storytold/FineTrainers-Conditioning
2
0
Fork 0
mirror of https://github.com/storytold/FineTrainers-Conditioning.git synced 2026-10-09 00:09:45 +00:00
Code Issues Packages Projects Releases Wiki Activity
196 Commits 6 Branches 0 Tags
feature/cross_attn_patchify
Commit Graph

12 Commits

Author SHA1 Message Date
CrossProduct 28165e67d0 Adapter weights can be loaded. 2025-02-04 16:46:45 +00:00
CrossProduct ea3cd5c753 Full Finetune should work with this adapter removed the residual_x 2025-01-30 00:14:44 +00:00
CrossProduct 09e3f3dd5f move residual arg. 2025-01-30 00:03:12 +00:00
CrossProduct be1cb10894 make residual optional. 2025-01-30 00:02:31 +00:00
CrossProduct 707e001f7b The encoder hidden states and encode attention mask sizes do not match up in the validation pipeline. 2025-01-29 05:24:06 +00:00
CrossProduct 981767154b modify the forward pass 2025-01-22 06:56:22 +00:00
CrossProduct 07e755c2b3 modifcations to the loading of the weights. 2025-01-22 01:26:49 +00:00
CrossProduct 9fde6600dc Fixing weights copy. 2025-01-22 01:26:17 +00:00
CrossProduct 34996c1eb1 replaced the pipeline functions. 
time to test this then test the weight changes.
 2025-01-21 02:22:35 +00:00
CrossProduct 48d2b61029 Need to test saving and loading. 2025-01-18 06:58:04 +00:00
CrossProduct 3c605a124e Adding in the conditioned transformer 3d model 2025-01-18 06:47:39 +00:00
CrossProduct fa422c4ca5 Adding conditioned transformer layer change. 2025-01-18 06:29:01 +00:00