summaryrefslogtreecommitdiffstats
path: root/training
Commit message (Expand)AuthorAgeFilesLines
...
* Combined TI with embedding and LoRAVolpeon2023-04-011-58/+18
* Experimental: TI via LoRAVolpeon2023-04-011-26/+4
* UpdateVolpeon2023-04-012-7/+18
* Add support for Adafactor, add TI initializer noiseVolpeon2023-04-012-1/+5
* UpdateVolpeon2023-03-311-0/+2
* Fix TIVolpeon2023-03-271-8/+10
* Sparse TI embeddings without sparse tensorsVolpeon2023-03-271-10/+8
* Improved TI embeddingsVolpeon2023-03-261-2/+1
* Improved inverted tokensVolpeon2023-03-261-10/+9
* Fix training with guidanceVolpeon2023-03-251-3/+9
* UpdateVolpeon2023-03-251-15/+21
* UpdateVolpeon2023-03-241-6/+5
* Fixed Lora training perf issueVolpeon2023-03-241-7/+8
* Lora fix: Save config JSON, tooVolpeon2023-03-241-0/+3
* Refactoring, fixed Lora trainingVolpeon2023-03-244-65/+32
* Bring back Perlin offset noiseVolpeon2023-03-231-1/+14
* UpdateVolpeon2023-03-234-17/+14
* FixVolpeon2023-03-221-1/+1
* Log DAdam/DAdan dVolpeon2023-03-211-0/+14
* Fixed SNR weighting, re-enabled xformersVolpeon2023-03-212-21/+84
* Restore min SNRVolpeon2023-03-191-13/+12
* New loss weighting from arxiv.org:2204.00227Volpeon2023-03-181-2/+5
* Better SNR weightingVolpeon2023-03-181-3/+3
* Fixed snr weight calculationVolpeon2023-03-171-1/+4
* Fix loss=nanVolpeon2023-03-171-2/+2
* Test: https://arxiv.org/pdf/2303.09556.pdfVolpeon2023-03-171-3/+8
* UpdateVolpeon2023-03-072-15/+16
* UpdateVolpeon2023-03-061-16/+0
* Added Perlin noise to trainingVolpeon2023-03-041-0/+17
* Removed offset noise from training, added init offset to pipelineVolpeon2023-03-031-10/+2
* Implemented different noise offsetVolpeon2023-03-032-22/+10
* Low freq noise with randomized strengthVolpeon2023-03-031-1/+8
* Better low freq noiseVolpeon2023-03-021-1/+1
* Changed low freq noiseVolpeon2023-03-011-23/+10
* UpdateVolpeon2023-03-014-28/+32
* Fixed TI normalization orderVolpeon2023-02-213-15/+19
* FixVolpeon2023-02-211-6/+3
* Don't rely on Accelerate for gradient accumulationVolpeon2023-02-212-30/+29
* Embedding normalization: Ignore tensors with grad = 0Volpeon2023-02-212-6/+16
* UpdateVolpeon2023-02-181-7/+14
* Added Lion optimizerVolpeon2023-02-171-4/+5
* Remove xformers, switch to Pytorch NightlyVolpeon2023-02-174-9/+8
* FixVolpeon2023-02-161-4/+2
* Integrated WIP UniPC schedulerVolpeon2023-02-161-8/+22
* UpdateVolpeon2023-02-151-1/+1
* Made low-freq noise configurableVolpeon2023-02-141-6/+11
* Better noise generation during training: https://www.crosslabs.org/blog/diffu...Volpeon2023-02-131-0/+7
* UpdateVolpeon2023-02-133-3/+3
* Fixed Lora trainingVolpeon2023-02-081-18/+5
* Fix Lora memory usageVolpeon2023-02-074-9/+3