github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4148] Importing a Mistral finetune into Ollama fails with invalid file magic #2577

New Issue
Open
opened 2026-04-12 12:55:18 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 12:55:18 -05:00
Owner
Copy Link

Originally created by @BruceMacD on GitHub (May 4, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4148

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

Originally created by @BruceMacD on GitHub (May 4, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4148 ### 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
GiteaMirror added the bug label 2026-04-12 12:55:18 -05:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#2577
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?