51616 faf271b675 add ppl		2025-01-10 08:25:45 +00:00
..
configs.py	add use_kl_loss!	2025-01-09 19:56:08 +00:00
data_utils.py	readd remove cols after adding samples + no grad for base chat output	2025-01-09 20:19:14 +00:00
hooks.py	better logging	2024-12-23 04:03:19 +00:00
intx_sft.py	add ppl	2025-01-10 08:25:45 +00:00
model_loading.py	workaround to work with deepspeed (avoid dtype cast of hypernet)	2025-01-08 19:33:08 +00:00
modeling_utils.py	readd remove cols after adding samples + no grad for base chat output	2025-01-09 20:19:14 +00:00
pooling.py	add hyperlora w/ mean pooler + biggest head	2024-12-21 09:56:19 +00:00
training_utils.py	load checkpoint working	2025-01-09 15:49:34 +00:00
utils.py	biashyperinit + better config + bigger ctx_num_10 + perceiver args	2025-01-04 15:42:08 +00:00