CodeGen
modelFamily of autoregressive code generation models from 350M to 16.1B parameters. Trained with multi-step paradigm: natural language → multilingual code → monolingual (Python) specialization.
Competitive with OpenAI Codex at release. Introduced the MTPB (Multi-Turn Programming Benchmark). ICLR 2023. By Nijkamp, Pang, Hayashi et al. Apache 2.0.
Model Details
Architecture DENSE
Parameters 16.1B
Variants
| Name | Parameters | Notes |
|---|---|---|
| CodeGen-350M | 350M | — |
| CodeGen-2B | 2B | — |
| CodeGen-6B | 6B | — |
| CodeGen-16B | 16.1B | — |
Paper
arXiv: 2203.13474
Venue: ICLR 2023