Language Models
CodeGen
Introduced by Nijkamp et al. in CodeGen: An Open Large Language Model for Code with Multi-Turn Program SynthesisCodeGen is an autoregressive transformers with next-token prediction language modeling as the learning objective trained on a natural language corpus and programming language data curated from GitHub.
Source: CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Code Generation | 17 | 42.50% |
| Language Modelling | 5 | 12.50% |
| Program Synthesis | 4 | 10.00% |
| Memorization | 2 | 5.00% |
| In-Context Learning | 2 | 5.00% |
| Large Language Model | 2 | 5.00% |
| Benchmarking | 2 | 5.00% |
| Prompt Engineering | 1 | 2.50% |
| Question Answering | 1 | 2.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
