Official docs outline
9 sections- Llama overview
Llama model family, licensing, and ecosystem.
- Model cards and prompt formats
Model variants, context lengths, and chat prompt formats.
- Getting the models
Downloading weights from Meta, Hugging Face, and other sources.
- Prompting guide
Prompt engineering techniques specific to Llama.
- Fine-tuning
Adapting Llama with full and parameter-efficient methods.
- Quantization
Reducing memory and compute with lower precision.
- Vision capabilities
Multimodal image understanding.
- Llama Guard and safety
Input and output safety classification.
- Llama Stack
Standardized APIs and tooling for building Llama applications.
Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.