Code Generation
Code Generation
Code Generation
Paper: Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges
AlphaCode
Paper: Competition-Level Code Generation with AlphaCode
AlphaCode 2
Report: AlphaCode 2 Technical Report
StarCoder
Paper: StarCoder: may the source be with you!
The StarCoder models are 15.5B parameter models trained on 80+ programming languages from The Stack (v1.2), with opt-out requests excluded. The model uses Multi Query Attention, a context window of 8192 tokens, and was trained using the Fill-in-the-Middle objective on 1 trillion tokens.
StarChat-Alpha
Blog: Creating a Coding Assistant with StarCoder
DeciCoder
Blog: Introducing DeciCoder: The New Gold Standard in Efficient and Accurate Code Generation
CodeGen2.5
Blog: CodeGen2.5: Small, but mighty
Paper: CodeGen2: Lessons for Training LLMs on Programming and Natural Languages
Code: https://github.com/salesforce/CodeGen/tree/main/codegen25
Code Llama
Paper: Code Llama: Open Foundation Models for Code
Kaggle: https://www.kaggle.com/rkuo2000/llm-code-llama
Language Agent TreeSearch
Paper: Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Code: https://github.com/andyz245/LanguageAgentTreeSearch
Magicoder
Paper: Magicoder: Source Code Is All You Need
Kaggle: https://www.kaggle.com/code/rkuo2000/llm-magicoder
This site was last updated June 29, 2024.