Model Family
Llama
Meta's open-weights LLM family — the backbone of most open-source fine-tunes.
Definition
Llama 1, 2, 3 and 3.1/3.2/3.3 are Meta's openly-released transformer LLMs. Sizes range from 1B to 405B parameters; later versions support vision and 128k context. The permissive licence has made Llama the foundation for most community fine-tunes and downstream open models.
Common use cases
- Self-hosting
- Fine-tuning
- Research