-
LLaMa-1: Open and Efficient Foundation Language Models
-
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
-
β βend-to-endβ directory
-
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling
-
https://www.together.ai/blog/redpajama-models-v1
-
https://github.com/openlm-research/open_llama
-