Yarn-Llama-2-7B-64K-GGML

<!-- 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 -->

Yarn Llama 2 7B 64K - GGML

• Model creator: NousResearch
• Original model: Yarn Llama 2 7B 64K

Description

This repo contains GGML format model files for NousResearch's Yarn Llama 2 7B 64K.

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The GGML format has now been superseded by GGUF.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

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

Prompt template: None

{prompt}

<!-- compatibility_ggml start -->

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

<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
• 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.

</details> <!-- compatibility_ggml end -->

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.

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 yarn-llama-2-7b-64k.ggmlv3.q4_K_M.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Write a story about llamas"

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.

<!-- footer start --> <!-- 200823 -->

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.

• 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: NousResearch's Yarn Llama 2 7B 64K

Model Card: Nous-Yarn-Llama-2-7b-64k

Preprint (arXiv)
GitHub

Model Description

Nous-Yarn-Llama-2-7b-64k is a state-of-the-art language model for long context, further pretrained on long context data for 400 steps.
This model is the Flash Attention 2 patched version of the original model: https://huggingface.co/conceptofmind/Yarn-Llama-2-7b-64k

Note that this model requires the Flash Attention library in order to function correctly, see the Model Usage section for installation instructions.

Model Training

Starting from the base Llama 2 models, this model was further pretrained on a subset of the PG19 dataset, allowing it to effectively utilize up to 64k tokens of context.

Collaborators

• bloc97: Methods, Paper and evals
• @theemozilla: Methods, Paper and evals
• @EnricoShippole: Model Training
• honglu2875: Paper and evals

The authors would like to thank Stability AI, Carper AI, and Eleuther AI for their generous support of significant computing resources that enabled the training of these models and the completion of this research. We would also like to thank Jonathan Tow and Dakota Mahan directly for their help in advising on the use of the Stability AI compute cluster. Additionally, we would like to thank a16z, and PygmalionAI, for providing resources to run evaluations and experiments on the models.

Usage and Prompt Format

Install FA2 and Rotary Extensions:

pip install flash-attn --no-build-isolation
pip install git+https://github.com/HazyResearch/flash-attention.git#subdirectory=csrc/rotary

There are no specific prompt formats as this is a pretrained base model.

Benchmark Results

TODO

Future Plans

We plan to continue training when we have more compute and to improve the dataset and/or instruct tune the models in order to improve the long context performance even further.

Model Usage

The model is available for download on HuggingFace.