Hugging Face's logo

TheBloke
/
WizardMath-70B-V1.0-GGML

Transformers
llama
text-generation-inference
Model card Files Community
2
WizardMath-70B-V1.0-GGML / README.md
WizardLM's picture
WizardLM
Update README.md
d5856bb
preview code
|
raw history blame
16.3 kB
metadata
inference: false
license: other
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardMath-70B-V1.0
model_name: WizardMath 70B V1.0
model_type: llama
quantized_by: TheBloke
TheBlokeAI

WizardMath 70B V1.0 - GGML

Description

This repo contains GGML format model files for WizardLM's WizardMath 70B V1.0.

GPU acceleration is now available for Llama 2 70B GGML files, with both CUDA (NVidia) and Metal (macOS). The following clients/libraries are known to work with these files, including with GPU acceleration:

  • llama.cpp, commit e76d630 and later.
  • text-generation-webui, the most widely used web UI.
  • KoboldCpp, version 1.37 and later. A powerful GGML web UI, especially good for story telling.
  • LM Studio, a fully featured local GUI with GPU acceleration for both Windows and macOS. Use 0.1.11 or later for macOS GPU acceleration with 70B models.
  • llama-cpp-python, version 0.1.77 and later. A Python library with LangChain support, and OpenAI-compatible API server.
  • ctransformers, version 0.2.15 and later. A Python library with LangChain support, and OpenAI-compatible API server.

Repositories available

Prompt template:

❗Note for model system prompts usage:

Default version:

"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"

CoT Version: （❗For the simple math questions, we do NOT recommend to use the CoT prompt.） 

"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response: Let's think step by step."

Compatibility

Requires llama.cpp commit e76d630 or later.

Or one of the other tools and libraries listed above.

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
wizardmath-70b-v1.0.ggmlv3.q2_K.bin q2_K 2 28.96 GB 31.46 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.
wizardmath-70b-v1.0.ggmlv3.q3_K_L.bin q3_K_L 3 36.49 GB 38.99 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
wizardmath-70b-v1.0.ggmlv3.q3_K_M.bin q3_K_M 3 33.39 GB 35.89 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
wizardmath-70b-v1.0.ggmlv3.q3_K_S.bin q3_K_S 3 30.09 GB 32.59 GB New k-quant method. Uses GGML_TYPE_Q3_K for all tensors
wizardmath-70b-v1.0.ggmlv3.q4_0.bin q4_0 4 38.80 GB 41.30 GB Original quant method, 4-bit.
wizardmath-70b-v1.0.ggmlv3.q4_1.bin q4_1 4 43.12 GB 45.62 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.
wizardmath-70b-v1.0.ggmlv3.q4_K_M.bin q4_K_M 4 41.69 GB 44.19 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
wizardmath-70b-v1.0.ggmlv3.q4_K_S.bin q4_K_S 4 39.18 GB 41.68 GB New k-quant method. Uses GGML_TYPE_Q4_K for all tensors
wizardmath-70b-v1.0.ggmlv3.q5_0.bin q5_0 5 47.43 GB 49.93 GB Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference.
wizardmath-70b-v1.0.ggmlv3.q5_K_M.bin q5_K_M 5 49.03 GB 51.53 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
wizardmath-70b-v1.0.ggmlv3.q5_K_S.bin q5_K_S 5 47.74 GB 50.24 GB New k-quant method. Uses GGML_TYPE_Q5_K for all tensors
wizardmath-70b-v1.0.ggmlv3.q5_1.bin q5_1 5 51.76 GB 54.26 GB Original quant method, 5-bit. Higher accuracy, slower inference than q5_0.
wizardmath-70b-v1.0.ggmlv3.q6_K.bin q6_K 6 56.59 GB 59.09 GB New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors
wizardmath-70b-v1.0.ggmlv3.q8_0.bin q8_0 8 73.23 GB 75.73 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.

q5_1, 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, they are just for storing a .bin file in two parts.

Click for instructions regarding q5_1, q6_K and q8_0 files

q5_1

Please download:

  • wizardmath-70b-v1.0.ggmlv3.q5_1.zip
  • wizardmath-70b-v1.0.ggmlv3.q5_1.z01

q6_K

Please download:

  • wizardmath-70b-v1.0.ggmlv3.q6_K.zip
  • wizardmath-70b-v1.0.ggmlv3.q6_K.z01

q8_0

Please download:

  • wizardmath-70b-v1.0.ggmlv3.q8_0.zip
  • wizardmath-70b-v1.0.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 wizardmath-70b-v1.0.ggmlv3.q6_K.zip

How to run in llama.cpp

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

./main -t 10 -ngl 40 -gqa 8 -m wizardmath-70b-v1.0.ggmlv3.q4_K_M.bin --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n\n### Instruction:\nWrite a story about llamas\n\n\n### Response: Let's think step by step."

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. If you are fully offloading the model to GPU, use -t 1

Change -ngl 40 to the number of GPU layers you have VRAM for. Use -ngl 100 to offload all layers to VRAM - if you have a 48GB card, or 2 x 24GB, or similar. Otherwise you can partially offload as many as you have VRAM for, on one or more GPUs.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

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

Change -c 4096 to the desired sequence length for this model. For models that use RoPE, add --rope-freq-base 10000 --rope-freq-scale 0.5 for doubled context, or --rope-freq-base 10000 --rope-freq-scale 0.25 for 4x context.

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

Thank you to all my generous patrons and donaters!

Original model card: WizardLM's WizardMath 70B V1.0

WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct

🤗 HF Repo • 🐦 Twitter • 📃 [WizardLM] • 📃 [WizardCoder]

👋 Join our Discord

Model Checkpoint Paper GSM8k MATH License
WizardMath-70B-V1.0 🤗 HF Link 📃Coming Soon 81.6 22.7 Llama 2 License
WizardMath-13B-V1.0 🤗 HF Link 📃Coming Soon 63.9 14.0 Llama 2 License
WizardMath-7B-V1.0 🤗 HF Link 📃Coming Soon 54.9 10.7 Llama 2 License

Github Repo: https://github.com/nlpxucan/WizardLM/tree/main/WizardMath

Twitter: https://twitter.com/WizardLM_AI/status/1689990201467432960

Discord: https://discord.gg/bpmeZD7V

❗Note for model system prompts usage:

CoT Version: 

Below is an instruction that describes a task. Write a response that appropriately completes the request.


### Instruction:
{instruction}


### Response: Let's think step by step.

❗To commen concern about dataset:

Recently, there have been clear changes in the open-source policy and regulations of our overall organization's code, data, and models. Despite this, we have still worked hard to obtain opening the weights of the model first, but the data involves stricter auditing and is in review with our legal team . Our researchers have no authority to publicly release them without authorization. Thank you for your understanding.