Importing a Mistral finetune into Ollama fails with `invalid file magic`

### What is the issue? Importing a custom Mistral-7B finetune into Ollama from safetensors fails with `invalid file magic`. Converting the same safetensors to gguf with llama.cpp works on import. Steps to reproduce: - Finetune Mistral with MLX, fuse the lora to the model to get the resulting safetensors. - Create the modelfile: ``` FROM ./model TEMPLATE """[INST] {{ .System }} {{ .Prompt }} [/INST]""" PARAMETER stop "[INST]" PARAMETER stop "[/INST]" ``` - Import the model ``` ❯ ollama create my-finetune -f ~/models/my-finetune/Modelfile transferring model data unpacking model metadata processing tensors creating model layer Error: invalid file magic ``` This Modelfile works, after converting the safetensors with llama.cpp: ``` FROM ./ggml-model-Q4_K_M.gguf TEMPLATE """[INST] {{ .System }} {{ .Prompt }} [/INST]""" PARAMETER stop "[INST]" PARAMETER stop "[/INST]" ``` ### OS macOS ### GPU _No response_ ### CPU _No response_ ### Ollama version 0.1.33