L

LLaMA 2 paper

Study / ResearchMentioned in 2 videos

Mentioned to show how tokens are pervasive in model descriptions and to motivate tokenizer training/coverage decisions (e.g., tokens trained on large corpora).

Videos Mentioning LLaMA 2 paper

Let's build the GPT Tokenizer

Let's build the GPT Tokenizer

Andrej Karpathy

Mentioned to show how tokens are pervasive in model descriptions and to motivate tokenizer training/coverage decisions (e.g., tokens trained on large corpora).

Llama 405b: Full 92 page Analysis, and Uncontaminated SIMPLE Benchmark Results

Llama 405b: Full 92 page Analysis, and Uncontaminated SIMPLE Benchmark Results

AI Explained