FSoft-AI4Code / SRank-CodeRanker
[ACL 2024] Novel reranking method to select the best solutions for code generation
☆14Updated 3 months ago
Related projects: ⓘ
- Predicting Program Behavior with Dynamic Dependencies Learning☆22Updated last month
- [EMNLP 2023] The Vault: A Comprehensive Multilingual Dataset for Advancing Code Understanding and Generation☆81Updated 3 weeks ago
- Benchmark for Repository-Level Code Generation, focus on Executability, Correctness from Test Cases and Usage of Contexts from Cross-file…☆19Updated 2 months ago
- Graph-based method for end-to-end code completion with context awareness on repository☆42Updated 2 weeks ago
- Language Model for Mainframe Modernization☆40Updated 3 weeks ago
- ⚒️ Tree-sitter custom toolkit for extracting function and class from raw source file☆38Updated 2 months ago
- Open-source Self-Instruction Tuning Code LLM☆166Updated last year
- [EACL 2024] ICE-Score: Instructing Large Language Models to Evaluate Code☆67Updated 3 months ago
- evol augment any dataset online☆55Updated last year
- A collection of recent papers, benchmarks and datasets of AI4Code domain.☆54Updated 4 months ago
- ☆39Updated 3 months ago
- ☆77Updated this week
- CRUXEval: Code Reasoning, Understanding, and Execution Evaluation☆99Updated last month
- InstructCoder (former name:Codelnstruct) enables LLMs to edit code☆47Updated 6 months ago
- Distillation Contrastive Decoding: Improving LLMs Reasoning with Contrastive Decoding and Distillation☆29Updated 6 months ago
- ☆12Updated 6 months ago
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆57Updated 5 months ago
- ☆34Updated last month
- ☆53Updated 4 months ago
- Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructions☆38Updated last month
- Training language models to make programs faster☆80Updated 5 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
- A distributed, extensible, secure solution for evaluating machine generated code with unit tests in multiple programming languages.☆36Updated last month
- Harness used to benchmark aider against SWE Bench benchmarks☆44Updated 2 months ago
- EvolKit is an innovative framework designed to automatically enhance the complexity of instructions used for fine-tuning Large Language M…☆118Updated last week
- RepoQA: Evaluating Long-Context Code Understanding☆96Updated this week
- VNHSGE: Vietnamese High School Graduation Examination Dataset for Large Language Models☆22Updated last year
- Enhancing AI Software Engineering with Repository-level Code Graph☆60Updated 3 weeks ago
- RecGPT: Generative Pre-training for Text-based Recommendation (ACL 2024)☆25Updated last month
- ✨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024☆129Updated last month