bigcode-project/starcoder

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

7506 stars · 524 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

StarCoder is a 15B-parameter code language model trained on 80+ programming languages, and this repository hosts the fine-tuning and inference code for it. It includes training pipelines (including a chat fine-tune), evaluation, and quickstart code for code generation via Hugging Face transformers.

Use cases

• generate code completions with an open code LLM
• fine-tune a code language model on my own data
• run starcoder inference locally on a GPU
• build a coding assistant chatbot
• evaluate code generation models
• merge PEFT adapter layers into a base model

When to choose

• you want an open, permissively licensed code generation model with training and inference code
• you need to fine-tune or adapt a code LLM with PEFT/LoRA
• you want a self-hosted alternative to proprietary code assistants

When to avoid

• you need a maintained, actively updated project - the repo's last release was early 2024
• you lack GPU hardware for 15B-parameter inference
• you just want to call the model via an API without training code

Facets

library · maturity maintenance

llm-inference llm-training machine-learning large-language-models deep-learning artificial-intelligence developer-tools python code-llm huggingface fine-tuning peft starcoder code-completion code-generation gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="bigcode-project/starcoder")