us at:

[TheBloke AI's Discord server](https://discord.gg/theblokeai)

## 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

**Special thanks to**: Aemon Algiz.

**Patreon special mentions**: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper Wikieł, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik Bjäreholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser


Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

<!-- footer end -->

<!-- original-model-card start -->
# Original model card: Junu Kim's Asclepius 13B

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

This is official model checkpoint for Asclepius-13B [arxiv](todo)
This model is the first publicly shareable clinical LLM, trained with synthetic data.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->



- **Model type:** Clinical LLM (Large Language Model)
- **Language(s) (NLP):** English
- **License:** CC-BY-NC-SA 4.0
- **Finetuned from model [optional]:** LLaMA-13B

### Model Sources [optional]

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/starmpcc/Asclepius
- **Paper [optional]:** TODO Arxiv
- **Data:** https://huggingface.co/datasets/starmpcc/Asclepius-Synthetic-Clinical-Notes

## Uses

<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
This model can perform below 8 clinical NLP tasks, with clincal notes.
- Named Entity Recognition
- Abbreviation Expansion
- Relation Extraction
- Temporal Information Extraction
- Coreference Resolution
- Paraphrasing
- Summarization
- Question Answering

### Direct Use

<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->

[More Information Needed]

### Downstream Use [optional]

<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->

[More Information Needed]

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

ONLY USE THIS MODEL FOR RESEARCH PURPOSE!!

## How to Get Started with the Model

```python
prompt = """You are an intelligent clinical languge model.
Below is a snippet of patient's discharge summary and a following instruction from healthcare professional.
Write a response that appropriately completes the instruction.
The response should provide the accurate answer to the instruction, while being concise.

[Discharge Summary Begin]
{note}
[Discharge Summary End]

[Instruction Begin]
{question}
[Instruction End] 
"""

from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("starmpcc/Asclepius-13B")
model = AutoModel.from_pretrained("starmpcc/Asclepius-13B")

note = "This is a sample note"
question = "What is the diagnosis?"

model_input = prompt.format(note=note, question=question)
input_ids = tokenizer(model_input, return_tensors="pt").input_ids
output = model.generate(input_ids)
print(tokenizer.decode(output[0]))
```

## Training Details

### Training Data

<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->

https://huggingface.co/datasets/starmpcc/Asclepius-Synthetic-Clinical-Notes

### Training Procedure 

<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
- Initial training was conducted using causal language modeling on synthetic clinical notes.
- It was then fine-tuned with clinical instruction-response pairs.
- For a comprehensive overview of our methods, our upcoming paper will serve as a resource.

#### Training Hyperparameters

- We followed config used in [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca)
- 
#### Speeds, Sizes, Times [optional]

<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
- Pre-Training (1 epoch): 1h 52m with 8x A100 80G
- Instruction Fine-Tuning (3 epoch): 12h 16m with 8x A100 80G



## Citation [optional]

<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->

**BibTeX:**

[More Information Needed]

**APA:**

[More Information Needed]




<!-- original-model-card end -->