root
/
ollama
mirror of https://github.com/ollama/ollama.git
1
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity
ollama/convert
History
Patrick Devine 2717dce6fe
convert: convert bf16 vision weights to fp16 (#12324) 
This change moves back to converting bf16 vision weights to fp16,
specifically if they start with the name "v." (such as v.blk.0.attn_k.weight).

This fixes a bug where converted images are failing because they are trying
to call `im2col` which doesn't have a bf16 kernel in ggml.
 		2025-09-17 17:43:17 -07:00
..
sentencepiece chore(all): replace instances of interface with any (#10067) 2025-04-02 09:44:27 -07:00
testdata convert: import support for command-r models from safetensors (#6063) 2025-01-15 16:31:22 -08:00
convert.go gpt-oss (#11672) 2025-08-05 12:21:16 -07:00
convert_bert.go model: implement bert in ollama engine (#9080) 2025-09-15 15:35:59 -07:00
convert_commandr.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_gemma.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_gemma2.go next ollama runner (#7913) 2025-02-13 16:31:21 -08:00
convert_gemma2_adapter.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_gemma3.go fix: change default context size for gemma3 (#9744) 2025-03-13 13:59:19 -07:00
convert_gemma3n.go chore: cleanup comments + unused vars (#11225) 2025-06-27 11:45:33 -07:00
convert_gptoss.go convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018) 2025-08-26 16:41:02 -07:00
convert_llama.go fix mllama conversion (#10716) 2025-05-15 12:15:01 -07:00
convert_llama4.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_llama_adapter.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_mistral.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_mixtral.go convert: utility for merging tensors (#11069) 2025-06-20 11:12:01 -07:00
convert_mllama.go fix: mllama quality (#10807) 2025-05-22 11:30:49 -07:00
convert_phi3.go Move quantization to new backend (#10363) 2025-05-06 11:20:48 -07:00
convert_qwen2.go model: add Qwen2.5-VL support (#10385) 2025-05-13 20:58:02 -07:00
convert_qwen25vl.go feat: uneven splits (#11048) 2025-06-11 12:10:54 -07:00
convert_test.go s#x/exp/maps#maps# (#11506) 2025-07-23 13:23:32 -07:00
reader.go convert(gptoss): mxfp4 to ggml layout to avoid jit conversion (#12018) 2025-08-26 16:41:02 -07:00
reader_safetensors.go convert: convert bf16 vision weights to fp16 (#12324) 2025-09-17 17:43:17 -07:00
reader_test.go convert: convert bf16 vision weights to fp16 (#12324) 2025-09-17 17:43:17 -07:00
reader_torch.go llama4 2025-04-25 16:59:20 -07:00
sentencepiece_model.proto all: fix typos in documentation, code, and comments (#7021) 2024-12-10 12:58:06 -08:00
tensor.go convert: utility for merging tensors (#11069) 2025-06-20 11:12:01 -07:00
tensor_test.go gpt-oss (#11672) 2025-08-05 12:21:16 -07:00
tokenizer.go s#x/exp/maps#maps# (#11506) 2025-07-23 13:23:32 -07:00
tokenizer_spm.go temporary work around for converting spm 2025-03-11 14:49:18 -07:00
tokenizer_test.go model: handle multiple eos tokens (#10577) 2025-05-16 13:40:23 -07:00