Nhines/WizardCoder-Python-34B-V1.0-llamafile
0128
1---2license: llama23library_name: transformers4tags:5- code6- llamafile7metrics:8- code_eval9base_model: WizardLM/WizardCoder-Python-34B-V1.010inference: false11model_creator: WizardLM12model_type: llama13prompt_template: >14 Below is an instruction that describes a task. Write a response that15 appropriately completes the request.16 17 18 ### Instruction:19 20 {prompt}21 22 23 ### Response:24quantized_by: TheBloke25model-index:26- name: WizardCoder-Python-34B-V1.027 results:28 - task:29 type: text-generation30 dataset:31 name: HumanEval32 type: openai_humaneval33 metrics:34 - type: pass@135 value: 0.73236 name: pass@137 verified: false38---39 40# WizardCoder Python 34B V1.0 - llamafile41- Model creator: [WizardLM](https://huggingface.co/WizardLM)42- Original model: [WizardCoder Python 34B V1.0](https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0)43 44<!-- description start -->45## Description46 47This repo contains llamafile format model files for [WizardLM's WizardCoder Python 34B V1.0](https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0).48 49WARNING: This README may contain inaccuracies. It was generated automatically by forking <a href=/TheBloke/WizardCoder-Python-34B-V1.0-GGUF>TheBloke/WizardCoder-Python-34B-V1.0-GGUF</a> and piping the README through sed. Errors should be reported to jartine, and do not reflect TheBloke. You can also support his work on [Patreon](https://www.patreon.com/TheBlokeAI).50<!-- README_llamafile.md-about-llamafile start -->51### About llamafile52 53llamafile is a new format introduced by Mozilla Ocho on Nov 20th 2023. It uses Cosmopolitan Libc to turn LLM weights into runnable llama.cpp binaries that run on the stock installs of six OSes for both ARM64 and AMD64. llamafile 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.54 55Here is an incomplate list of clients and libraries that are known to support llamafile:56 57* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for llamafile. Offers a CLI and a server option.58* [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.59* [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.60* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.61* [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.62* [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.63* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.64* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.65* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.66 67<!-- README_llamafile.md-about-llamafile end -->68<!-- repositories-available start -->69## Repositories available70 71* [AWQ model(s) for GPU inference.](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-AWQ)72* [GPTQ models for GPU inference, with multiple quantisation parameter options.](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-GPTQ)73* [2, 3, 4, 5, 6 and 8-bit llamafile models for CPU+GPU inference](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile)74* [WizardLM's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardCoder-Python-34B-V1.0)75<!-- repositories-available end -->76 77<!-- prompt-template start -->78## Prompt template: Alpaca79 80```81Below is an instruction that describes a task. Write a response that appropriately completes the request.82 83### Instruction:84{prompt}85 86### Response:87 88```89 90<!-- prompt-template end -->91 92 93<!-- compatibility_llamafile start -->94## Compatibility95 96These quantised llamafilev2 files are compatible with llama.cpp from August 27th onwards, as of commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221)97 98They are also compatible with many third party UIs and libraries - please see the list at the top of this README.99 100## Explanation of quantisation methods101<details>102 <summary>Click to see details</summary>103 104The new methods available are:105* 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)106* 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.107* 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.108* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw109* 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 bpw110 111Refer to the Provided Files table below to see what files use which methods, and how.112</details>113<!-- compatibility_llamafile end -->114 115<!-- README_llamafile.md-provided-files start -->116## Provided files117 118| Name | Quant method | Bits | Size | Max RAM required | Use case |119| ---- | ---- | ---- | ---- | ---- | ----- |120| [wizardcoder-python-34b-v1.0.Q2_K.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q2_K.llamafile) | Q2_K | 2 | 14.21 GB| 16.71 GB | smallest, significant quality loss - not recommended for most purposes |121| [wizardcoder-python-34b-v1.0.Q3_K_S.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q3_K_S.llamafile) | Q3_K_S | 3 | 14.61 GB| 17.11 GB | very small, high quality loss |122| [wizardcoder-python-34b-v1.0.Q3_K_M.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q3_K_M.llamafile) | Q3_K_M | 3 | 16.28 GB| 18.78 GB | very small, high quality loss |123| [wizardcoder-python-34b-v1.0.Q3_K_L.