mirror of
https://github.com/ollama/ollama.git
synced 2026-03-27 02:58:43 +07:00
fa69b833cd
This change adds a tensorImportTransform interface for model-specific tensor transformations during safetensors import. This allows importing and modifying the standard HF based weights as well as the mlx-community derived pre-quantized safetensors repos to be directly imported into `ollama create`. Right now this only works with Qwen3.5 importing which does tensor renaming, norm weight shifting (it adds +1 to each value of the norm vectors), conv1d transposition, and casts to BF16s for F32 based vectors.