TheBloke/WizardCoder-Python-13B-V1.0-GGUF
615k
1---2license: llama23library_name: transformers4tags:5- code6metrics:7- code_eval8base_model: WizardLM/WizardCoder-Python-13B-V1.09inference: false10model_creator: WizardLM11model_type: llama12prompt_template: 'Below is an instruction that describes a task. Write a response13 that appropriately completes the request.14 15 16 ### Instruction:17 18 {prompt}19 20 21 ### Response:22 23 '24quantized_by: TheBloke25model-index:26- name: WizardCoder-Python-13B-V1.027 results:28 - task:29 type: text-generation30 dataset:31 name: HumanEval32 type: openai_humaneval33 metrics:34 - type: pass@135 value: 0.6436 name: pass@137 verified: false38---39 40<!-- header start -->41<!-- 200823 -->42<div style="width: auto; margin-left: auto; margin-right: auto">43<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">44</div>45<div style="display: flex; justify-content: space-between; width: 100%;">46 <div style="display: flex; flex-direction: column; align-items: flex-start;">47 <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://discord.gg/theblokeai">Chat & support: TheBloke's Discord server</a></p>48 </div>49 <div style="display: flex; flex-direction: column; align-items: flex-end;">50 <p style="margin-top: 0.5em; margin-bottom: 0em;"><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>51 </div>52</div>53<div style="text-align:center; margin-top: 0em; margin-bottom: 0em"><p style="margin-top: 0.25em; margin-bottom: 0em;">TheBloke's LLM work is generously supported by a grant from <a href="https://a16z.com">andreessen horowitz (a16z)</a></p></div>54<hr style="margin-top: 1.0em; margin-bottom: 1.0em;">55<!-- header end -->56 57# WizardCoder Python 13B V1.0 - GGUF58- Model creator: [WizardLM](https://huggingface.co/WizardLM)59- Original model: [WizardCoder Python 13B V1.0](https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0)60 61<!-- description start -->62## Description63 64This repo contains GGUF format model files for [WizardLM's WizardCoder Python 13B V1.0](https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0).65 66<!-- description end -->67<!-- README_GGUF.md-about-gguf start -->68### About GGUF69 70GGUF 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. GGUF offers numerous advantages over GGML, such as better tokenisation, and support for special tokens. It is also supports metadata, and is designed to be extensible.71 72Here is an incomplate list of clients and libraries that are known to support GGUF:73 74* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.75* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.76* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.77* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.78* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.79* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.80* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.81* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.82* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.83 84<!-- README_GGUF.md-about-gguf end -->85<!-- repositories-available start -->86## Repositories available87 88* [AWQ model(s) for GPU inference.](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-AWQ)89* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GPTQ)90* [2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF)91* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0)92<!-- repositories-available end -->93 94<!-- prompt-template start -->95## Prompt template: Alpaca96 97```98Below is an instruction that describes a task. Write a response that appropriately completes the request.99 100### Instruction:101{prompt}102 103### Response:104 105```106 107<!-- prompt-template end -->108 109 110<!-- compatibility_gguf start -->111## Compatibility112 113These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)114 115They are also compatible with many third party UIs and libraries - please see the list at the top of this README.116 117## Explanation of quantisation methods118<details>119 <summary>Click to see details</summary>120 121The new methods available are:122* 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)123* 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.124* 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.125* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw126* 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 bpw127 128Refer to the Provided Files table below to see what files use which methods, and how.129</details>130<!-- compatibility_gguf end -->131 132<!-- README_GGUF.md-provided-files start -->133## Provided files134 135| Name | Quant method | Bits | Size | Max RAM required | Use case |136| ---- | ---- | ---- | ---- | ---- | ----- |137| [wizardcoder-python-13b-v1.0.Q2_K.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q2_K.gguf) | Q2_K | 2 | 5.43 GB| 7.93 GB | smallest, significant quality loss - not recommended for most purposes |138| [wizardcoder-python-13b-v1.0.Q3_K_S.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q3_K_S.gguf) | Q3_K_S | 3 | 5.66 GB| 8.16 GB | very small, high quality loss |139| [wizardcoder-python-13b-v1.0.Q3_K_M.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q3_K_M.gguf) | Q3_K_M | 3 | 6.34 GB| 8.84 GB | very small, high quality loss |140| [wizardcoder-python-13b-v1.0.Q3_K_L.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q3_K_L.gguf) | Q3_K_L | 3 | 6.93 GB| 9.43 GB | small, substantial quality loss |141| [wizardcoder-python-13b-v1.0.Q4_0.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q4_0.gguf) | Q4_0 | 4 | 7.37 GB| 9.87 GB | legacy; small, very high quality loss - prefer using Q3_K_M |142| [wizardcoder-python-13b-v1.0.Q4_K_S.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q4_K_S.gguf) | Q4_K_S | 4 | 7.41 GB| 9.91 GB | small, greater quality loss |143| [wizardcoder-python-13b-v1.0.Q4_K_M.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q4_K_M.gguf) | Q4_K_M | 4 | 7.87 GB| 10.37 GB | medium, balanced quality - recommended |144| [wizardcoder-python-13b-v1.0.Q5_0.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q5_0.gguf) | Q5_0 | 5 | 8.97 GB| 11.47 GB | legacy; medium, balanced quality - prefer using Q4_K_M |145| [wizardcoder-python-13b-v1.0.Q5_K_S.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q5_K_S.gguf) | Q5_K_S | 5 | 8.97 GB| 11.47 GB | large, low quality loss - recommended |146| [wizardcoder-python-13b-v1.0.Q5_K_M.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q5_K_M.gguf) | Q5_K_M | 5 | 9.23 GB| 11.73 GB | large, very low quality loss - recommended |147| [wizardcoder-python-13b-v1.0.Q6_K.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q6_K.gguf) | Q6_K | 6 | 10.68 GB| 13.18 GB | very large, extremely low quality loss |148| [wizardcoder-python-13b-v1.0.Q8_0.gguf](https://huggingface.co/TheBloke/WizardCoder-Python-13B-V1.0-GGUF/blob/main/wizardcoder-python-13b-v1.0.Q8_0.gguf) | Q8_0 | 8 | 13.83 GB| 16.33 GB | very large, extremely low quality loss - not recommended |149 150**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.151 152 153 154<!-- README_GGUF.md-provided-files end -->155 156<!-- README_GGUF.md-how-to-download start -->157## How to download GGUF files158 159**Note for manual downloaders:** You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.160 161The following clients/libraries will automatically download models for you, providing a list of available models to choose from:162- LM Studio163- LoLLMS Web UI164- Faraday.dev165 166### In `text-generation-webui`167 168Under Download Model, you can enter the model repo: TheBloke/WizardCoder-Python-13B-V1.0-GGUF and below it, a specific filename to download, such as: wizardcoder-python-13b-v1.0.q4_K_M.gguf.169 170Then click Download.171 172### On the command line, including multiple files at once173 174I recommend using the `huggingface-hub` Python library:175 176```shell177pip3 install huggingface-hub>=0.17.1178```179 180Then you can download any individual model file to the current directory, at high speed, with a command like this:181 182```shell183huggingface-cli download TheBloke/WizardCoder-Python-13B-V1.0-GGUF wizardcoder-python-13b-v1.0.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False184```185 186<details>187 <summary>More advanced huggingface-cli download usage</summary>188 189You can also download multiple files at once with a pattern:190 191```shell192huggingface-cli download TheBloke/WizardCoder-Python-13B-V1.0-GGUF --local-dir . --local-dir-use-symlinks False --include='*Q4_K*gguf'193```194 195For more documentation on downloading with `huggingface-cli`, please see: [HF -> Hub Python Library -> Download files -> Download from the CLI](https://huggingface.co/docs/huggingface_hub/guides/download#download-from-the-cli).196 197To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:198 199```shell200pip3 install hf_transfer201```202 203And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:204 205```shell206HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/WizardCoder-Python-13B-V1.0-GGUF wizardcoder-python-13b-v1.0.q4_K_M.gguf --local-dir . --local-dir-use-symlinks False207```208 209Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.210</details>211<!-- README_GGUF.md-how-to-download end -->212 213<!-- README_GGUF.md-how-to-run start -->214## Example `llama.cpp` command215 216Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.217 218```shell219./main -ngl 32 -m wizardcoder-python-13b-v1.0.q4_K_M.gguf --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### Instruction:\n{prompt}\n\n### Response:"220```221 222Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.223 224Change `-c 4096` to the desired sequence length. 