James WYang's BigTrans GGML
These files are GGML format model files for James WYang's BigTrans.
GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:
Repositories available
- 4-bit GPTQ models for GPU inference
- 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference
- Unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt format: Alpaca
### Instruction: please translate the following into French: Large language models are the future
### Response:
Compatibility
Original llama.cpp quant methods: q4_0, q4_1, q5_0, q5_1, q8_0
I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.
These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.
New k-quant methods: q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K
These new quantisation methods are compatible with llama.cpp as of June 6th, commit 2d43387.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.
Explanation of the new k-quant methods
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.
Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
|---|---|---|---|---|---|
| bigtrans-13b.ggmlv3.q2_K.bin | q2_K | 2 | 5.64 GB | 8.14 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| bigtrans-13b.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 7.07 GB | 9.57 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| bigtrans-13b.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.45 GB | 8.95 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| bigtrans-13b.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.80 GB | 8.30 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| bigtrans-13b.ggmlv3.q4_0.bin | q4_0 | 4 | 7.45 GB | 9.95 GB | Original llama.cpp quant method, 4-bit. |
| bigtrans-13b.ggmlv3.q4_1.bin | q4_1 | 4 | 8.28 GB | 10.78 GB | Original llama.cpp quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| bigtrans-13b.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 8.02 GB | 10.52 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| bigtrans-13b.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.52 GB | 10.02 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| bigtrans-13b.ggmlv3.q5_0.bin | q5_0 | 5 | 9.10 GB | 11.60 GB | Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| bigtrans-13b.ggmlv3.q5_1.bin | q5_1 | 5 | 9.93 GB | 12.43 GB | Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| bigtrans-13b.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.40 GB | 11.90 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| bigtrans-13b.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 9.14 GB | 11.64 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| bigtrans-13b.ggmlv3.q6_K.bin | q6_K | 6 | 10.86 GB | 13.36 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| bigtrans-13b.ggmlv3.q8_0.bin | q8_0 | 8 | 14.07 GB | 16.57 GB | Original llama.cpp quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
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
I use the following command line; adjust for your tastes and needs:
./main -t 10 -ngl 32 -m bigtrans-13b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: please translate the following into French: llamas are cute and fluffy and make excellent guards.\n### Response:"
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.
If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins
How to run in text-generation-webui
Further instructions here: text-generation-webui/docs/llama.cpp-models.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: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
Patreon special mentions: vamX, K, Jonathan Leane, Lone Striker, Sean Connelly, Chris McCloskey, WelcomeToTheClub, Nikolai Manek, John Detwiler, Kalila, David Flickinger, Fen Risland, subjectnull, Johann-Peter Hartmann, Talal Aujan, John Villwock, senxiiz, Khalefa Al-Ahmad, Kevin Schuppel, Alps Aficionado, Derek Yates, Mano Prime, Nathan LeClaire, biorpg, trip7s trip, Asp the Wyvern, chris gileta, Iucharbius , Artur Olbinski, Ai Maven, Joseph William Delisle, Luke Pendergrass, Illia Dulskyi, Eugene Pentland, Ajan Kanaga, Willem Michiel, Space Cruiser, Pyrater, Preetika Verma, Junyu Yang, Oscar Rangel, Spiking Neurons AB, Pierre Kircher, webtim, Cory Kujawski, terasurfer , Trenton Dambrowitz, Gabriel Puliatti, Imad Khwaja, Luke.
Thank you to all my generous patrons and donaters!
Original model card: James WYang's BigTrans
BigTrans: Augmenting Large Language Models with Multilingual Translation Capability over 100 Languages
Large language models (LLMs) demonstrate promising translation performance among various natural languages. However, many LLMs especially the open-sourced ones, such as BLOOM and LLaMA, are English-dominant and support only dozens of natural languages, making the potential of LLMs on language translation less explored. In this work, we present BigTrans which adapts LLaMA that covers only 20 languages and enhances it with multilingual translation capability on more than 100 languages. BigTrans is built upon LLaMA-13B and it is optimized in three steps. First, we continue training LLaMA with massive Chinese monolingual data. Second, we continue training the model with a large-scale parallel dataset that covers 102 natural languages. Third, we instruct-tune the foundation model with multilingual translation instructions, leading to our BigTrans model. The preliminary experiments on multilingual translation show that BigTrans performs comparably with ChatGPT and Google Translate in many languages and even outperforms ChatGPT in 8 language pairs. We release the BigTrans model and hope it can advance the research progress.
More Details can be found at https://github.com/ZNLP/BigTrans and https://arxiv.org/abs/2305.18098