Med42 70B GGUF

🚀 Med42 70B - GGUF

This repository provides GGUF format model files for M42 Health's Med42 70B, offering efficient and flexible solutions for text generation tasks in the medical field.

📚 Documentation

Description

This repo contains GGUF format model files for M42 Health's Med42 70B. These files were quantised using hardware kindly provided by Massed Compute.

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.

Here is an incomplete list of clients and libraries that are known to support GGUF:

• llama.cpp. The source project for GGUF. Offers a CLI and a server option.
• text-generation-webui, the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
• KoboldCpp, a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
• LM Studio, an easy - to - use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
• LoLLMS Web UI, a great web UI with many interesting and unique features, including a full model library for easy model selection.
• Faraday.dev, an attractive and easy to use character - based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
• 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.
• candle, a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

• AWQ model(s) for GPU inference.
• GPTQ models for GPU inference, with multiple quantisation parameter options.
• 2, 3, 4, 5, 6 and 8 - bit GGUF models for CPU+GPU inference
• M42 Health's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions

Prompt template: Med42

<|system|>: You are a helpful medical assistant created by M42 Health in the UAE.
<|prompter|>:{prompt}
<|assistant|>:

Licensing

The creator of the source model has listed its license as other, and this quantization has therefore used that same license.

As this model is based on Llama 2, it is also subject to the Meta Llama 2 license terms, and the license files for that are additionally included. It should therefore be considered as being claimed to be licensed under both licenses. I contacted Hugging Face for clarification on dual licensing but they do not yet have an official position. Should this change, or should Meta provide any feedback on this situation, I will update this section accordingly.

In the meantime, any questions regarding licensing, and in particular how these two licenses might interact, should be directed to the original model repository: M42 Health's Med42 70B.

Compatibility

These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d

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

Explanation of quantisation methods

Provided files

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.

Q6_K and Q8_0 files are split and require joining

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.

cat med42-70b.Q6_K.gguf-split-* > med42-70b.Q6_K.gguf && rm med42-70b.Q6_K.gguf-split-*
cat med42-70b.Q8_0.gguf-split-* > med42-70b.Q8_0.gguf && rm med42-70b.Q8_0.gguf-split-*

COPY /B med42-70b.Q6_K.gguf-split-a + med42-70b.Q6_K.gguf-split-b med42-70b.Q6_K.gguf
del med42-70b.Q6_K.gguf-split-a med42-70b.Q6_K.gguf-split-b

COPY /B med42-70b.Q8_0.gguf-split-a + med42-70b.Q8_0.gguf-split-b med42-70b.Q8_0.gguf
del med42-70b.Q8_0.gguf-split-a med42-70b.Q8_0.gguf-split-b

How to download GGUF files

Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

The following clients/libraries will automatically download models for you, providing a list of available models to choose from:

• LM Studio
• LoLLMS Web UI
• Faraday.dev

In text-generation-webui

Under Download Model, you can enter the model repo: TheBloke/med42-70B-GGUF and below it, a specific filename to download, such as: med42-70b.Q4_K_M.gguf.

Then click Download.

On the command line, including multiple files at once

I recommend using the huggingface-hub Python library:

pip3 install huggingface-hub

Then you can download any individual model file to the current directory, at high speed, with a command like this:

huggingface-cli download TheBloke/med42-70B-GGUF med42-70b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

huggingface-cli download TheBloke/med42-70B-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'

pip3 install hf_transfer

HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/med42-70B-GGUF med42-70b.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

Example llama.cpp command

Make sure you are using llama.cpp from commit d0cee0d or later.

./main -ngl 32 -m med42-70b.Q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|system|>: You are a helpful medical assistant created by M42 Health in the UAE.\n<|prompter|>:{prompt}\n<|assistant|>:"

Change -ngl 32 to the number of layers you want to offload to the GPU.

⚠️ Important Note

You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.

💡 Usage Tip

I recommend using the huggingface-hub Python library to download model files at high speed.