13 commits

Author	SHA1	Message	Date
Luciferian Ink	1ca0e04004	fix grad flow	2025-01-18 02:02:56 -06:00
Luciferian Ink	5adf1c7133	allow grads when calculating entropies	2025-01-18 01:42:00 -06:00
Luciferian Ink	9e42f5dd1d	revert to original patcher style, fix warning	2025-01-17 20:36:07 -06:00
Luciferian Ink	cff0dcb7ab	allow patch_batch_size to be adjusted in the forward() method	2025-01-17 19:41:17 -06:00
Luciferian Ink	175fce61df	remove spammy warning	2025-01-17 18:04:37 -06:00
Luciferian Ink	6129756e10	remove unused argument	2025-01-17 18:04:25 -06:00
Luciferian Ink	420326184a	allow loading of the entropy model directly	2025-01-17 18:03:18 -06:00
Pedro Rodriguez	6ffeb66b53	Changes for training entropy model and correcting attention in local models (#25) ... Summary: - Refactor local model configs to be separate and clearer - Add attention arguments and correct which attention is used in local models - Preparation for being able to have an entropy train script - Fix failing unit tests Test Plan:	2025-01-17 14:23:01 -08:00
Ink	caec8d2621	allow flex-attention to be disabled (#19) ... * allow flex-attention to silently fail * allow flex-attn to be disabled via an env var	2025-01-14 09:32:07 -08:00
Pedro Rodriguez	1da3dd9315	Update preprocess_entropies script to blt inference + add fsspec support (#23) ... Summary: Test Plan:	2025-01-13 15:28:14 -08:00
Pedro Rodriguez	b0120da72f	Replace regular filesystem calls with fsspec + add s3 support (#18) ... Summary: For compatibility with either local/nfs or S3 datasets, swap to fsspec. Add a tool to compare local and remote filesystems Test Plan: - Ran regular train script - Ran with config with data in S3	2025-01-10 11:04:41 -08:00
Pedro Rodriguez	d4ddb95322	Add plotting code from paper (#17) ... Summary: Test Plan:	2025-01-09 12:11:50 -08:00
Pedro Rodriguez	bcc039bb75	Initial commit	2024-12-12 15:32:30 -08:00