Discolm 70B GGUF

🚀 DiscoLM 70B - GGUF

This repository contains GGUF format model files for Disco Research's DiscoLM 70B, offering various quantization options for different use - cases.

📚 Documentation

Model Information

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](https://github.com/oobabooga/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.
• GPT4All, a free and open source local running GUI, supporting Windows, Linux and macOS with full GPU accel.
• LM Studio, an easy - to - use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration. Linux available, in beta as of 27/11/2023.
• [LoLLMS Web UI](https://github.com/ParisNeo/lollms - webui), 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.
• [llama - cpp - python](https://github.com/abetlen/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.
• ctransformers, a Python library with GPU accel, LangChain support, and OpenAI - compatible AI server. Note, as of time of writing (November 27th 2023), ctransformers has not been updated in a long time and does not support many recent models.

Repositories available

• [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/DiscoLM - 70B - AWQ)
• [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/DiscoLM - 70B - GPTQ)
• [2, 3, 4, 5, 6 and 8 - bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/DiscoLM - 70B - GGUF)
• [Disco Research's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/DiscoResearch/DiscoLM - 70b)

Prompt template: ChatML

<|im_start|>system
{system_message}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

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

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

COPY /B discolm - 70b.Q8_0.gguf - split - a + discolm - 70b.Q8_0.gguf - split - b discolm - 70b.Q8_0.gguf
del discolm - 70b.Q8_0.gguf - split - a discolm - 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/DiscoLM - 70B - GGUF and below it, a specific filename to download, such as: discolm - 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/DiscoLM - 70B - GGUF discolm - 70b.Q4_K_M.gguf --local - dir . --local - dir - use - symlinks False

huggingface - cli download TheBloke/DiscoLM - 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/DiscoLM - 70B - GGUF discolm - 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 35 -m discolm - 70b.Q4_K_M.gguf --color -c 8192 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant"

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

Change -c 8192 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K -