qishenghu / CodeInstruct
InstructCoder (former name:Codelnstruct) enables LLMs to edit code
☆47Updated 6 months ago
Related projects: ⓘ
- ☆39Updated 3 months ago
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆57Updated 5 months ago
- CRUXEval: Code Reasoning, Understanding, and Execution Evaluation☆99Updated last month
- Code for paper "LEVER: Learning to Verifiy Language-to-Code Generation with Execution" (ICML'23)☆76Updated last year
- [EMNLP'23] Execution-Based Evaluation for Open Domain Code Generation☆42Updated 8 months ago
- ☆80Updated 9 months ago
- RepoQA: Evaluating Long-Context Code Understanding☆96Updated this week
- [ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"☆45Updated 6 months ago
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆81Updated last month
- CodeUltraFeedback: aligning large language models to coding preferences☆62Updated 2 months ago
- ☆48Updated 3 months ago
- StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback☆48Updated 2 weeks ago
- ☆73Updated last year
- ☆16Updated last month
- Repoformer: Selective Retrieval for Repository-Level Code Completion (ICML 2024)☆33Updated 2 months ago
- ☆101Updated 2 months ago
- ☆25Updated last week
- Enhancing AI Software Engineering with Repository-level Code Graph☆60Updated 3 weeks ago
- Repository for paper Tools Are Instrumental for Language Agents in Complex Environments☆32Updated 8 months ago
- We have released the code and demo program required for LLM with self-verification☆45Updated 11 months ago
- A distributed, extensible, secure solution for evaluating machine generated code with unit tests in multiple programming languages.☆36Updated last month
- Official code for the paper "CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules"☆28Updated 9 months ago
- Language Models of Code are Few-Shot Commonsense Learners (EMNLP 2022)☆85Updated last year
- Lightweight tool to identify Data Contamination in LLMs evaluation☆39Updated 6 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆44Updated 8 months ago
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆65Updated last month
- BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions☆19Updated last month
- This is the official repository of the paper "OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI"☆79Updated last month
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆62Updated 3 months ago
- evol augment any dataset online☆55Updated last year