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q3_K_L.llamafile) | Q3_K_L | 3 | 17.77 GB| 20.27 GB | small, substantial quality loss |124| [wizardcoder-python-34b-v1.0.Q4_0.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q4_0.llamafile) | Q4_0 | 4 | 19.05 GB| 21.55 GB | legacy; small, very high quality loss - prefer using Q3_K_M |125| [wizardcoder-python-34b-v1.0.Q4_K_S.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q4_K_S.llamafile) | Q4_K_S | 4 | 19.15 GB| 21.65 GB | small, greater quality loss |126| [wizardcoder-python-34b-v1.0.Q4_K_M.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q4_K_M.llamafile) | Q4_K_M | 4 | 20.22 GB| 22.72 GB | medium, balanced quality - recommended |127| [wizardcoder-python-34b-v1.0.Q5_0.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q5_0.llamafile) | Q5_0 | 5 | 23.24 GB| 25.74 GB | legacy; medium, balanced quality - prefer using Q4_K_M |128| [wizardcoder-python-34b-v1.0.Q5_K_S.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q5_K_S.llamafile) | Q5_K_S | 5 | 23.24 GB| 25.74 GB | large, low quality loss - recommended |129| [wizardcoder-python-34b-v1.0.Q5_K_M.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q5_K_M.llamafile) | Q5_K_M | 5 | 23.84 GB| 26.34 GB | large, very low quality loss - recommended |130| [wizardcoder-python-34b-v1.0.Q6_K.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q6_K.llamafile) | Q6_K | 6 | 27.68 GB| 30.18 GB | very large, extremely low quality loss |131| [wizardcoder-python-34b-v1.0.Q8_0.llamafile](https://huggingface.co/jartine/WizardCoder-Python-34B-V1.0-llamafile/blob/main/wizardcoder-python-34b-v1.0.Q8_0.llamafile) | Q8_0 | 8 | 35.86 GB| 38.36 GB | very large, extremely low quality loss - not recommended |132 133**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.134 135 136 137<!-- README_llamafile.md-provided-files end -->138 139<!-- README_llamafile.md-how-to-download start -->140## How to download llamafile files141 142**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.143 144The following clients/libraries will automatically download models for you, providing a list of available models to choose from:145- LM Studio146- LoLLMS Web UI147- Faraday.dev148 149### In `text-generation-webui`150 151Under Download Model, you can enter the model repo: jartine/WizardCoder-Python-34B-V1.0-llamafile and below it, a specific filename to download, such as: wizardcoder-python-34b-v1.0.q4_K_M.llamafile.152 153Then click Download.154 155### On the command line, including multiple files at once156 157I recommend using the `huggingface-hub` Python library:158 159```shell160pip3 install huggingface-hub>=0.17.1161```162 163Then you can download any individual model file to the current directory, at high speed, with a command like this:164 165```shell166huggingface-cli download jartine/WizardCoder-Python-34B-V1.0-llamafile wizardcoder-python-34b-v1.0.q4_K_M.llamafile --local-dir . --local-dir-use-symlinks False167```168 169<details>170 <summary>More advanced huggingface-cli download usage</summary>171 172You can also download multiple files at once with a pattern:173 174```shell175huggingface-cli download jartine/WizardCoder-Python-34B-V1.0-llamafile --local-dir . --local-dir-use-symlinks False --include='*Q4_K*llamafile'176```177 178For 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).179 180To accelerate downloads on fast connections (1Gbit/s or higher), install `hf_transfer`:181 182```shell183pip3 install hf_transfer184```185 186And set environment variable `HF_HUB_ENABLE_HF_TRANSFER` to `1`:187 188```shell189HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download jartine/WizardCoder-Python-34B-V1.0-llamafile wizardcoder-python-34b-v1.0.q4_K_M.llamafile --local-dir . --local-dir-use-symlinks False190```191 192Windows CLI users: Use `set HUGGINGFACE_HUB_ENABLE_HF_TRANSFER=1` before running the download command.193</details>194<!-- README_llamafile.md-how-to-download end -->195 196<!-- README_llamafile.md-how-to-run start -->197## Example `llama.cpp` command198 199Make sure you are using `llama.cpp` from commit [d0cee0d36d5be95a0d9088b674dbb27354107221](https://github.com/ggerganov/llama.cpp/commit/d0cee0d36d5be95a0d9088b674dbb27354107221) or later.200 201```shell202./main -ngl 32 -m wizardcoder-python-34b-v1.0.q4_K_M.llamafile --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:"203```204 205Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.206 207Change `-c 4096` to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the llamafile file and set by llama.cpp automatically.208 209If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`210 211For 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)212 213## How to run in `text-generation-webui`214 215Further instructions here: [text-generation-webui/docs/llama.cpp.