Commit Graph

3 Commits

Author SHA1 Message Date
Michael Yang
3f6642f6fc model: implement bert in ollama engine (#9080)
* fix truncate

* s/SentencePieceModel/SentencePiece/

* bert

* wordpiece

* refactor pooling

* more tokenizers

* normalize embeddings
2025-09-15 15:35:59 -07:00
Michael Yang
6f7117145f batch: use tensors for outputs (#12185)
this cleans up the model interface slightly without too much impact in
other areas
2025-09-15 14:33:06 -07:00
Michael Yang
5994e8e8fd embedding gemma model (#12181)
* ollama: add embeddings
2025-09-04 09:09:07 -07:00