radu/LLamaRecipes

mirror de https://github.com/facebookresearch/llama-recipes.git

Autor	SHA1 Mensagem	Data
Matthias Reso	9def4fbafd Remove micro_batch_training parameter and replace with gradient_accumulation_steps	2 anos atrás
Brian Vaughan	3faf005226 fix a bug in the config for use_fast_kernels	2 anos atrás
lchu	feaa344af3 resolve conflicts	2 anos atrás
Hamid Shojanazeri	44ef280d31 adding flash attention and xformer memory efficient through PT SDPA	2 anos atrás
lchu	895dfcea30 add nightly check for using low_cpu_fsdp mode	2 anos atrás
chauhang	4767f09ecd Initial commit	2 anos atrás