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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.
Here is an incomplate 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.
The creator of the source model has listed its license as cc-by-nc-4.0, 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: Open-Orca's OpenOrca Platypus2 13B.
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
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.
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 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/OpenOrca-Platypus2-13B-GGUF and below it, a specific filename to download, such as: openorca-platypus2-13b.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>=0.17.1
Then you can download any individual model file to the current directory, at high speed, with a command like this:
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 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
How to load this model from Python using ctransformers
First install the package
bash
1# Base ctransformers with no GPU acceleration2pip install ctransformers>=0.2.24
3# Or with CUDA GPU acceleration4pip install ctransformers[cuda]>=0.2.24
5# Or with ROCm GPU acceleration6CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
7# Or with Metal GPU acceleration for macOS systems8CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
Simple example code to load one of these GGUF models
python
1from ctransformers import AutoModelForCausalLM
23# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.4llm = AutoModelForCausalLM.from_pretrained("TheBloke/OpenOrca-Platypus2-13B-GGUF", model_file="openorca-platypus2-13b.q4_K_M.gguf", model_type="llama", gpu_layers=50)56print(llm("AI is going to"))
How to use with LangChain
Here's guides on using llama-cpp-python or ctransformers with LangChain:
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 special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: Open-Orca's OpenOrca Platypus2 13B
This model is more than the sum of its parts! We are happy to be teaming up with the Platypus team to bring you a new model which once again tops the leaderboards!
Want to visualize our full (pre-filtering) dataset? Check out our Nomic Atlas Map.
We use Language Model Evaluation Harness to run the benchmark tests above, using the same version as the HuggingFace LLM Leaderboard.
Please see below for detailed instructions on reproducing benchmark results.
AGIEval Performance
We compare our results to our base Preview2 model (using LM Evaluation Harness).
We find 112% of the base model's performance on AGI Eval, averaging 0.463.
A large part of this boost is the substantial improvement to LSAT Logical Reasoning performance.
OpenOrca-Platypus2-13B AGIEval Performance
BigBench-Hard Performance
We compare our results to our base Preview2 model (using LM Evaluation Harness).
We find 105% of the base model's performance on BigBench-Hard, averaging 0.442.
OpenOrca-Platypus2-13B BigBench-Hard Performance
Model Details
Trained by: Platypus2-13B trained by Cole Hunter & Ariel Lee; OpenOrcaxOpenChat-Preview2-13B trained by Open-Orca
Model type:OpenOrca-Platypus2-13B is an auto-regressive language model based on the Lllama 2 transformer architecture.
Language(s): English
License for Platypus2-13B base weights: Non-Commercial Creative Commons license (CC BY-NC-4.0)
License for OpenOrcaxOpenChat-Preview2-13B base weights: Llama 2 Commercial
Prompting
Prompt Template for base Platypus2-13B
### Instruction:
<prompt> (without the <>)
### Response:
Prompt Template for base OpenOrcaxOpenChat-Preview2-13B
Open-Orca/OpenOrcaxOpenChat-Preview2-13B trained using a refined subset of most of the GPT-4 data from the OpenOrca dataset.
Training Procedure
Open-Orca/Platypus2-13B was instruction fine-tuned using LoRA on 1x A100-80GB.
For training details and inference instructions please see the Platypus GitHub repo.
Llama 2 and fine-tuned variants are a new technology that carries risks with use. Testing conducted to date has been in English, and has not covered, nor could it cover all scenarios. For these reasons, as with all LLMs, Llama 2 and any fine-tuned varient's potential outputs cannot be predicted in advance, and the model may in some instances produce inaccurate, biased or other objectionable responses to user prompts. Therefore, before deploying any applications of Llama 2 variants, developers should perform safety testing and tuning tailored to their specific applications of the model.
