Llamas 🦙

• llama.com - hub (aggregates everything)
• Llama Recipes repo

Llama 3

• Paper: The Llama 3 Herd of Models
• Llama 3: Model Cards & Prompt formats - AFAIK the same tokenizer (wrapped tiktoken) and special tokens were used for all Llama 3.XX model iterations
  • clipped: Llama 3 Model Cards and Prompt formats

Llama 3.1:

• Llama 3.1 Model card - github.com/meta-llama/llama-models

Llama 3.2:

• Llama 3.2 Model Card - github.com/meta-llama/llama-model
  • clipped: llama-modelsmodelsllama3_2MODEL_CARD.md at main · meta-llamallama-models
• GitHub meta-llama - Llama 3.2
• Hugging Face Llama 3.2 1B
• Llama 3.2 From Scratch (A Standalone Notebook) by Sebastian Raschka
  • see also: Converting Llama 2 to Llama 3.2 From Scratch
  • see also: Converting a From-Scratch GPT Architecture to Llama 2

Comparison of Llama 3.2 1B and 3B

Llama 2

• Llama 2 Open Foundation and Fine-Tuned Chat Models

Llama Stack: Production Use Cases & Deployment

Llama Stack defines and standardizes the set of core building blocks needed to bring generative AI applications to market. These building blocks are presented in the form of interoperable APIs with a broad set of Service Providers providing their implementations.

• Quick Start
• Documentation
• Zero-to-Hero Guide

👉 Llama Stack repo

News

• Llama Website
• With 10x growth since 2023, Llama is the leading engine of AI innovation
• Llama 3.2 Revolutionizing edge AI and vision with open, customizable models