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

..

sentencepiece

…

testdata

…

convert_bert.go

model: implement bert in ollama engine (#9080)

2025-09-15 15:35:59 -07:00

convert_commandr.go

…

convert_gemma2_adapter.go

…

convert_gemma2.go

…

convert_gemma3.go

…

convert_gemma3n.go

chore: cleanup comments + unused vars (#11225)

2025-06-27 11:45:33 -07:00

convert_gemma.go

…

convert_gptoss.go

convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)

2025-08-26 16:41:02 -07:00

convert_llama4.go

…

convert_llama_adapter.go

…

convert_llama.go

…

convert_mistral.go

…

convert_mixtral.go

…

convert_mllama.go

…

convert_phi3.go

…

convert_qwen2.go

…

convert_qwen25vl.go

…

convert_test.go

s#x/exp/maps#maps# (#11506)

2025-07-23 13:23:32 -07:00

convert.go

gpt-oss (#11672)

2025-08-05 12:21:16 -07:00

reader_safetensors.go

convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)

2025-08-26 16:41:02 -07:00

reader_test.go

convert: skip reading into memory when possible (#11507)

2025-08-14 15:03:57 -07:00

reader_torch.go

…

reader.go

convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018)

2025-08-26 16:41:02 -07:00

sentencepiece_model.proto

…

tensor_test.go

gpt-oss (#11672)

2025-08-05 12:21:16 -07:00

tensor.go

…

tokenizer_spm.go

…

tokenizer_test.go

…

tokenizer.go

s#x/exp/maps#maps# (#11506)

2025-07-23 13:23:32 -07:00