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 #9042] ollama create suddenly stops #5885

New Issue
Closed
opened 2026-04-12 17:13:15 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 17:13:15 -05:00
Owner
Copy Link

Originally created by @cicapatak on GitHub (Feb 12, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/9042

Originally assigned to: @pdevine on GitHub.

What is the issue?

I ran a full fine tune on Llama3.2. using MLX.
When finished, I tried to run "ollama create", using the model file previously created. This model file worked wonderfully for lora fine tunes to the same model.
Now, after the full fine tune, the creation process starts normally, and then the message "converting model", then "converting adapter" and then nothing. It just stops.

Relevant log output

panic: runtime error: index out of range [1] with length 1

goroutine 49 [running]:
github.com/ollama/ollama/convert.(*llamaAdapter).repack(0x140003b2360, {0x140003b2480, 0x1c}, {0x14000e16000, 0xc00, 0xc00}, {0x1400012f0e0, 0x1, 0x801?})
	github.com/ollama/ollama/convert/convert_llama_adapter.go:74 +0x430
github.com/ollama/ollama/convert.safetensor.WriteTo({{0x103bb4060, 0x140005021a0}, {0x1037dcbe4, 0x14}, {0x1400012f0c8, 0x4}, 0x1476521fe, 0x1800, 0x140004ac9c0}, {0x103bb3d88, ...})
	github.com/ollama/ollama/convert/reader_safetensors.go:144 +0x4b4
github.com/ollama/ollama/llm.ggufWriteTensor({0x103bb8368, 0x14000444030}, {{0x140003b2480, 0x1c}, 0x0, 0x0, {0x1400012f0e0, 0x1, 0x1}, {0x12e374898, ...}}, ...)
	github.com/ollama/ollama/llm/gguf.go:656 +0x14c
github.com/ollama/ollama/llm.WriteGGUF({0x103bb8368, 0x14000444030}, 0x14000ddc9c0, {0x140006e7508, 0xfc, 0x12e})
	github.com/ollama/ollama/llm/gguf.go:556 +0x548
github.com/ollama/ollama/convert.AdapterParameters.writeFile(...)
	github.com/ollama/ollama/convert/convert.go:
87
github.com/ollama/ollama/convert.ConvertAdapter({0x103bb4060, 0x140005021a0}, {0x103bb8368, 0x14000444030}, 0x14000459830)
	github.com/ollama/ollama/convert/convert.go:156 +0x2ec
github.com/ollama/ollama/server.convertFromSafetensors(0x14000389380, {0x14000526058, 0x1, 0x1}, 0x1, 0x14000231900)
	github.com/ollama/ollama/server/create.go:255 +0x2e0
github.com/ollama/ollama/server.convertModelFromFiles(0x14000389380, {0x14000526058, 0x1, 0x1}, 0x1, 0x14000231900)
	github.com/ollama/ollama/server/create.go:151 +0x178
github.com/ollama/ollama/server.(*Server).CreateHandler.func1()
	github.com/ollama/ollama/server/create.go:105 +0x564
created by github.com/ollama/ollama/server.(*Server).CreateHandler in goroutine 43
	github.com/ollama/ollama/server/create.go:62 +0x5a8

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.5.7

Originally created by @cicapatak on GitHub (Feb 12, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/9042 Originally assigned to: @pdevine on GitHub. ### What is the issue? I ran a full fine tune on Llama3.2. using MLX. When finished, I tried to run "ollama create", using the model file previously created. This model file worked wonderfully for lora fine tunes to the same model. Now, after the full fine tune, the creation process starts normally, and then the message "converting model", then "converting adapter" and then nothing. It just stops. ### Relevant log output ```shell panic: runtime error: index out of range [1] with length 1 goroutine 49 [running]: github.com/ollama/ollama/convert.(*llamaAdapter).repack(0x140003b2360, {0x140003b2480, 0x1c}, {0x14000e16000, 0xc00, 0xc00}, {0x1400012f0e0, 0x1, 0x801?}) github.com/ollama/ollama/convert/convert_llama_adapter.go:74 +0x430 github.com/ollama/ollama/convert.safetensor.WriteTo({{0x103bb4060, 0x140005021a0}, {0x1037dcbe4, 0x14}, {0x1400012f0c8, 0x4}, 0x1476521fe, 0x1800, 0x140004ac9c0}, {0x103bb3d88, ...}) github.com/ollama/ollama/convert/reader_safetensors.go:144 +0x4b4 github.com/ollama/ollama/llm.ggufWriteTensor({0x103bb8368, 0x14000444030}, {{0x140003b2480, 0x1c}, 0x0, 0x0, {0x1400012f0e0, 0x1, 0x1}, {0x12e374898, ...}}, ...) github.com/ollama/ollama/llm/gguf.go:656 +0x14c github.com/ollama/ollama/llm.WriteGGUF({0x103bb8368, 0x14000444030}, 0x14000ddc9c0, {0x140006e7508, 0xfc, 0x12e}) github.com/ollama/ollama/llm/gguf.go:556 +0x548 github.com/ollama/ollama/convert.AdapterParameters.writeFile(...) github.com/ollama/ollama/convert/convert.go: 87 github.com/ollama/ollama/convert.ConvertAdapter({0x103bb4060, 0x140005021a0}, {0x103bb8368, 0x14000444030}, 0x14000459830) github.com/ollama/ollama/convert/convert.go:156 +0x2ec github.com/ollama/ollama/server.convertFromSafetensors(0x14000389380, {0x14000526058, 0x1, 0x1}, 0x1, 0x14000231900) github.com/ollama/ollama/server/create.go:255 +0x2e0 github.com/ollama/ollama/server.convertModelFromFiles(0x14000389380, {0x14000526058, 0x1, 0x1}, 0x1, 0x14000231900) github.com/ollama/ollama/server/create.go:151 +0x178 github.com/ollama/ollama/server.(*Server).CreateHandler.func1() github.com/ollama/ollama/server/create.go:105 +0x564 created by github.com/ollama/ollama/server.(*Server).CreateHandler in goroutine 43 github.com/ollama/ollama/server/create.go:62 +0x5a8 ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.5.7
GiteaMirror added the bug label 2026-04-12 17:13:15 -05:00
GiteaMirror commented 2026-04-12 17:13:16 -05:00
Author
Owner
Copy Link

@pdevine commented on GitHub (Mar 16, 2025):

@cicapatak sorry for the late reply. Do you still have the Modelfile so I can try to debug this? From your stack trace it's definitely getting caught trying to read your lora adapter.

<!-- gh-comment-id:2727132866 --> @pdevine commented on GitHub (Mar 16, 2025): @cicapatak sorry for the late reply. Do you still have the Modelfile so I can try to debug this? From your stack trace it's definitely getting caught trying to read your lora adapter.
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#5885
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?