TheBloke's picture
Initial GGML model commit
0d0221f
|
raw
history blame
11.9 kB
metadata
inference: false
language:
  - en
license: other
model_creator: Mikael110
model_link: https://huggingface.co/Mikael110/llama-2-70b-guanaco-qlora
model_name: Llama2 70B Guanaco QLoRA
model_type: llama
pipeline_tag: text-classification
quantized_by: TheBloke
tags:
  - llama-2
TheBlokeAI

Llama2 70B Guanaco QLoRA - GGML

Description

This repo contains GGML format model files for Mikael110's Llama2 70b Guanaco QLoRA.

These 70B Llama 2 GGML files currently only support CPU inference. They are known to work with:

  • llama.cpp, commit e76d630 and later.
  • text-generation-webui, the most popular web UI.
  • KoboldCpp, version 1.37 and later. A powerful GGML web UI, especially good for story telling.
  • llama-cpp-python, version 0.1.77 and later. A Python library with LangChain support, and OpenAI-compatible API server.

Repositories available

Prompt template: Guanaco

### Human: {prompt}
### Assistant:

Compatibility

Requires llama.cpp commit e76d630 or later.

Or one of the other tools and libraries listed above.

There is currently no GPU acceleration; only CPU can be used.

To use in llama.cpp, you must add -gqa 8 argument.

For other UIs and libraries, please check the docs.

Explanation of the new k-quant 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
  • 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
llama-2-70b-guanaco-qlora.ggmlv3.q2_K.bin q2_K 2 28.59 GB 31.09 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.
llama-2-70b-guanaco-qlora.ggmlv3.q3_K_L.bin q3_K_L 3 36.15 GB 38.65 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
llama-2-70b-guanaco-qlora.ggmlv3.q3_K_M.bin q3_K_M 3 33.04 GB 35.54 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
llama-2-70b-guanaco-qlora.ggmlv3.q3_K_S.bin q3_K_S 3 29.75 GB 32.25 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
llama-2-70b-guanaco-qlora.ggmlv3.q4_0.bin q4_0 4 38.87 GB 41.37 GB Original quant method, 4-bit.
llama-2-70b-guanaco-qlora.ggmlv3.q4_1.bin q4_1 4 43.17 GB 45.67 GB Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models.
llama-2-70b-guanaco-qlora.ggmlv3.q4_K_M.bin q4_K_M 4 41.38 GB 43.88 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
llama-2-70b-guanaco-qlora.ggmlv3.q4_K_S.bin q4_K_S 4 38.87 GB 41.37 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
llama-2-70b-guanaco-qlora.ggmlv3.q5_0.bin q5_0 5 47.46 GB 49.96 GB Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
llama-2-70b-guanaco-qlora.ggmlv3.q5_K_M.bin q5_K_M 5 48.75 GB 51.25 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
llama-2-70b-guanaco-qlora.ggmlv3.q5_K_S.bin q5_K_S 5 47.46 GB 49.96 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors

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 -gqa 8 -m llama-2-70b-guanaco-qlora.ggmlv3.q4_K_M.bin --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Human: Write a story about llamas\n### Assistant:"

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.

Remember the -gqa 8 argument, required for Llama 70B models.

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:

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.

Special thanks to: Luke from CarbonQuill, Aemon Algiz.

Patreon special mentions: Slarti, Chadd, John Detwiler, Pieter, zynix, K, Mano Prime, ReadyPlayerEmma, Ai Maven, Leonard Tan, Edmond Seymore, Joseph William Delisle, Luke @flexchar, Fred von Graf, Viktor Bowallius, Rishabh Srivastava, Nikolai Manek, Matthew Berman, Johann-Peter Hartmann, ya boyyy, Greatston Gnanesh, Femi Adebogun, Talal Aujan, Jonathan Leane, terasurfer, David Flickinger, William Sang, Ajan Kanaga, Vadim, Artur Olbinski, Raven Klaugh, Michael Levine, Oscar Rangel, Randy H, Cory Kujawski, RoA, Dave, Alex, Alexandros Triantafyllidis, Fen Risland, Eugene Pentland, vamX, Elle, Nathan LeClaire, Khalefa Al-Ahmad, Rainer Wilmers, subjectnull, Junyu Yang, Daniel P. Andersen, SuperWojo, LangChain4j, Mandus, Kalila, Illia Dulskyi, Trenton Dambrowitz, Asp the Wyvern, Derek Yates, Jeffrey Morgan, Deep Realms, Imad Khwaja, Pyrater, Preetika Verma, biorpg, Gabriel Tamborski, Stephen Murray, Spiking Neurons AB, Iucharbius, Chris Smitley, Willem Michiel, Luke Pendergrass, Sebastain Graf, senxiiz, Will Dee, Space Cruiser, Karl Bernard, Clay Pascal, Lone Striker, transmissions 11, webtim, WelcomeToTheClub, Sam, theTransient, Pierre Kircher, chris gileta, John Villwock, Sean Connelly, Willian Hasse

Thank you to all my generous patrons and donaters!

Original model card: Mikael110's Llama2 70b Guanaco QLoRA

This is a Llama-2 version of Guanaco. It was finetuned from the base Llama-70b model using the official training scripts found in the QLoRA repo. I wanted it to be as faithful as possible and therefore changed nothing in the training script beyond the model it was pointing to. The model prompt is therefore also the same as the original Guanaco model.

This repo contains the QLoRA adapter.

A 7b version of the adapter can be found here. A 13b version of the adapter can be found here.

Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.