bigcode-evaluation-harness
Code evaluation framework
A framework for evaluating autoregressive code generation language models in terms of their accuracy and robustness.
A framework for the evaluation of autoregressive code generation language models.
846 stars
12 watching
225 forks
Language: Python
last commit: 4 months ago
Linked from 1 awesome list
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
| bigcode-project/starcoder2 | Trains models to generate code in multiple programming languages | 1,808 |
 modelscope/evalscope | A framework for efficiently evaluating and benchmarking large models | 308 |
 flageval-baai/flageval | An evaluation toolkit and platform for assessing large models in various domains | 307 |
 princeton-nlp/intercode | An interactive code environment framework for evaluating language agents through execution feedback. | 198 |
 bin123apple/autocoder | An AI model designed to generate and execute code automatically | 816 |
 codefuse-ai/codefuse-devops-eval | An evaluation suite for assessing foundation models in the DevOps field. | 690 |
 relari-ai/continuous-eval | Provides a comprehensive framework for evaluating Large Language Model (LLM) applications and pipelines with customizable metrics | 455 |
 open-evals/evals | A framework for evaluating OpenAI models and an open-source registry of benchmarks. | 19 |
 quantifiedcode/quantifiedcode | A code analysis and automation platform | 111 |
 ukgovernmentbeis/inspect_ai | A framework for evaluating large language models | 669 |
 allenai/olmo-eval | A framework for evaluating language models on NLP tasks | 326 |
| quantifiedcode/python-anti-patterns | A collection of common Python coding mistakes and poor practices | 1,716 |
 huggingface/evaluate | An evaluation framework for machine learning models and datasets, providing standardized metrics and tools for comparing model performance. | 2,063 |
 nvlabs/verilog-eval | An evaluation harness for generating Verilog code from natural language prompts | 188 |
 budecosystem/code-millenials | A state-of-the-art open-source code generation model with human evaluability score comparable to GPT-4 and Google's proprietary models. | 20 |