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.225 226If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`227 228For other parameters and how to use them, please refer to [the llama.cpp documentation](https://github.com/ggerganov/llama.cpp/blob/master/examples/main/README.md)229 230## How to run in `text-generation-webui`231 232Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).233 234## How to run from Python code235 236You can use GGUF models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.237 238### How to load this model from Python using ctransformers239 240#### First install the package241 242```bash243# Base ctransformers with no GPU acceleration244pip install ctransformers>=0.2.24245# Or with CUDA GPU acceleration246pip install ctransformers[cuda]>=0.2.24247# Or with ROCm GPU acceleration248CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers249# Or with Metal GPU acceleration for macOS systems250CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers251```252 253#### Simple example code to load one of these GGUF models254 255```python256from ctransformers import AutoModelForCausalLM257 258# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.259llm = AutoModelForCausalLM.from_pretrained("TheBloke/WizardCoder-Python-13B-V1.0-GGUF", model_file="wizardcoder-python-13b-v1.0.q4_K_M.gguf", model_type="llama", gpu_layers=50)260 261print(llm("AI is going to"))262```263 264## How to use with LangChain265 266Here's guides on using llama-cpp-python or ctransformers with LangChain:267 268* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)269* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)270 271<!-- README_GGUF.md-how-to-run end -->272 273<!-- footer start -->274<!-- 200823 -->275## Discord276 277For further support, and discussions on these models and AI in general, join us at:278 279[TheBloke AI's Discord server](https://discord.gg/theblokeai)280 281## Thanks, and how to contribute282 283Thanks to the [chirper.ai](https://chirper.ai) team!284 285Thanks to Clay from [gpus.llm-utils.org](llm-utils)!286 287I'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.288 289If 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.290 291Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.292 293* Patreon: https://patreon.com/TheBlokeAI294* Ko-Fi: https://ko-fi.com/TheBlokeAI295 296**Special thanks to**: Aemon Algiz.297 298**Patreon special mentions**: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov299 300 301Thank you to all my generous patrons and donaters!302 303And thank you again to a16z for their generous grant.304 305<!-- footer end -->306 307<!-- original-model-card start -->308# Original model card: WizardLM's WizardCoder Python 13B V1.0309 310 311<p align="center">312🤗 <a href="https://huggingface.co/WizardLM" target="_blank">HF Repo</a> •🐱 <a href="https://github.com/nlpxucan/WizardLM" target="_blank">Github Repo</a> • 🐦 <a href="https://twitter.com/WizardLM_AI" target="_blank">Twitter</a> • 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> • 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> • 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a> <br>313</p>314<p align="center">315 👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>316</p>317 318## News319 320- 🔥🔥🔥[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](https://github.com/openai/human-eval).321- [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](https://github.com/openai/human-eval).322 323❗Note: 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](https://arxiv.org/abs/2303.08774). The 82.0 and 72.5 are tested by ourselves with the latest API (2023/08/26).324 325 326| Model | Checkpoint | Paper | HumanEval | MBPP | Demo | License |327| ----- |------| ---- |------|-------| ----- | ----- |328| WizardCoder-Python-34B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 73.2 | 61.2 | [Demo](http://47.103.63.15:50085/) | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |329| WizardCoder-15B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-15B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 59.8 |50.6 | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |330| WizardCoder-Python-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 64.0 | 55.6 | -- | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |331| WizardCoder-Python-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-Python-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 55.5 | 51.6 | [Demo](http://47.103.63.15:50088/) | <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama2</a> |332| WizardCoder-3B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-3B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 34.8 |37.4 | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |333| WizardCoder-1B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardCoder-1B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2306.08568" target="_blank">[WizardCoder]</a> | 23.8 |28.6 | -- | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |334 335 336- 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**.337- Our **WizardMath-70B-V1.0** model achieves **81.6 pass@1** on the [GSM8k Benchmarks](https://github.com/openai/grade-school-math), which is **24.8** points higher than the SOTA open-source LLM, and achieves **22.7 pass@1** on the [MATH Benchmarks](https://github.com/hendrycks/math), which is **9.2** points higher than the SOTA open-source LLM.338 339<font size=4>340 341| Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|342| ----- |------| ---- |------|-------| ----- | ----- |343| WizardMath-70B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-70B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **81.6** | **22.7** |[Demo](http://47.103.63.15:50083/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |344| WizardMath-13B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-13B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **63.9** | **14.0** |[Demo](http://47.103.63.15:50082/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a> |345| WizardMath-7B-V1.0 | 🤗 <a href="https://huggingface.co/WizardLM/WizardMath-7B-V1.0" target="_blank">HF Link</a> | 📃 <a href="https://arxiv.org/abs/2308.09583" target="_blank">[WizardMath]</a>| **54.9** | **10.7** | [Demo ](http://47.103.63.15:50080/)| <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 </a>|346</font>347 348 349- [08/09/2023] We released **WizardLM-70B-V1.0** model. Here is [Full Model Weight](https://huggingface.co/WizardLM/WizardLM-70B-V1.0).350 351<font size=4>352 353 354| <sup>Model</sup> | <sup>Checkpoint</sup> | <sup>Paper</sup> |<sup>MT-Bench</sup> | <sup>AlpacaEval</sup> | <sup>GSM8k</sup> | <sup>HumanEval</sup> | <sup>License</sup>|355| ----- |------| ---- |------|-------| ----- | ----- | ----- |356| <sup>**WizardLM-70B-V1.0**</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-70B-V1.0" target="_blank">HF Link</a> </sup>|<sup>📃**Coming Soon**</sup>| <sup>**7.78**</sup> | <sup>**92.91%**</sup> |<sup>**77.6%**</sup> | <sup> **50.6**</sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |357| <sup>WizardLM-13B-V1.2</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.2" target="_blank">HF Link</a> </sup>| | <sup>7.06</sup> | <sup>89.17%</sup> |<sup>55.3%</sup> | <sup>36.6 </sup>|<sup> <a href="https://ai.meta.com/resources/models-and-libraries/llama-downloads/" target="_blank">Llama 2 License </a></sup> |358| <sup>WizardLM-13B-V1.1</sup> |<sup> 🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.1" target="_blank">HF Link</a> </sup> | | <sup>6.76</sup> |<sup>86.32%</sup> | | <sup>25.0 </sup>| <sup>Non-commercial</sup>|359| <sup>WizardLM-30B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-30B-V1.0" target="_blank">HF Link</a></sup> | | <sup>7.01</sup> | | | <sup>37.8 </sup>| <sup>Non-commercial</sup> |360| <sup>WizardLM-13B-V1.0</sup> | <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-13B-V1.0" target="_blank">HF Link</a> </sup> | | <sup>6.35</sup> | <sup>75.31%</sup> | | <sup> 24.0 </sup> | <sup>Non-commercial</sup>|361| <sup>WizardLM-7B-V1.0 </sup>| <sup>🤗 <a href="https://huggingface.co/WizardLM/WizardLM-7B-V1.0" target="_blank">HF Link</a> </sup> |<sup> 📃 <a href="https://arxiv.org/abs/2304.12244" target="_blank">[WizardLM]</a> </sup>| | | |<sup>19.1 </sup>|<sup> Non-commercial</sup>|362</font>363 364## Comparing WizardCoder-Python-34B-V1.0 with Other LLMs.365 366🔥 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).367 368<p align="center" width="100%">369<a ><img src="https://raw.githubusercontent.com/nlpxucan/WizardLM/main/WizardCoder/imgs/compare_sota.png" alt="WizardCoder" style="width: 96%; min-width: 300px; display: block; margin: auto;"></a>370</p>371 372## Prompt Format373```374"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"375```376 377## Inference Demo Script378 379We provide the inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).380 381Note: This script supports `WizardLM/WizardCoder-Python-34B/13B/7B-V1.0`. If you want to inference with `WizardLM/WizardCoder-15B/3B/1B-V1.0`, please change the `stop_tokens = ['</s>']` to `stop_tokens = ['<|endoftext|>']` in the script.382 383## Citation384 385Please cite the repo if you use the data, method or code in this repo.386 387```388@article{luo2023wizardcoder,389 title={WizardCoder: Empowering Code Large Language Models with Evol-Instruct},390 author={Luo, Ziyang and Xu, Can and Zhao, Pu and Sun, Qingfeng and Geng, Xiubo and Hu, Wenxiang and Tao, Chongyang and Ma, Jing and Lin, Qingwei and Jiang, Daxin},391 journal={arXiv preprint arXiv:2306.08568},392 year={2023}393}394```395 396<!-- original-model-card end -->397