Hugging Face's logo

TheBloke
/
Asclepius-13B-GGML

Text2Text Generation
Transformers
English
llama
medical
text-generation-inference
Model card Files Community
Edit model card
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

Asclepius 13B - GGML

Description

This repo contains GGML format model files for Junu Kim's Asclepius 13B.

Important note regarding GGML files.

The GGML format has now been superseded by GGUF. As of August 21st 2023, llama.cpp no longer supports GGML models. Third party clients and libraries are expected to still support it for a time, but many may also drop support.

Please use the GGUF models instead.

About GGML

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

  • text-generation-webui, the most popular web UI. Supports NVidia CUDA GPU acceleration.
  • KoboldCpp, a powerful GGML web UI with GPU acceleration on all platforms (CUDA and OpenCL). Especially good for story telling.
  • LM Studio, a fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
  • LoLLMS Web UI, a great web UI with CUDA GPU acceleration via the c_transformers backend.
  • ctransformers, a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
  • llama-cpp-python, a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.

Repositories available

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]

Compatibility

These quantised GGML files are compatible with llama.cpp between June 6th (commit 2d43387) and August 21st 2023.

For support with latest llama.cpp, please use GGUF files instead.

The final llama.cpp commit with support for GGML was: dadbed99e65252d79f81101a392d0d6497b86caa

As of August 23rd 2023 they are still compatible with all UIs, libraries and utilities which use GGML. This may change in the future.

Explanation of the new k-quant methods

Click to see details

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
  • GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

Refer to the Provided Files table below to see what files use which methods, and how.

Provided files

Name Quant method Bits Size Max RAM required Use case
asclepius-13b.ggmlv3.Q2_K.bin Q2_K 2 5.51 GB 8.01 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors.
asclepius-13b.ggmlv3.Q3_K_S.bin Q3_K_S 3 5.66 GB 8.16 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
asclepius-13b.ggmlv3.Q3_K_M.bin Q3_K_M 3 6.31 GB 8.81 GB New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
asclepius-13b.ggmlv3.Q3_K_L.bin Q3_K_L 3 6.93 GB 9.43 GB New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K
asclepius-13b.ggmlv3.Q4_0.bin Q4_0 4 7.37 GB 9.87 GB Original quant method, 4-bit.
asclepius-13b.ggmlv3.Q4_K_S.bin Q4_K_S 4 7.37 GB 9.87 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
asclepius-13b.ggmlv3.Q4_K_M.bin Q4_K_M 4 7.87 GB 10.37 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K
asclepius-13b.ggmlv3.Q4_1.bin Q4_1 4 8.17 GB 10.67 GB Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
asclepius-13b.ggmlv3.Q5_0.bin Q5_0 5 8.97 GB 11.47 GB Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
asclepius-13b.ggmlv3.Q5_K_S.bin Q5_K_S 5 8.97 GB 11.47 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
asclepius-13b.ggmlv3.Q5_K_M.bin Q5_K_M 5 9.23 GB 11.73 GB New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K
asclepius-13b.ggmlv3.Q5_1.bin Q5_1 5 9.78 GB 12.28 GB Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
asclepius-13b.ggmlv3.Q6_K.bin Q6_K 6 10.68 GB 13.18 GB New k-quant method. Uses GGML_TYPE_Q8_K for all tensors - 6-bit quantization
asclepius-13b.ggmlv3.Q8_0.bin Q8_0 8 13.79 GB 16.29 GB Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users.

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.

How to run in llama.cpp

Make sure you are using llama.cpp from commit dadbed99e65252d79f81101a392d0d6497b86caa or earlier.

For compatibility with latest llama.cpp, please use GGUF files instead.

./main -t 10 -ngl 32 -m asclepius-13b.ggmlv3.q4_K_M.bin --color -c 2048 --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 2048 to the desired sequence length for this model. For example, -c 4096 for a Llama 2 model. For models that use RoPE, add --rope-freq-base 10000 --rope-freq-scale 0.5 for doubled context, or --rope-freq-base 10000 --rope-freq-scale 0.25 for 4x context.

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

How to run in text-generation-webui

Further instructions here: text-generation-webui/docs/llama.cpp.md.

Discord

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

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the 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.

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.

Original model card: Junu Kim's Asclepius 13B

Model Card for Model ID

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

Model Details

Model Description

  • 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]

Uses

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

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

ONLY USE THIS MODEL FOR RESEARCH PURPOSE!!

How to Get Started with the Model 

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

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

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

Speeds, Sizes, Times [optional]

  • Pre-Training (1 epoch): 1h 52m with 8x A100 80G
  • Instruction Fine-Tuning (3 epoch): 12h 16m with 8x A100 80G

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Downloads last month
8
Text2Text Generation
Inference API (serverless) has been turned off for this model.

Finetuned from

Dataset used to train TheBloke/Asclepius-13B-GGML