summaryrefslogtreecommitdiff
path: root/candle-examples/examples/falcon/model.rs
Commit message (Expand)AuthorAgeFilesLines
* Move some models to candle-transformers so that it's easier to re-use. (#794)Laurent Mazare2023-09-101-485/+0
* Add a simple Module trait and implement it for the various nn layers (#500)Laurent Mazare2023-08-181-1/+1
* Use u8 tensors for masks. (#273)Laurent Mazare2023-07-291-1/+1
* Softmax numerical stability. (#267)Laurent Mazare2023-07-281-5/+7
* Rename the .r functions to .dims so as to be a bit more explicit. (#220)Laurent Mazare2023-07-221-4/+4
* Tensor mutability (#154)Laurent Mazare2023-07-131-3/+3
* Use arange in the examples. (#146)Laurent Mazare2023-07-121-2/+1
* Remove some dead-code pragmas. (#137)Laurent Mazare2023-07-111-19/+0
* VarBuilder path creation (#131)Laurent Mazare2023-07-101-49/+27
* Move the var-builder in a central place. (#130)Laurent Mazare2023-07-101-60/+2
* [nn] Move the Embedding and Activation parts. (#116)Laurent Mazare2023-07-101-29/+5
* Sketch the candle-nn crate. (#115)Laurent Mazare2023-07-101-79/+34
* Use F32 for the reduce ops. (#105)Laurent Mazare2023-07-071-1/+6
* Add a KV cache to falcon. (#104)Laurent Mazare2023-07-071-40/+72
* Add some caching to the causal mask. (#103)Laurent Mazare2023-07-071-2/+10
* Add some text generation pipeline for falcon. (#98)Laurent Mazare2023-07-071-5/+10
* Bugfixes. (#97)Laurent Mazare2023-07-061-1/+1
* Add the call to dense in the attention layer. (#96)Laurent Mazare2023-07-061-0/+1
* Fix some shape issues in falcon. (#95)Laurent Mazare2023-07-061-6/+17
* Sketch the Falcon model. (#93)Laurent Mazare2023-07-061-0/+590
generated by cgit v1.2.3 (git 2.39.1) at 2025-04-14 15:55:27 +0000