summaryrefslogtreecommitdiffstats
path: root/models/clip/embeddings.py
Commit message (Expand)AuthorAgeFilesLines
* FixVolpeon2023-04-161-1/+1
* FixVolpeon2023-04-161-32/+9
* FixVolpeon2023-04-161-1/+1
* UpdateVolpeon2023-04-161-2/+1
* FixVolpeon2023-04-151-1/+1
* TI via LoRAVolpeon2023-04-151-50/+26
* UpdateVolpeon2023-04-091-1/+4
* UpdateVolpeon2023-04-091-3/+4
* UpdateVolpeon2023-04-081-1/+1
* TI: Bring back old embedding decayVolpeon2023-04-041-8/+7
* Improved sparse embeddingsVolpeon2023-04-031-31/+21
* TI: Delta learningVolpeon2023-04-031-17/+33
* RevertVolpeon2023-04-011-38/+4
* Combined TI with embedding and LoRAVolpeon2023-04-011-4/+15
* Experimental: TI via LoRAVolpeon2023-04-011-15/+38
* Add support for Adafactor, add TI initializer noiseVolpeon2023-04-011-1/+9
* UpdateVolpeon2023-03-311-24/+9
* Fix TIVolpeon2023-03-271-9/+25
* Fix TIVolpeon2023-03-271-25/+9
* Revert to regular embeddingsVolpeon2023-03-271-19/+15
* Sparse TI embeddings without sparse tensorsVolpeon2023-03-271-17/+23
* Fix TI embeddings initVolpeon2023-03-261-1/+1
* Improved TI embeddingsVolpeon2023-03-261-7/+23
* UpdateVolpeon2023-03-011-1/+1
* Embedding normalization: Ignore tensors with grad = 0Volpeon2023-02-211-8/+0
* Optimized embedding normalizationVolpeon2023-01-171-5/+2
* UpdateVolpeon2023-01-171-0/+3
* More modularizationVolpeon2023-01-131-5/+1
* Removed PromptProcessor, modularized training loopVolpeon2023-01-131-1/+5
* Code deduplicationVolpeon2023-01-131-2/+2
* Fixed TI decayVolpeon2023-01-121-1/+9
* UpdateVolpeon2023-01-071-5/+0
* Added EMA to TIVolpeon2023-01-051-3/+3
* Various cleanupsVolpeon2023-01-051-0/+5
* UpdateVolpeon2023-01-041-1/+3
* UpdateVolpeon2023-01-011-11/+11
* CleanupVolpeon2023-01-011-11/+0
* UpdatesVolpeon2023-01-011-0/+11
* FixVolpeon2022-12-311-5/+7
* UpdateVolpeon2022-12-311-14/+16
* Bugfixes for multi-vector token handlingVolpeon2022-12-311-9/+18
* FixesVolpeon2022-12-311-1/+1
* Added multi-vector embeddingsVolpeon2022-12-311-0/+109