Hugging Face's logo

TheBloke
/
WizardLM-70B-V1.0-GGUF

Transformers
GGUF
llama
text-generation-inference
Model card Files Community
WizardLM-70B-V1.0-GGUF / README.md
TheBloke's picture
TheBloke
Upload README.md
09d9ada
preview code
|
raw
history blame
No virus
26.4 kB
metadata
inference: false
license: llama2
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardLM-70B-V1.0
model_name: WizardLM 70B V1.0
model_type: llama
quantized_by: TheBloke
TheBlokeAI

TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)

WizardLM 70B V1.0 - GGUF

Description

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

About GGUF

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.

The key benefit of GGUF is that it is a extensible, future-proof format which stores more information about the model as metadata. It also includes significantly improved tokenization code, including for the first time full support for special tokens. This should improve performance, especially with models that use new special tokens and implement custom prompt templates.

Here are a list of clients and libraries that are known to support GGUF:

  • llama.cpp.
  • text-generation-webui, the most widely used web UI. Supports GGUF with GPU acceleration via the ctransformers backend - llama-cpp-python backend should work soon too.
  • KoboldCpp, now supports GGUF as of release 1.41! A powerful GGML web UI, with full GPU accel. Especially good for story telling.
  • LM Studio, version 0.2.2 and later support GGUF. A fully featured local GUI with GPU acceleration on both Windows (NVidia and AMD), and macOS.
  • LoLLMS Web UI, should now work, choose the c_transformers backend. A great web UI with many interesting features. Supports CUDA GPU acceleration.
  • ctransformers, now supports GGUF as of version 0.2.24! A Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
  • llama-cpp-python, supports GGUF as of version 0.1.79. A Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
  • candle, added GGUF support on August 22nd. Candle is a Rust ML framework with a focus on performance, including GPU support, and ease of use.

Repositories available

Prompt template: Vicuna 

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: {prompt} ASSISTANT:

Compatibility

These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9

They are now also compatible with many third party UIs and libraries - please see the list at the top of the 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.

Provided files

Name Quant method Bits Size Max RAM required Use case
wizardlm-70b-v1.0.Q6_K.gguf-split-b Q6_K 6 19.89 GB 22.39 GB very large, extremely low quality loss
wizardlm-70b-v1.0.Q2_K.gguf Q2_K 2 29.28 GB 31.78 GB smallest, significant quality loss - not recommended for most purposes
wizardlm-70b-v1.0.Q3_K_S.gguf Q3_K_S 3 29.92 GB 32.42 GB very small, high quality loss
wizardlm-70b-v1.0.Q3_K_M.gguf Q3_K_M 3 33.19 GB 35.69 GB very small, high quality loss
wizardlm-70b-v1.0.Q3_K_L.gguf Q3_K_L 3 36.15 GB 38.65 GB small, substantial quality loss
wizardlm-70b-v1.0.Q8_0.gguf-split-b Q8_0 8 36.59 GB 39.09 GB very large, extremely low quality loss - not recommended
wizardlm-70b-v1.0.Q6_K.gguf-split-a Q6_K 6 36.70 GB 39.20 GB very large, extremely low quality loss
wizardlm-70b-v1.0.Q8_0.gguf-split-a Q8_0 8 36.70 GB 39.20 GB very large, extremely low quality loss - not recommended
wizardlm-70b-v1.0.Q4_0.gguf Q4_0 4 38.87 GB 41.37 GB legacy; small, very high quality loss - prefer using Q3_K_M
wizardlm-70b-v1.0.Q4_K_S.gguf Q4_K_S 4 39.07 GB 41.57 GB small, greater quality loss
wizardlm-70b-v1.0.Q4_K_M.gguf Q4_K_M 4 41.42 GB 43.92 GB medium, balanced quality - recommended
wizardlm-70b-v1.0.Q5_0.gguf Q5_0 5 47.46 GB 49.96 GB legacy; medium, balanced quality - prefer using Q4_K_M
wizardlm-70b-v1.0.Q5_K_S.gguf Q5_K_S 5 47.46 GB 49.96 GB large, low quality loss - recommended
wizardlm-70b-v1.0.Q5_K_M.gguf Q5_K_M 5 48.75 GB 51.25 GB large, very low quality loss - recommended
wizardlm-70b-v1.0.Q6_K.gguf Q6_K 6 56.59 GB 59.09 GB very large, extremely low quality loss
wizardlm-70b-v1.0.Q8_0.gguf Q8_0 8 73.29 GB 75.79 GB 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.

Q6_K and Q8_0 files are split and require joining

Note: HF does not support uploading files larger than 50GB. Therefore I have uploaded the Q6_K and Q8_0 files as split files.

