datasets:
- pg19
inference: false
library_name: transformers
license: llama2
metrics:
- perplexity
model_creator: NousResearch
model_link: https://huggingface.co/NousResearch/Yarn-Llama-2-13b-64k
model_name: Yarn Llama 2 13B 64K
model_type: llama
quantized_by: TheBloke
![TheBlokeAI](https://i.imgur.com/EBdldam.jpg)
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Yarn Llama 2 13B 64K - GGUF
- Model creator: NousResearch
- Original model: Yarn Llama 2 13B 64K
Description
This repo contains GGUF format model files for NousResearch's Yarn Llama 2 13B 64K.
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.
The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.
As of August 25th, here is a list of clients and libraries that are known to support GGUF:
- llama.cpp.
- text-generation-webui, the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
- KoboldCpp, now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
- LM Studio, version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
- LoLLMS Web UI, should now work, choose the
c_transformers
backend. A great web UI with many interesting features. Supports CUDA GPU acceleration. - ctransformers, now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
- llama-cpp-python, supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
- candle, added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.
The clients and libraries below are expecting to add GGUF support shortly:
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
These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9
They are now also compatible with many third party UIs and libraries - please see the list at the top of the README.
Explanation of quantisation 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
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 |
---|---|---|---|---|---|
yarn-llama-2-13b-64k.Q2_K.gguf | Q2_K | 2 | 5.43 GB | 7.93 GB | smallest, significant quality loss - not recommended for most purposes |
yarn-llama-2-13b-64k.Q3_K_S.gguf | Q3_K_S | 3 | 5.66 GB | 8.16 GB | very small, high quality loss |
yarn-llama-2-13b-64k.Q3_K_M.gguf | Q3_K_M | 3 | 6.34 GB | 8.84 GB | very small, high quality loss |
yarn-llama-2-13b-64k.Q3_K_L.gguf | Q3_K_L | 3 | 6.93 GB | 9.43 GB | small, substantial quality loss |
yarn-llama-2-13b-64k.Q4_0.gguf | Q4_0 | 4 | 7.37 GB | 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |
yarn-llama-2-13b-64k.Q4_K_S.gguf | Q4_K_S | 4 | 7.41 GB | 9.91 GB | small, greater quality loss |
yarn-llama-2-13b-64k.Q4_K_M.gguf | Q4_K_M | 4 | 7.87 GB | 10.37 GB | medium, balanced quality - recommended |
yarn-llama-2-13b-64k.Q5_0.gguf | Q5_0 | 5 | 8.97 GB | 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |
yarn-llama-2-13b-64k.Q5_K_S.gguf | Q5_K_S | 5 | 8.97 GB | 11.47 GB | large, low quality loss - recommended |
yarn-llama-2-13b-64k.Q5_K_M.gguf | Q5_K_M | 5 | 9.23 GB | 11.73 GB | large, very low quality loss - recommended |
yarn-llama-2-13b-64k.Q6_K.gguf | Q6_K | 6 | 10.68 GB | 13.18 GB | very large, extremely low quality loss |
yarn-llama-2-13b-64k.Q8_0.gguf | Q8_0 | 8 | 13.83 GB | 16.33 GB | very large, extremely low quality loss - not recommended |
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 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.
For compatibility with older versions of llama.cpp, or for use with third-party clients and libaries, please use GGML files instead.
./main -t 10 -ngl 32 -m yarn-llama-2-13b-64k.q4_K_M.gguf --color -c 4096 --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 4096
to the desired sequence length for this model. 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.
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:
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: Kacper Wikieł, knownsqashed, Leonard Tan, Asp the Wyvern, Daniel P. Andersen, Luke Pendergrass, Stanislav Ovsiannikov, RoA, Dave, Ai Maven, Kalila, Will Dee, Imad Khwaja, Nitin Borwankar, Joseph William Delisle, Tony Hughes, Cory Kujawski, Rishabh Srivastava, Russ Johnson, Stephen Murray, Lone Striker, Johann-Peter Hartmann, Elle, J, Deep Realms, SuperWojo, Raven Klaugh, Sebastain Graf, ReadyPlayerEmma, Alps Aficionado, Mano Prime, Derek Yates, Gabriel Puliatti, Mesiah Bishop, Magnesian, Sean Connelly, biorpg, Iucharbius, Olakabola, Fen Risland, Space Cruiser, theTransient, Illia Dulskyi, Thomas Belote, Spencer Kim, Pieter, John Detwiler, Fred von Graf, Michael Davis, Swaroop Kallakuri, subjectnull, Clay Pascal, Subspace Studios, Chris Smitley, Enrico Ros, usrbinkat, Steven Wood, alfie_i, David Ziegler, Willem Michiel, Matthew Berman, Andrey, Pyrater, Jeffrey Morgan, vamX, LangChain4j, Luke @flexchar, Trenton Dambrowitz, Pierre Kircher, Alex, Sam, James Bentley, Edmond Seymore, Eugene Pentland, Pedro Madruga, Rainer Wilmers, Dan Guido, Nathan LeClaire, Spiking Neurons AB, Talal Aujan, zynix, Artur Olbinski, Michael Levine, 阿明, K, John Villwock, Nikolai Manek, Femi Adebogun, senxiiz, Deo Leter, NimbleBox.ai, Viktor Bowallius, Geoffrey Montalvo, Mandus, Ajan Kanaga, ya boyyy, Jonathan Leane, webtim, Brandon Frisco, danny, Alexandros Triantafyllidis, Gabriel Tamborski, Randy H, terasurfer, Vadim, Junyu Yang, Vitor Caleffi, Chadd, transmissions 11
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: NousResearch's Yarn Llama 2 13B 64K
Model Card: Nous-Yarn-Llama-2-13b-64k
Model Description
Nous-Yarn-Llama-2-13b-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-2-13b-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.