salesforce / CodeRL
This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (NeurIPS22).
☆521Updated 2 months ago
Alternatives and similar repositories for CodeRL:
Users that are interested in CodeRL are comparing it to the libraries listed below
- Generative model for code infilling and synthesis☆300Updated last year
- Code for the TMLR 2023 paper "PPOCoder: Execution-based Code Generation using Deep Reinforcement Learning"☆109Updated last year
- APPS: Automated Programming Progress Standard (NeurIPS 2021)☆448Updated 9 months ago
- Minimal library to train LLMs on TPU in JAX with pjit().☆282Updated last year
- Training language models to make programs faster☆87Updated 11 months ago
- Accepted by Transactions on Machine Learning Research (TMLR)☆126Updated 5 months ago
- CodeBERTScore: an automatic metric for code generation, based on BERTScore☆186Updated last year
- CodeGen2 models for program synthesis☆274Updated last year
- Data and code for "DocPrompting: Generating Code by Retrieving the Docs" @ICLR 2023☆241Updated last year
- ☆640Updated 4 months ago
- 🐙 OctoPack: Instruction Tuning Code Large Language Models☆458Updated last month
- Simple next-token-prediction for RLHF☆222Updated last year
- A framework for the evaluation of autoregressive code generation language models.☆912Updated 4 months ago
- A multi-programming language benchmark for LLMs☆239Updated 2 months ago
- ✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024☆148Updated 7 months ago
- Pretrained Language Models for Source code☆252Updated 3 years ago
- ☆423Updated 7 months ago
- ☆122Updated last year
- Implementation of ChatGPT RLHF (Reinforcement Learning with Human Feedback) on any generation model in huggingface's transformer (blommz-…☆555Updated 10 months ago
- Code for Parsel 🐍 - generate complex programs with language models☆424Updated last year
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆463Updated 2 years ago
- Fine-tune SantaCoder for Code/Text Generation.☆190Updated last year
- ☆107Updated 8 months ago
- [ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".☆238Updated 4 months ago
- CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)☆135Updated 7 months ago
- A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.☆801Updated 8 months ago
- ☆268Updated last year
- Code for "StructCoder: Structure-Aware Transformer for Code Generation"☆71Updated last year
- ☆159Updated 2 years ago
- ☆115Updated 8 months ago