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp.md).216 217## How to run from Python code218 219You can use llamafile models from Python using the [llama-cpp-python](https://github.com/abetlen/llama-cpp-python) or [ctransformers](https://github.com/marella/ctransformers) libraries.220 221### How to load this model from Python using ctransformers222 223#### First install the package224 225```bash226# Base ctransformers with no GPU acceleration227pip install ctransformers>=0.2.24228# Or with CUDA GPU acceleration229pip install ctransformers[cuda]>=0.2.24230# Or with ROCm GPU acceleration231CT_HIPBLAS=1 pip install ctransformers>=0.2.24 --no-binary ctransformers232# Or with Metal GPU acceleration for macOS systems233CT_METAL=1 pip install ctransformers>=0.2.24 --no-binary ctransformers234```235 236#### Simple example code to load one of these llamafile models237 238```python239from ctransformers import AutoModelForCausalLM240 241# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.242llm = AutoModelForCausalLM.from_pretrained("jartine/WizardCoder-Python-34B-V1.0-llamafile", model_file="wizardcoder-python-34b-v1.0.q4_K_M.llamafile", model_type="llama", gpu_layers=50)243 244print(llm("AI is going to"))245```246 247## How to use with LangChain248 249Here's guides on using llama-cpp-python or ctransformers with LangChain:250 251* [LangChain + llama-cpp-python](https://python.langchain.com/docs/integrations/llms/llamacpp)252* [LangChain + ctransformers](https://python.langchain.com/docs/integrations/providers/ctransformers)253 254<!-- README_llamafile.md-how-to-run end -->255 256<!-- footer start -->257<!-- 200823 -->258## Discord259 260For further support, and discussions on these models and AI in general, join us at:261 262[jartine AI's Discord server](https://discord.gg/FwAVVu7eJ4)263 264## Thanks, and how to contribute265 266 267 268I'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.269 270If 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.271 272 273 274 275 276 277 278And thank you again to mozilla for their generous grant.279 280<!-- footer end -->281 282<!-- original-model-card start -->283# Original model card: WizardLM's WizardCoder Python 34B V1.0284 285 286<p align="center">287🤗 <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>288</p>289<p align="center">290 👋 Join our <a href="https://discord.gg/VZjjHtWrKs" target="_blank">Discord</a>291</p>292 293## News294 295- 🔥🔥🔥[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).296- [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).297 298❗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).299 300 301| Model | Checkpoint | Paper | HumanEval | MBPP | Demo | License |302| ----- |------| ---- |------|-------| ----- | ----- |303| 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> |304| 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> |305| 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> |306| 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 | [Demo](http://47.103.63.15:50086/) | <a href="https://huggingface.co/spaces/bigcode/bigcode-model-license-agreement" target="_blank">OpenRAIL-M</a> |307| 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> |308 309 310- 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**.311- 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.312 313<font size=4>314 315| Model | Checkpoint | Paper | GSM8k | MATH |Online Demo| License|316| ----- |------| ---- |------|-------| ----- | ----- |317| 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> |318| 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> |319| 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>|320</font>321 322 323- [08/09/2023] We released **WizardLM-70B-V1.0** model. Here is [Full Model Weight](https://huggingface.co/WizardLM/WizardLM-70B-V1.0).324 325<font size=4>326 327 328| <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>|329| ----- |------| ---- |------|-------| ----- | ----- | ----- |330| <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> |331| <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> |332| <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>|333| <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> |334| <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>|335| <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>|336</font>337 338 339## Comparing WizardCoder-Python-34B-V1.0 with Other LLMs.340 341🔥 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).342 343<p align="center" width="100%">344<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>345</p>346 347## Prompt Format348```349"Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\n{instruction}\n\n### Response:"350```351 352## Inference Demo Script353 354We provide the inference demo code [here](https://github.com/nlpxucan/WizardLM/tree/main/demo).355 356## Citation357 358Please cite the repo if you use the data, method or code in this repo.359 360```361@article{luo2023wizardcoder,362 title={WizardCoder: Empowering Code Large Language Models with Evol-Instruct},363 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},364 journal={arXiv preprint arXiv:2306.08568},365 year={2023}366}367```368 369<!-- original-model-card end -->