BigCode Project

BigCode Project is an open scientific collaboration run by Hugging Face and ServiceNow Research, focused on open and responsible development of LLMs for code.

Pinned Repositories

bigcode-dataset
Language:Jupyter Notebook366 9 3961
bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
Language:Python824 12 147219
bigcodebench
BigCodeBench: Benchmarking Code Generation Towards AGI
Language:Python232 6 4427
Megatron-LM
Ongoing research training transformer models at scale
Language:Python374 8 4149
octopack
🐙 OctoPack: Instruction Tuning Code Large Language Models
Language:Jupyter Notebook435 11 2026
starcoder
Home of StarCoder: fine-tuning & inference!
Language:Python7.3k 72 143521
starcoder.cpp
C++ implementation for 💫StarCoder
Language:C446 16 2936
starcoder2
Home of StarCoder2!
Language:Python1.8k 18 20160
starcoder2-self-align
[NeurIPS'24] Fully Transparent Self-Alignment for Code Generation
Language:Python225 6 615
the-stack-v2
Code for the curation of The Stack v2 and StarCoder2 training data
Language:Jupyter Notebook90 5 66

BigCode Project's Repositories

bigcode-project/starcoder
Home of StarCoder: fine-tuning & inference!
Language:Python7.3k 72 143521
bigcode-project/starcoder2
Home of StarCoder2!
Language:Python1.8k 18 20160
bigcode-project/bigcode-evaluation-harness
A framework for the evaluation of autoregressive code generation language models.
Language:Python824 12 147219
bigcode-project/starcoder.cpp
C++ implementation for 💫StarCoder
Language:C446 16 2936
bigcode-project/octopack
🐙 OctoPack: Instruction Tuning Code Large Language Models
Language:Jupyter Notebook435 11 2026
bigcode-project/Megatron-LM
Ongoing research training transformer models at scale
Language:Python374 8 4149
bigcode-project/bigcode-dataset
Language:Jupyter Notebook366 9 3961
bigcode-project/selfcodealign
[NeurIPS'24] SelfCodeAlign: Self-Alignment for Code Generation
Language:Python270 6 918
bigcode-project/bigcodebench
BigCodeBench: Benchmarking Code Generation Towards AGI
Language:Python232 6 4427
bigcode-project/jupytercoder
Language:JavaScript138 3 1812
bigcode-project/bigcode-analysis
Repository for analysis and experiments in the BigCode project.
Language:Jupyter Notebook115 7 1420
bigcode-project/the-stack-v2
Code for the curation of The Stack v2 and StarCoder2 training data
Language:Jupyter Notebook90 5 66
bigcode-project/astraios
Astraios: Parameter-Efficient Instruction Tuning Code Language Models
Language:Jupyter Notebook57 4 42
bigcode-project/bigcode-encoder
Language:Python29 3 42
bigcode-project/transformers
Language:Python26 7 48
bigcode-project/bigcode-website
Source of the website of the BigCode project.
Language:HTML19 4 25
bigcode-project/bigcodebench-annotation
BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions
Language:Jupyter Notebook19 2 710
bigcode-project/bigcode-inference-benchmark
Language:Python17 7 34
bigcode-project/bigcode-tokenizer
Language:Jupyter Notebook15 3 02
bigcode-project/pii-lib
Code for PII detection and redaction in code datasets
Language:Python11 2 02
bigcode-project/admin
A place for generic issues and administrative things.
9 2 9
bigcode-project/opt-out-v2
Repository for opt-out requests.
8 2 2.2k2
bigcode-project/Megatron-LM-deprecated
Language:Python5 4 0
bigcode-project/bigcode-notebooks
Language:Jupyter Notebook3 3 01
bigcode-project/text-generation-inference
Large Language Model Text Generation Inference
Language:Python3 1 0
bigcode-project/bigcode-data-mix
Language:Python1 3 01
bigcode-project/bigcode-demo
A place to build and share model demos
1 2 0
bigcode-project/search
Language:Python2 0