1@software{hunterlee2023orcaplaty1
2 title = {OpenOrcaPlatypus: Llama2-13B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset and Merged with divergent STEM and Logic Dataset Model},
3 author = {Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz and Bleys Goodson and Wing Lian and Guan Wang and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
4 year = {2023},
5 publisher = {HuggingFace},
6 journal = {HuggingFace repository},
7 howpublished = {\url{https://huggingface.co/Open-Orca/OpenOrca-Platypus2-13B},
8}
9@article{platypus2023,
10 title={Platypus: Quick, Cheap, and Powerful Refinement of LLMs},
11 author={Ariel N. Lee and Cole J. Hunter and Nataniel Ruiz},
12 booktitle={arXiv preprint arxiv:2308.07317},
13 year={2023}
14}
15@software{OpenOrcaxOpenChatPreview2,
16 title = {OpenOrcaxOpenChatPreview2: Llama2-13B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset},
17 author = {Guan Wang and Bleys Goodson and Wing Lian and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"},
18 year = {2023},
19 publisher = {HuggingFace},
20 journal = {HuggingFace repository},
21 howpublished = {\url{https://https://huggingface.co/Open-Orca/OpenOrcaxOpenChat-Preview2-13B},
22}
23@software{openchat,
24 title = {{OpenChat: Advancing Open-source Language Models with Imperfect Data}},
25 author = {Wang, Guan and Cheng, Sijie and Yu, Qiying and Liu, Changling},
26 doi = {10.5281/zenodo.8105775},
27 url = {https://github.com/imoneoi/openchat},
28 version = {pre-release},
29 year = {2023},
30 month = {7},
31}
32@misc{mukherjee2023orca,
33 title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4},
34 author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah},
35 year={2023},
36 eprint={2306.02707},
37 archivePrefix={arXiv},
38 primaryClass={cs.CL}
39}
40@misc{touvron2023llama,
41 title={Llama 2: Open Foundation and Fine-Tuned Chat Models},
42 author={Hugo Touvron and Louis Martin and Kevin Stone and Peter Albert and Amjad Almahairi and Yasmine Babaei and Nikolay Bashlykov and Soumya Batra and Prajjwal Bhargava and Shruti Bhosale and Dan Bikel and Lukas Blecher and Cristian Canton Ferrer and Moya Chen and Guillem Cucurull and David Esiobu and Jude Fernandes and Jeremy Fu and Wenyin Fu and Brian Fuller and Cynthia Gao and Vedanuj Goswami and Naman Goyal and Anthony Hartshorn and Saghar Hosseini and Rui Hou and Hakan Inan and Marcin Kardas and Viktor Kerkez and Madian Khabsa and Isabel Kloumann and Artem Korenev and Punit Singh Koura and Marie-Anne Lachaux and Thibaut Lavril and Jenya Lee and Diana Liskovich and Yinghai Lu and Yuning Mao and Xavier Martinet and Todor Mihaylov and Pushkar Mishra and Igor Molybog and Yixin Nie and Andrew Poulton and Jeremy Reizenstein and Rashi Rungta and Kalyan Saladi and Alan Schelten and Ruan Silva and Eric Michael Smith and Ranjan Subramanian and Xiaoqing Ellen Tan and Binh Tang and Ross Taylor and Adina Williams and Jian Xiang Kuan and Puxin Xu and Zheng Yan and Iliyan Zarov and Yuchen Zhang and Angela Fan and Melanie Kambadur and Sharan Narang and Aurelien Rodriguez and Robert Stojnic and Sergey Edunov and Thomas Scialom},
43 year={2023},
44 eprint= arXiv 2307.09288
45}
46@misc{longpre2023flan,
47 title={The Flan Collection: Designing Data and Methods for Effective Instruction Tuning},
48 author={Shayne Longpre and Le Hou and Tu Vu and Albert Webson and Hyung Won Chung and Yi Tay and Denny Zhou and Quoc V. Le and Barret Zoph and Jason Wei and Adam Roberts},
49 year={2023},
50 eprint={2301.13688},
51 archivePrefix={arXiv},
52 primaryClass={cs.AI}
53}
54@article{hu2021lora,
55 title={LoRA: Low-Rank Adaptation of Large Language Models},
56 author={Hu, Edward J. and Shen, Yelong and Wallis, Phillip and Allen-Zhu, Zeyuan and Li, Yuanzhi and Wang, Shean and Chen, Weizhu},
57 journal={CoRR},
58 year={2021}
59}
