summaryrefslogtreecommitdiff
path: root/candle-nn
Commit message (Expand)AuthorAgeFilesLines
* Transposed conv1d in candle-nn. (#1252)Laurent Mazare2023-11-031-0/+94
* Add the swiglu activation from the chatglm PR. (#1246)Laurent Mazare2023-11-022-0/+7
* Add hard-sigmoid and hard-swish activations (#1244)jamjamjon2023-11-022-0/+9
* Add support for the marian base model. (#1221)Laurent Mazare2023-10-301-0/+2
* Allow for different behavior between training and eval (#1213)Laurent Mazare2023-10-293-2/+43
* Add the relu2 and relu6 activations. (#1201)Laurent Mazare2023-10-271-0/+4
* Add fuse-conv-bn method for Conv2d (#1196)jamjamjon2023-10-272-0/+25
* Expose the fields from batch-norm. (#1176)Laurent Mazare2023-10-251-2/+12
* Add Binary Cross Entropy With Logit Loss to nn crate (#1157)Ogundepo Odunayo2023-10-232-0/+69
* Make func cloneable. (#1137)Laurent Mazare2023-10-202-6/+8
* Add the sequential layer. (#1136)Laurent Mazare2023-10-202-0/+64
* Experiment with resnet (#1128)Laurent Mazare2023-10-191-0/+9
* feat: add pth varbuilder (#1108)OlivierDehaene2023-10-161-0/+41
* Add a matvec cpu benchmark. (#1076)Laurent Mazare2023-10-121-3/+22
* Convmixer (#1073)Laurent Mazare2023-10-111-2/+2
* Only optimize float tensors. (#1069)Laurent Mazare2023-10-101-0/+5
* More general seq forward functions for RNNs. (#1050)Laurent Mazare2023-10-071-27/+25
* Use AsRef<str> for set_one. (#1033)Laurent Mazare2023-10-051-1/+1
* Improve the quantized whisper setup. (#1018)Laurent Mazare2023-10-021-1/+1
* Bump the version to 0.3.0. (#1014)Laurent Mazare2023-10-012-21/+1
* Use a silu activation in mistral. (#991)Laurent Mazare2023-09-291-0/+4
* Use the gelu-erf activation. (#969)Laurent Mazare2023-09-261-3/+1
* Configurable layer idx for the lstm layer. (#962)Laurent Mazare2023-09-251-4/+12
* Depreate the VarBuilder::from_safetensors function. (#951)Laurent Mazare2023-09-241-2/+6
* Self-contained safetensors for the multiprocess llama example. (#950)Laurent Mazare2023-09-241-31/+17
* Add the buffered safetensor wrapper. (#948)Laurent Mazare2023-09-231-0/+32
* Self-contained safetensor wrappers (#946)Laurent Mazare2023-09-231-1/+42
* Use yoke to provide a self-referential container for mmaped safetenso… (#939)Laurent Mazare2023-09-231-11/+5
* VarMap setter functions (#938)Laurent Mazare2023-09-231-0/+38
* Add clone to various nn layers. (#910)Laurent Mazare2023-09-207-11/+11
* Fix the leaky relu. (#898)Laurent Mazare2023-09-191-1/+2
* Bump the crate versions to v0.2.3. (#886)Laurent Mazare2023-09-181-1/+1
* Remove the parameters for the Wuerstchen layer-norm. (#879)Laurent Mazare2023-09-171-1/+1
* Replication pad (#861)Laurent Mazare2023-09-151-0/+15
* DiffNeXt/unet (#859)Laurent Mazare2023-09-151-0/+24
* Add leaky-relu in the activation enum. (#858)Laurent Mazare2023-09-151-0/+2
* Add the upblocks. (#853)Laurent Mazare2023-09-141-0/+4
* Add support to flan-t5 (#840)Juarez Bochi2023-09-131-0/+6
* Extract T5 module and add main function to use it (#829)Juarez Bochi2023-09-132-1/+5
* Bump the crate version + update the changelog. (#822)Laurent Mazare2023-09-121-1/+1
* Bugfix for the conv2d cpu kernel. (#820)Laurent Mazare2023-09-111-1/+1
* Add weight, bias, and hidden_size methods (#816)Eric Buehler2023-09-112-0/+21
* im2col based conv2d (#802)Laurent Mazare2023-09-101-16/+69
* Bugfix so that im2col produce the same results as conv2d. (#801)Laurent Mazare2023-09-101-1/+5
* Add an im2col based benchmark. (#800)Laurent Mazare2023-09-101-2/+71
* TinyViT backbone for segment-anything. (#787)Laurent Mazare2023-09-091-13/+13
* Segment Anything - process images (#766)Laurent Mazare2023-09-072-6/+7
* More segment-anything. (#763)Laurent Mazare2023-09-071-0/+11
* Expose the conv2d-transpose layers. (#761)Laurent Mazare2023-09-072-1/+45
* Add a nn layer for conv-transpose2d. (#760)Laurent Mazare2023-09-071-1/+50
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-05 03:56:39 +0000