TheBloke/SG-Raccoon-Yi-55B-200k-GGUF · Hugging Face (2024)

• Model creator: Marco Lironi
• Original model: SG Raccoon Yi 55B 200K

Description

This repo contains GGUF format model files for Marco Lironi's SG Raccoon Yi 55B 200K.

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

Prompt template: Orca-Vicuna

SYSTEM: {system_message}USER: {prompt}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 sg-raccoon-yi-55b-200k.Q6_K.gguf-split-* > sg-raccoon-yi-55b-200k.Q6_K.gguf && rm sg-raccoon-yi-55b-200k.Q6_K.gguf-split-*cat sg-raccoon-yi-55b-200k.Q8_0.gguf-split-* > sg-raccoon-yi-55b-200k.Q8_0.gguf && rm sg-raccoon-yi-55b-200k.Q8_0.gguf-split-*

COPY /B sg-raccoon-yi-55b-200k.Q6_K.gguf-split-a + sg-raccoon-yi-55b-200k.Q6_K.gguf-split-b sg-raccoon-yi-55b-200k.Q6_K.ggufdel sg-raccoon-yi-55b-200k.Q6_K.gguf-split-a sg-raccoon-yi-55b-200k.Q6_K.gguf-split-bCOPY /B sg-raccoon-yi-55b-200k.Q8_0.gguf-split-a + sg-raccoon-yi-55b-200k.Q8_0.gguf-split-b sg-raccoon-yi-55b-200k.Q8_0.ggufdel sg-raccoon-yi-55b-200k.Q8_0.gguf-split-a sg-raccoon-yi-55b-200k.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/SG-Raccoon-Yi-55B-200k-GGUF and below it, a specific filename to download, such as: sg-raccoon-yi-55b-200k.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/SG-Raccoon-Yi-55B-200k-GGUF sg-raccoon-yi-55b-200k.Q4_K_M.gguf --local-dir . --local-dir-use-symlinks False

huggingface-cli download TheBloke/SG-Raccoon-Yi-55B-200k-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/SG-Raccoon-Yi-55B-200k-GGUF sg-raccoon-yi-55b-200k.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 sg-raccoon-yi-55b-200k.Q4_K_M.gguf --color -c 200000 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "SYSTEM: {system_message}\nUSER: {prompt}\nASSISTANT:"

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

Change -c 200000 to the desired sequence length. 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. Note that longer sequence lengths require much more resources, so you may need to reduce this value.

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 can be found in the text-generation-webui documentation, here: text-generation-webui/docs/04 ‐ Model Tab.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries. Note that at the time of writing (Nov 27th 2023), ctransformers has not been updated for some time and is not compatible with some recent models. Therefore I recommend you use llama-cpp-python.

How to load this model in Python code, using llama-cpp-python

For full documentation, please see: llama-cpp-python docs.

First install the package

Run one of the following commands, according to your system:

# Base ctransformers with no GPU accelerationpip install llama-cpp-python# With NVidia CUDA accelerationCMAKE_ARGS="-DLLAMA_CUBLAS=on" pip install llama-cpp-python# Or with OpenBLAS accelerationCMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" pip install llama-cpp-python# Or with CLBLast accelerationCMAKE_ARGS="-DLLAMA_CLBLAST=on" pip install llama-cpp-python# Or with AMD ROCm GPU acceleration (Linux only)CMAKE_ARGS="-DLLAMA_HIPBLAS=on" pip install llama-cpp-python# Or with Metal GPU acceleration for macOS systems onlyCMAKE_ARGS="-DLLAMA_METAL=on" pip install llama-cpp-python# In windows, to set the variables CMAKE_ARGS in PowerShell, follow this format; eg for NVidia CUDA:$env:CMAKE_ARGS = "-DLLAMA_OPENBLAS=on"pip install llama-cpp-python

Simple llama-cpp-python example code

from llama_cpp import Llama# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.llm = Llama( model_path="./sg-raccoon-yi-55b-200k.Q4_K_M.gguf", # Download the model file first n_ctx=200000, # The max sequence length to use - note that longer sequence lengths require much more resources n_threads=8, # The number of CPU threads to use, tailor to your system and the resulting performance n_gpu_layers=35 # The number of layers to offload to GPU, if you have GPU acceleration available)# Simple inference exampleoutput = llm( "SYSTEM: {system_message}\nUSER: {prompt}\nASSISTANT:", # Prompt max_tokens=512, # Generate up to 512 tokens stop=["</s>"], # Example stop token - not necessarily correct for this specific model! Please check before using. echo=True # Whether to echo the prompt)# Chat Completion APIllm = Llama(model_path="./sg-raccoon-yi-55b-200k.Q4_K_M.gguf", chat_format="llama-2") # Set chat_format according to the model you are usingllm.create_chat_completion( messages = [ {"role": "system", "content": "You are a story writing assistant."}, { "role": "user", "content": "Write a story about llamas." } ])

