microsoft / PyCodeGPT
A pre-trained GPT model for Python code completion and generation
β270Updated last year
Alternatives and similar repositories for PyCodeGPT:
Users that are interested in PyCodeGPT are comparing it to the libraries listed below
- Generative model for code infilling and synthesisβ298Updated last year
- π OctoPack: Instruction Tuning Code Large Language Modelsβ448Updated 4 months ago
- Fine-tune SantaCoder for Code/Text Generation.β188Updated last year
- Data and code for "DocPrompting: Generating Code by Retrieving the Docs" @ICLR 2023β236Updated last year
- β623Updated 2 months ago
- β121Updated last year
- β85Updated last year
- CodeBERTScore: an automatic metric for code generation, based on BERTScoreβ181Updated 10 months ago
- This is the official code for the paper CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning (Neurβ¦β508Updated last week
- Script for downloading GitHub.β90Updated 6 months ago
- β266Updated last year
- β385Updated 5 months ago
- Meta-prompt: a simple self-improving language agentβ87Updated last year
- Run evaluation on LLMs using human-eval benchmarkβ393Updated last year
- Ongoing research training transformer models at scaleβ380Updated 5 months ago
- CodeGen2 models for program synthesisβ274Updated last year
- β172Updated last year
- [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898β203Updated 8 months ago
- Code for the paper "Efficient Training of Language Models to Fill in the Middle"β170Updated last year
- PaL: Program-Aided Language Models (ICML 2023)β481Updated last year
- APPS: Automated Programming Progress Standard (NeurIPS 2021)β435Updated 7 months ago
- β¨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024β141Updated 5 months ago
- Accepted by Transactions on Machine Learning Research (TMLR)β123Updated 3 months ago
- A collection of practical code generation tasks and tests in open source projects. Complementary to HumanEval by OpenAI.β129Updated last month
- This repository contains all the code for collecting large scale amounts of code from GitHub.β105Updated last year
- xCodeEval: A Large Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrievalβ77Updated 4 months ago
- A hard gym for programmingβ145Updated 6 months ago
- Minimal library to train LLMs on TPU in JAX with pjit().β280Updated last year
- A multi-programming language benchmark for LLMsβ219Updated last week
- [ICLR 2023] Code for the paper "Binding Language Models in Symbolic Languages"β306Updated last year