ollama/model/models
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
..
bert model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
gemma2 model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
gemma3 model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
gemma3n model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
gptoss batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
llama batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
llama4 batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
mistral3 batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
mllama batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
qwen2 batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
qwen3 batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
qwen25vl batch: use tensors for outputs (#12185) 2025-09-15 14:33:06 -07:00
models.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00