Click for instructions regarding Q6_K and Q8_0 files

q6_K

Please download:

  • wizardlm-70b-v1.0.Q6_K.gguf-split-a
  • wizardlm-70b-v1.0.Q6_K.gguf-split-b

q8_0

Please download:

  • wizardlm-70b-v1.0.Q8_0.gguf-split-a
  • wizardlm-70b-v1.0.Q8_0.gguf-split-b

To join the files, do the following:

Linux and macOS:

cat wizardlm-70b-v1.0.Q6_K.gguf-split-* > wizardlm-70b-v1.0.Q6_K.gguf && rm wizardlm-70b-v1.0.Q6_K.gguf-split-*
cat wizardlm-70b-v1.0.Q8_0.gguf-split-* > wizardlm-70b-v1.0.Q8_0.gguf && rm wizardlm-70b-v1.0.Q8_0.gguf-split-*

Windows command line:

COPY /B wizardlm-70b-v1.0.Q6_K.gguf-split-a + wizardlm-70b-v1.0.Q6_K.gguf-split-b wizardlm-70b-v1.0.Q6_K.gguf
del wizardlm-70b-v1.0.Q6_K.gguf-split-a wizardlm-70b-v1.0.Q6_K.gguf-split-b

COPY /B wizardlm-70b-v1.0.Q8_0.gguf-split-a + wizardlm-70b-v1.0.Q8_0.gguf-split-b wizardlm-70b-v1.0.Q8_0.gguf
del wizardlm-70b-v1.0.Q8_0.gguf-split-a wizardlm-70b-v1.0.Q8_0.gguf-split-b

Example llama.cpp command

Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.

For compatibility with older versions of llama.cpp, or for any third-party libraries or clients that haven't yet updated for GGUF, please use GGML files instead.

./main -t 10 -ngl 32 -m wizardlm-70b-v1.0.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Write a story about llamas 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. If offloading all layers to GPU, set -t 1.

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 this model. 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

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.md.

How to run from Python code

You can use GGUF models from Python using the llama-cpp-python or ctransformers libraries.

How to load this model from Python using ctransformers

First install the package 

# Base ctransformers with no GPU acceleration
pip install ctransformers>=0.2.24
# Or with CUDA GPU acceleration
pip install ctransformers[cuda]>=0.2.24
# Or with ROCm GPU acceleration
CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers
# Or with Metal GPU acceleration for macOS systems
CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers

Simple example code to load one of these GGUF models 

from ctransformers import AutoModelForCausalLM

# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardLM-70B-V1.0-GGUF", model_file="wizardlm-70b-v1.0.q4_K_M.gguf", model_type="llama", gpu_layers=50)

print(llm("AI is going to"))

How to use with LangChain

Here's guides on using llama-cpp-python or ctransformers with LangChain:

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: Aemon Algiz.

Patreon special mentions: Russ Johnson, J, alfie_i, Alex, NimbleBox.ai, Chadd, Mandus, Nikolai Manek, Ken Nordquist, ya boyyy, Illia Dulskyi, Viktor Bowallius, vamX, Iucharbius, zynix, Magnesian, Clay Pascal, Pierre Kircher, Enrico Ros, Tony Hughes, Elle, Andrey, knownsqashed, Deep Realms, Jerry Meng, Lone Striker, Derek Yates, Pyrater, Mesiah Bishop, James Bentley, Femi Adebogun, Brandon Frisco, SuperWojo, Alps Aficionado, Michael Dempsey, Vitor Caleffi, Will Dee, Edmond Seymore, usrbinkat, LangChain4j, Kacper WikieΕ‚, Luke Pendergrass, John Detwiler, theTransient, Nathan LeClaire, Tiffany J. Kim, biorpg, Eugene Pentland, Stanislav Ovsiannikov, Fred von Graf, terasurfer, Kalila, Dan Guido, Nitin Borwankar, 阿明, Ai Maven, John Villwock, Gabriel Puliatti, Stephen Murray, Asp the Wyvern, danny, Chris Smitley, ReadyPlayerEmma, S_X, Daniel P. Andersen, Olakabola, Jeffrey Morgan, Imad Khwaja, Caitlyn Gatomon, webtim, Alicia Loh, Trenton Dambrowitz, Swaroop Kallakuri, Erik BjΓ€reholt, Leonard Tan, Spiking Neurons AB, Luke @flexchar, Ajan Kanaga, Thomas Belote, Deo Leter, RoA, Willem Michiel, transmissions 11, subjectnull, Matthew Berman, Joseph William Delisle, David Ziegler, Michael Davis, Johann-Peter Hartmann, Talal Aujan, senxiiz, Artur Olbinski, Rainer Wilmers, Spencer Kim, Fen Risland, Cap'n Zoog, Rishabh Srivastava, Michael Levine, Geoffrey Montalvo, Sean Connelly, Alexandros Triantafyllidis, Pieter, Gabriel Tamborski, Sam, Subspace Studios, Junyu Yang, Pedro Madruga, Vadim, Cory Kujawski, K, Raven Klaugh, Randy H, Mano Prime, Sebastain Graf, Space Cruiser

Thank you to all my generous patrons and donaters!

