robin-65B-v2-GGML / README.md
TheBloke's picture
Update README.md
82500cb
metadata
inference: false
license: other
TheBlokeAI

OptimalScale's Robin 65B v2 GGML

These files are GGML format model files for OptimalScale's Robin 65B v2.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

Repositories available

Prompt template

A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions
###Human: prompt
###Assistant:

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
robin-65b.ggmlv3.q2_K.bin q2_K 2 27.45 GB 29.95 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.
robin-65b.ggmlv3.q3_K_L.bin q3_K_L 3 34.65 GB 37.15 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
robin-65b.ggmlv3.q3_K_M.bin q3_K_M 3 31.50 GB 34.00 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
robin-65b.ggmlv3.q3_K_S.bin q3_K_S 3 28.16 GB 30.66 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
robin-65b.ggmlv3.q4_0.bin q4_0 4 36.73 GB 39.23 GB Original llama.cpp quant method, 4-bit.
robin-65b.ggmlv3.q4_1.bin q4_1 4 40.81 GB 43.31 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.
robin-65b.ggmlv3.q4_K_M.bin q4_K_M 4 39.35 GB 41.85 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
robin-65b.ggmlv3.q4_K_S.bin q4_K_S 4 36.80 GB 39.30 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
robin-65b.ggmlv3.q5_0.bin q5_0 5 44.89 GB 47.39 GB Original llama.cpp quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
robin-65b.ggmlv3.q5_1.bin q5_1 5 48.97 GB 51.47 GB Original llama.cpp quant method, 5-bit. Even higher accuracy, resource usage and slower inference.
robin-65b.ggmlv3.q5_K_M.bin q5_K_M 5 46.24 GB 48.74 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
robin-65b.ggmlv3.q5_K_S.bin q5_K_S 5 44.92 GB 47.42 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
robin-65b.ggmlv3.q6_K.bin q6_K 6 53.56 GB 56.06 GB New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors
robin-65b.ggmlv3.q8_0.bin q8_0 8 69.370 GB 71.87 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.

q6_K and q8_0 files require expansion from archive

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the q6_K and q8_0 files as multi-part ZIP files. They are not compressed, it is just storing the .bin file in two parts.

q6_K

Please download:

  • robin-65b.ggmlv3.q6_K.zip
  • robin-65b.ggmlv3.q6_K.z01

q8_0

Please download:

  • robin-65b.ggmlv3.q8_0.zip
  • robin-65b.ggmlv3.q8_0.z01

Then extract the .zip archive. This will will expand both parts automatically. On Linux I found I had to use 7zip - the basic unzip tool did not work. Example:

sudo apt update -y && sudo apt install 7zip
7zz x robin-65b.ggmlv3.q6_K.zip`

Once the .bin is extracted you can delete the .zip and .z01 files

How to run in llama.cpp

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m robin-65b.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions\n###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.

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:

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, 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: OptimalScale's Robin 65B v2

No model card provided in source repository.