structuredllm / syncode
Efficient and general syntactical decoding for Large Language Models
β253Updated last week
Alternatives and similar repositories for syncode:
Users that are interested in syncode are comparing it to the libraries listed below
- π€ A specialized library for integrating context-free grammars (CFG) in EBNF with the Hugging Face Transformersβ115Updated 2 weeks ago
- A curated list of papers related to constrained decoding of LLM, along with their relevant code and resources.β189Updated last month
- A multi-programming language benchmark for LLMsβ241Updated 3 months ago
- A certifier for bias in LLMsβ24Updated 2 weeks ago
- [NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generationβ304Updated 2 months ago
- r2e: turn any github repository into a programming agent environmentβ114Updated this week
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.β167Updated 3 weeks ago
- Can It Edit? Evaluating the Ability of Large Language Models to Follow Code Editing Instructionsβ41Updated 8 months ago
- RepoQA: Evaluating Long-Context Code Understandingβ107Updated 5 months ago
- Enhancing AI Software Engineering with Repository-level Code Graphβ155Updated 3 weeks ago
- β¨ RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems - ICLR 2024β156Updated 8 months ago
- CRUXEval: Code Reasoning, Understanding, and Execution Evaluationβ136Updated 6 months ago
- CodeSage: Code Representation Learning At Scale (ICLR 2024)β102Updated 5 months ago
- Fine-tune SantaCoder for Code/Text Generation.β191Updated 2 years ago
- DafnyBench: A Benchmark for Formal Software Verificationβ31Updated 4 months ago
- EvoEval: Evolving Coding Benchmarks via LLMβ68Updated last year
- Allows to check regexes for overlaps. Based on greenery by @qntm.β50Updated 10 months ago
- Accepted by Transactions on Machine Learning Research (TMLR)β126Updated 6 months ago
- CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion (NeurIPS 2023)β139Updated 8 months ago
- Code and Data artifact for NeurIPS 2023 paper - "Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context". `multisβ¦β254Updated 8 months ago
- β91Updated 9 months ago
- [ICML 2023] Data and code release for the paper "DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation".β241Updated 5 months ago
- β392Updated this week
- Making code edting up to 7.7x faster using multi-layer speculationβ20Updated 2 months ago
- A collection of practical code generation tasks and tests in open source projects. Complementary to HumanEval by OpenAI.β139Updated 4 months ago
- The repository for paper "DebugBench: "Evaluating Debugging Capability of Large Language Models".β72Updated 9 months ago
- β60Updated 11 months ago
- Improving Alignment and Robustness with Circuit Breakersβ197Updated 7 months ago
- Multi-SWE-bench: A Multilingual Benchmark for Issue Resolvingβ128Updated last week
- Super-fast Structured Outputsβ207Updated this week