inference: false
library_name: transformers
license: llama2
metrics:
- code_eval
model-index:
- name: WizardCoder-Python-34B-V1.0
results:
- dataset:
name: HumanEval
type: openai_humaneval
metrics:
- name: pass@1
type: pass@1
value: 0.732
verified: false
task:
type: text-generation
model_creator: WizardLM
model_link: https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0
model_name: WizardCoder Python 34B V1.0
model_type: llama
quantized_by: TheBloke
tags:
- code
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
WizardCoder Python 34B V1.0 - GGUF
- Model creator: WizardLM
- Original model: WizardCoder Python 34B V1.0
Description
This repo contains GGUF format model files for WizardLM's WizardCoder Python 34B 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.
As of August 25th, here is 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.
- LoLLMS Web UI, should now work, choose the
c_transformersbackend. 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.
The clients and libraries below are expecting to add GGUF support shortly:
- LM Studio, should be updated by end August 25th.
Repositories available
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- 2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference (deprecated)
- WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Alpaca
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
{prompt}
### Response:
Compatibility
These quantised GGUF files are compatible with llama.cpp from August 21st 2023 onwards, as of commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9
As of August 24th 2023 they are now compatible with KoboldCpp, release 1.41 and later.
They are are not yet compatible with any other third-party UIS, libraries or utilities but this is expected to change very soon.
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 |
|---|---|---|---|---|---|
| wizardcoder-python-34b-v1.0.Q2_K.gguf | Q2_K | 2 | 14.58 GB | 17.08 GB | smallest, significant quality loss - not recommended for most purposes |
| wizardcoder-python-34b-v1.0.Q3_K_S.gguf | Q3_K_S | 3 | 14.95 GB | 17.45 GB | very small, high quality loss |
| wizardcoder-python-34b-v1.0.Q3_K_M.gguf | Q3_K_M | 3 | 16.63 GB | 19.13 GB | very small, high quality loss |
| wizardcoder-python-34b-v1.0.Q3_K_L.gguf | Q3_K_L | 3 | 18.12 GB | 20.62 GB | small, substantial quality loss |
| wizardcoder-python-34b-v1.0.Q4_K_S.gguf | Q4_K_S | 4 | 19.46 GB | 21.96 GB | small, greater quality loss |
| wizardcoder-python-34b-v1.0.Q4_K_M.gguf | Q4_K_M | 4 | 20.53 GB | 23.03 GB | medium, balanced quality - recommended |
| wizardcoder-python-34b-v1.0.Q5_K_S.gguf | Q5_K_S | 5 | 23.51 GB | 26.01 GB | large, low quality loss - recommended |
| wizardcoder-python-34b-v1.0.Q5_K_M.gguf | Q5_K_M | 5 | 24.12 GB | 26.62 GB | large, very low quality loss - recommended |
| wizardcoder-python-34b-v1.0.Q6_K.gguf | Q6_K | 6 | 27.93 GB | 30.43 GB | very large, extremely low quality loss |
| wizardcoder-python-34b-v1.0.Q8_0.gguf | Q8_0 | 8 | 35.86 GB | 38.36 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.
How to run in llama.cpp
Make sure you are using llama.cpp from commit 6381d4e110bd0ec02843a60bbeb8b6fc37a9ace9 or later.
For compatibility with older versions of llama.cpp, or for use with third-party clients and libaries, please use GGML files instead.
./main -t 10 -ngl 32 -m wizardcoder-python-34b-v1.0.q4_K_M.gguf --color -c 4096 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\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.
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.
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: Aemon Algiz.
