sahil280114/codealpaca resource

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1514 stars · 113 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Code Alpaca is a 20K instruction-following dataset and training code for fine-tuning LLaMA models on code generation tasks, based on Stanford Alpaca. It includes the dataset, the Self-Instruct-based data generation pipeline, and fine-tuning scripts.

Use cases

• fine-tune a llama model to generate code from instructions
• get a dataset of code generation instruction-output pairs
• generate synthetic instruction data for code tasks
• reproduce an instruction-tuned code model
• train a small open model for programming help

When to choose

• you want to instruction-tune LLaMA-style models for code generation
• you need a compact 20K code instruction dataset
• you want to study the Self-Instruct data generation approach

When to avoid

• you need model weights out of the box (not released)
• you need a safety-tuned production chat model
• you need up-to-date training tooling or strong benchmark results (evals are a todo)

Facets

dataset · maturity maintenance

machine-learning llm-training data-generation prompt-engineering large-language-models machine-learning developer-tools python code-generation instruction-tuning llama fine-tuning self-instruct dataset

Member repositories

For agents

markdown · JSON · MCP: product_card(name="sahil280114/codealpaca")