And thank you again to a16z for their generous grant.

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

WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions

πŸ€— HF Repo β€’πŸ± Github Repo β€’ 🐦 Twitter β€’ πŸ“ƒ [WizardLM] β€’ πŸ“ƒ [WizardCoder] β€’ πŸ“ƒ [WizardMath]

πŸ‘‹ Join our Discord

Unofficial Video Introductions

Thanks to the enthusiastic friends, their video introductions are more lively and interesting.

  1. NEW WizardLM 70b πŸ”₯ Giant Model...Insane Performance
  2. GET WizardLM NOW! 7B LLM KING That Can Beat ChatGPT! I'm IMPRESSED!
  3. WizardLM: Enhancing Large Language Models to Follow Complex Instructions
  4. WizardCoder AI Is The NEW ChatGPT's Coding TWIN!

News

  • πŸ”₯πŸ”₯πŸ”₯[2023/08/26] We released WizardCoder-Python-34B-V1.0 , which achieves the 73.2 pass@1 and surpasses GPT4 (2023/03/15), ChatGPT-3.5, and Claude2 on the HumanEval Benchmarks. For more details, please refer to WizardCoder.
  • [2023/06/16] We released WizardCoder-15B-V1.0 , which surpasses Claude-Plus (+6.8), Bard (+15.3) and InstructCodeT5+ (+22.3) on the HumanEval Benchmarks. For more details, please refer to WizardCoder.
Model Checkpoint Paper HumanEval MBPP Demo License
WizardCoder-Python-34B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardCoder] 73.2 61.2 Demo Llama2
WizardCoder-15B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardCoder] 59.8 50.6 -- OpenRAIL-M
WizardCoder-Python-13B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardCoder] 64.0 55.6 -- Llama2
WizardCoder-Python-7B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardCoder] 55.5 51.6 Demo Llama2
WizardCoder-3B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardCoder] 34.8 37.4 -- OpenRAIL-M
WizardCoder-1B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardCoder] 23.8 28.6 -- OpenRAIL-M
  • πŸ”₯ [08/11/2023] We release WizardMath Models.
  • πŸ”₯ Our WizardMath-70B-V1.0 model slightly outperforms some closed-source LLMs on the GSM8K, including ChatGPT 3.5, Claude Instant 1 and PaLM 2 540B.
  • πŸ”₯ Our WizardMath-70B-V1.0 model achieves 81.6 pass@1 on the GSM8k Benchmarks, which is 24.8 points higher than the SOTA open-source LLM.
  • πŸ”₯ Our WizardMath-70B-V1.0 model achieves 22.7 pass@1 on the MATH Benchmarks, which is 9.2 points higher than the SOTA open-source LLM.
Model Checkpoint Paper GSM8k MATH Online Demo License
WizardMath-70B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardMath] 81.6 22.7 Demo Llama 2
WizardMath-13B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardMath] 63.9 14.0 Demo Llama 2
WizardMath-7B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardMath] 54.9 10.7 Demo Llama 2
Model Checkpoint Paper MT-Bench AlpacaEval GSM8k HumanEval License
WizardLM-70B-V1.0 πŸ€— HF Link πŸ“ƒComing Soon 7.78 92.91% 77.6% 50.6 pass@1 Llama 2 License
WizardLM-13B-V1.2 πŸ€— HF Link 7.06 89.17% 55.3% 36.6 pass@1 Llama 2 License
WizardLM-13B-V1.1 πŸ€— HF Link 6.76 86.32% 25.0 pass@1 Non-commercial
WizardLM-30B-V1.0 πŸ€— HF Link 7.01 37.8 pass@1 Non-commercial
WizardLM-13B-V1.0 πŸ€— HF Link 6.35 75.31% 24.0 pass@1 Non-commercial
WizardLM-7B-V1.0 πŸ€— HF Link πŸ“ƒ [WizardLM] 19.1 pass@1 Non-commercial
  • πŸ”₯πŸ”₯πŸ”₯ [08/09/2023] We released WizardLM-70B-V1.0 model.

Github Repo: https://github.com/nlpxucan/WizardLM

Twitter: https://twitter.com/WizardLM_AI/status/1689270108747976704

Discord: https://discord.gg/bpmeZD7V

❗Note for model system prompts usage:

WizardLM adopts the prompt format from Vicuna and supports multi-turn conversation. The prompt should be as following:

A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions. USER: Hi ASSISTANT: Hello.</s>USER: Who are you? ASSISTANT: I am WizardLM.</s>......

Inference WizardLM Demo Script

We provide the inference WizardLM demo code here.

❗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.