WizardCoder-Python-34B-V1.0 Open-source Code Generation Model - Focused on Efficient Python Code Generation

Wizardcoder Python 7B V1.0

Developed by vanillaOVO

WizardCoder-Python-34B-V1.0 is a high-performance code generation model based on the Llama2 architecture, focusing on Python code generation tasks.

Large Language Model

Transformers

Other#Code generation #Mathematical reasoning #Multi-task Q&A

Downloads 2,206

Release Time : 6/19/2024

Model Overview

This model performs excellently in the field of code generation, especially in Python code generation, and is suitable for scenarios such as development assistance and automated programming.

Model Features

High-performance code generation

Achieved 73.2 pass@1 in the HumanEval benchmark test, surpassing models such as GPT4 and Claude2.

Multiple model size options

Provides model versions with different parameter scales from 1B to 34B to meet different computing requirements.

Open-source and commercially available

Released under the Llama2 license, allowing commercial use.

Model Capabilities

Python code generation

Code completion

Code explanation

Programming problem solving

Use Cases

Development assistance

Automated code generation

Automatically generate Python code snippets based on natural language descriptions

Achieved a 73.2% accuracy rate in the HumanEval test

Programming education

Help students understand programming concepts and solve programming problems

Software development

Code completion

Provide intelligent code completion suggestions in the IDE

🚀 WizardCoder and Related Models

This repository focuses on a series of models including WizardCoder, WizardMath, and WizardLM, aiming to provide high - performance language models for various tasks such as code generation and math problem - solving.

📚 Documentation

Note

This is a replica of the official repository, intended solely for research purposes to replicate results. If there are any copyright issues, please contact me.

🤗 HF Repo •🐱 Github Repo • 🐦 Twitter • 📃 [WizardLM] • 📃 [WizardCoder] • 📃 [WizardMath]

👋 Join our Discord

News

🔥🔥🔥[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.

❗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. The 82.0 and 72.5 are tested by ourselves with the latest API (2023/08/26).

Property	Details
Model Type	WizardCoder - Python - 34B - V1.0, WizardCoder - 15B - V1.0, etc.
Training Data	Not specified
Metrics	code_eval
Library Name	transformers
License	llama2 (for some models), OpenRAIL - M (for some models)

Model	Checkpoint	Paper	HumanEval	MBPP	Demo	License
WizardCoder - Python - 34B - V1.0	🤗 HF Link	📃 [WizardCoder]	73.2	61.2	Demo	Llama2
WizardCoder - 15B - V1.0	🤗 HF Link	📃 [WizardCoder]	59.8	50.6	--	OpenRAIL - M
WizardCoder - Python - 13B - V1.0	🤗 HF Link	📃 [WizardCoder]	64.0	55.6	--	Llama2
WizardCoder - Python - 7B - V1.0	🤗 HF Link	📃 [WizardCoder]	55.5	51.6	Demo	Llama2
WizardCoder - 3B - V1.0	🤗 HF Link	📃 [WizardCoder]	34.8	37.4	--	OpenRAIL - M
WizardCoder - 1B - V1.0	🤗 HF Link	📃 [WizardCoder]	23.8	28.6	--	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](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, which is 9.2 points higher than the SOTA open - source LLM.

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

[08/09/2023] We released WizardLM - 70B - V1.0 model. Here is [Full Model Weight](https://huggingface.co/WizardLM/WizardLM - 70B - V1.0).

^Model	^Checkpoint	^Paper	^{MT - Bench}	^AlpacaEval	^GSM8k	^HumanEval	^License
^{WizardLM - 70B - V1.0}	^{🤗 HF Link}	^{📃Coming Soon}	^7.78	^92.91%	^77.6%	^50.6	^{Llama 2 License}
^{WizardLM - 13B - V1.2}	^{🤗 HF Link}		^7.06	^89.17%	^55.3%	^36.6	^{Llama 2 License}
^{WizardLM - 13B - V1.1}	^{🤗 HF Link}		^6.76	^86.32%		^25.0	^{Non - commercial}
^{WizardLM - 30B - V1.0}	^{🤗 HF Link}		^7.01			^37.8	^{Non - commercial}
^{WizardLM - 13B - V1.0}	^{🤗 HF Link}		^6.35	^75.31%		^24.0	^{Non - commercial}
^{WizardLM - 7B - V1.0}	^{🤗 HF Link}	^{📃 [WizardLM]}				^19.1	^{Non - commercial}

Comparing WizardCoder - Python - 34B - V1.0 with Other LLMs

🔥 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).

Prompt Format

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

Inference Demo Script

We provide the inference demo code here.

Citation

Please cite the repo if you use the data, method or code in this repo.

@article{luo2023wizardcoder,
  title={WizardCoder: Empowering Code Large Language Models with Evol - Instruct},
  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},
  journal={arXiv preprint arXiv:2306.08568},
  year={2023}
}

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご