bigcode-project / bigcode-analysisLinks
Repository for analysis and experiments in the BigCode project.
☆128Updated last year
Alternatives and similar repositories for bigcode-analysis
Users that are interested in bigcode-analysis are comparing it to the libraries listed below
Sorting:
- Code for the paper "Efficient Training of Language Models to Fill in the Middle"☆194Updated 2 years ago
- Accepted by Transactions on Machine Learning Research (TMLR)☆136Updated last year
- Open Instruction Generalist is an assistant trained on massive synthetic instructions to perform many millions of tasks☆210Updated last year
- ☆32Updated 2 years ago
- Data and code for "DocPrompting: Generating Code by Retrieving the Docs" @ICLR 2023☆251Updated 2 years ago
- Fine-tune SantaCoder for Code/Text Generation.☆194Updated 2 years ago
- ☆53Updated 9 months ago
- Python tools for processing the stackexchange data dumps into a text dataset for Language Models☆85Updated 2 years ago
- Code for the curation of The Stack v2 and StarCoder2 training data☆123Updated last year
- This is the repo for the paper Shepherd -- A Critic for Language Model Generation☆220Updated 2 years ago
- This project studies the performance and robustness of language models and task-adaptation methods.☆155Updated last year
- Open Source WizardCoder Dataset☆162Updated 2 years ago
- Multipack distributed sampler for fast padding-free training of LLMs☆202Updated last year
- Scaling Data-Constrained Language Models☆342Updated 5 months ago
- ☆277Updated 2 years ago
- CodeGen2 models for program synthesis☆271Updated 2 years ago
- ☆80Updated 8 months ago
- A framework for few-shot evaluation of autoregressive language models.☆105Updated 2 years ago
- [EMNLP'23] Execution-Based Evaluation for Open Domain Code Generation☆49Updated 2 years ago
- Minimal library to train LLMs on TPU in JAX with pjit().☆299Updated 2 years ago
- A repository for transformer critique learning and generation☆89Updated 2 years ago
- CodeBERTScore: an automatic metric for code generation, based on BERTScore☆206Updated last year
- Pre-training code for CrystalCoder 7B LLM☆55Updated last year
- Astraios: Parameter-Efficient Instruction Tuning Code Language Models☆63Updated last year
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆226Updated 3 months ago
- Code repository for the c-BTM paper☆108Updated 2 years ago
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆315Updated 2 years ago
- evol augment any dataset online☆61Updated 2 years ago
- RepoQA: Evaluating Long-Context Code Understanding☆127Updated last year
- Experiments on speculative sampling with Llama models☆127Updated 2 years ago