Patreon special mentions: Kacper WikieΕ, knownsqashed, Leonard Tan, Asp the Wyvern, Daniel P. Andersen, Luke Pendergrass, Stanislav Ovsiannikov, RoA, Dave, Ai Maven, Kalila, Will Dee, Imad Khwaja, Nitin Borwankar, Joseph William Delisle, Tony Hughes, Cory Kujawski, Rishabh Srivastava, Russ Johnson, Stephen Murray, Lone Striker, Johann-Peter Hartmann, Elle, J, Deep Realms, SuperWojo, Raven Klaugh, Sebastain Graf, ReadyPlayerEmma, Alps Aficionado, Mano Prime, Derek Yates, Gabriel Puliatti, Mesiah Bishop, Magnesian, Sean Connelly, biorpg, Iucharbius, Olakabola, Fen Risland, Space Cruiser, theTransient, Illia Dulskyi, Thomas Belote, Spencer Kim, Pieter, John Detwiler, Fred von Graf, Michael Davis, Swaroop Kallakuri, subjectnull, Clay Pascal, Subspace Studios, Chris Smitley, Enrico Ros, usrbinkat, Steven Wood, alfie_i, David Ziegler, Willem Michiel, Matthew Berman, Andrey, Pyrater, Jeffrey Morgan, vamX, LangChain4j, Luke @flexchar, Trenton Dambrowitz, Pierre Kircher, Alex, Sam, James Bentley, Edmond Seymore, Eugene Pentland, Pedro Madruga, Rainer Wilmers, Dan Guido, Nathan LeClaire, Spiking Neurons AB, Talal Aujan, zynix, Artur Olbinski, Michael Levine, ιΏζ, K, John Villwock, Nikolai Manek, Femi Adebogun, senxiiz, Deo Leter, NimbleBox.ai, Viktor Bowallius, Geoffrey Montalvo, Mandus, Ajan Kanaga, ya boyyy, Jonathan Leane, webtim, Brandon Frisco, danny, Alexandros Triantafyllidis, Gabriel Tamborski, Randy H, terasurfer, Vadim, Junyu Yang, Vitor Caleffi, Chadd, transmissions 11
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: WizardLM's WizardCoder Python 34B V1.0
News
- π₯π₯π₯[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.
- [2023/06/16] We released WizardCoder-15B-V1.0 , which achieves the 57.3 pass@1 and surpasses Claude-Plus (+6.8), Bard (+15.3) and InstructCodeT5+ (+22.3) on the HumanEval Benchmarks.
βNote: There are two HumanEval results of GPT4 and ChatGPT-3.5. The 67.0 and 48.1 are reported by the official GPT4 Report (2023/03/15) of OpenAI. The 82.0 and 72.5 are tested by ourselves with the latest API (2023/08/26).
| Model | Checkpoint | Paper | HumanEval | MBPP | Demo | License |
|---|---|---|---|---|---|---|
| WizardCoder-Python-34B-V1.0 | π€ HF Link | π [WizardCoder] | 73.2 | 61.2 | Demo | Llama2 |
| WizardCoder-15B-V1.0 | π€ HF Link | π [WizardCoder] | 59.8 | 50.6 | -- | OpenRAIL-M |
- 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.
- 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, and 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 | π€ HF Link | π [WizardMath] | 81.6 | 22.7 | Demo | Llama 2 |
| WizardMath-13B-V1.0 | π€ HF Link | π [WizardMath] | 63.9 | 14.0 | Demo | Llama 2 |
| WizardMath-7B-V1.0 | π€ HF Link | π [WizardMath] | 54.9 | 10.7 | Demo | Llama 2 |
- [08/09/2023] We released WizardLM-70B-V1.0 model. Here is Full Model Weight.
| Model | Checkpoint | Paper | MT-Bench | AlpacaEval | GSM8k | HumanEval | License |
|---|---|---|---|---|---|---|---|
| WizardLM-70B-V1.0 | π€ HF Link | πComing Soon | 7.78 | 92.91% | 77.6% | 50.6 | Llama 2 License |
| WizardLM-13B-V1.2 | π€ HF Link | 7.06 | 89.17% | 55.3% | 36.6 | Llama 2 License | |
| WizardLM-13B-V1.1 | π€ HF Link | 6.76 | 86.32% | 25.0 | Non-commercial | ||
| WizardLM-30B-V1.0 | π€ HF Link | 7.01 | 37.8 | Non-commercial | |||
| WizardLM-13B-V1.0 | π€ HF Link | 6.35 | 75.31% | 24.0 | Non-commercial | ||
| WizardLM-7B-V1.0 | π€ HF Link | π [WizardLM] | 19.1 | Non-commercial | |||
Comparing WizardCoder-Python-34B-V1.0 with Other LLMs.
π₯ The following figure shows that our WizardCoder-Python-34B-V1.0 attains the second position in this benchmark, surpassing GPT4 (2023/03/15, 73.2 vs. 67.0), ChatGPT-3.5 (73.2 vs. 72.5) and Claude2 (73.2 vs. 71.2).