How to use with LangChain

Here are guides on using llama-cpp-python and ctransformers with LangChain:

• LangChain + llama-cpp-python
• LangChain + ctransformers

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!

Thanks to Clay from gpus.llm-utils.org!

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: Brandon Frisco, LangChain4j, Spiking Neurons AB, transmissions 11, Joseph William Delisle, Nitin Borwankar, Willem Michiel, Michael Dempsey, vamX, Jeffrey Morgan, zynix, jjj, Omer Bin Jawed, Sean Connelly, jinyuan sun, Jeromy Smith, Shadi, Pawan Osman, Chadd, Elijah Stavena, Illia Dulskyi, Sebastain Graf, Stephen Murray, terasurfer, Edmond Seymore, Celu Ramasamy, Mandus, Alex, biorpg, Ajan Kanaga, Clay Pascal, Raven Klaugh, 阿明, K, ya boyyy, usrbinkat, Alicia Loh, John Villwock, ReadyPlayerEmma, Chris Smitley, Cap'n Zoog, fincy, GodLy, S_X, sidney chen, Cory Kujawski, OG, Mano Prime, AzureBlack, Pieter, Kalila, Spencer Kim, Tom X Nguyen, Stanislav Ovsiannikov, Michael Levine, Andrey, Trailburnt, Vadim, Enrico Ros, Talal Aujan, Brandon Phillips, Jack West, Eugene Pentland, Michael Davis, Will Dee, webtim, Jonathan Leane, Alps Aficionado, Rooh Singh, Tiffany J. Kim, theTransient, Luke @flexchar, Elle, Caitlyn Gatomon, Ari Malik, subjectnull, Johann-Peter Hartmann, Trenton Dambrowitz, Imad Khwaja, Asp the Wyvern, Emad Mostaque, Rainer Wilmers, Alexandros Triantafyllidis, Nicholas, Pedro Madruga, SuperWojo, Harry Royden McLaughlin, James Bentley, Olakabola, David Ziegler, Ai Maven, Jeff Scroggin, Nikolai Manek, Deo Leter, Matthew Berman, Fen Risland, Ken Nordquist, Manuel Alberto Morcote, Luke Pendergrass, TL, Fred von Graf, Randy H, Dan Guido, NimbleBox.ai, Vitor Caleffi, Gabriel Tamborski, knownsqashed, Lone Striker, Erik Bjäreholt, John Detwiler, Leonard Tan, Iucharbius

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

The first 55B auto-regressive causal LM created by combining 2x finetuned Yi 34b with 200K context into one.

SYSTEM: <ANY SYSTEM CONTEXT>USER:ASSISTANT:

The models used in the merge are Tess-M-v1.3 and Nous-Capybara-34B.

The layer ranges used are as follows:

- model: migtissera/Tess-M-v1.3 layer_range: [0, 14]- model: NousResearch/Nous-Capybara-34B layer_range: [7, 21]- model: migtissera/Tess-M-v1.3 layer_range: [15, 29]- model: NousResearch/Nous-Capybara-34B layer_range: [22, 36]- model: migtissera/Tess-M-v1.3 layer_range: [30, 44]- model: NousResearch/Nous-Capybara-34B layer_range: [37, 51]- model: migtissera/Tess-M-v1.3 layer_range: [45, 59]

Being a Yi model, try disabling the BOS token and/or running a lower temperature with MinP (and no other samplers) if output doesn't seem right. Yi tends to run "hot" by default.

Sometimes the model "spells out" the stop token as like Capybara, so you may need to add as an additional stopping condition.

Coming soon.

• Special thanks to MSS for sponsoring this project

• @chargoddard for developing the framework used to merge the model - mergekit.

• Great thanks to @Undi95 for helping figuring out model merge options

• Also credits to the 01-ai team for their amazing models

• This merged model is inspired by Goliath 120B