github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #4629] granite-code:20b-instruct-q8_0 error loading model vocabulary: unknown pre-tokenizer type: 'refact' #2907

New Issue
Closed
opened 2026-04-12 13:15:40 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-12 13:15:40 -05:00
Owner
Copy Link

Originally created by @ekolawole on GitHub (May 25, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4629

Originally assigned to: @BruceMacD on GitHub.

What is the issue?

llama_model_loader: - type f32: 419 tensors
llama_model_loader: - type q8_0: 209 tensors
llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'refact'
llama_load_model_from_file: exception loading model
libc++abi: terminating due to uncaught exception of type std::runtime_error: error loading model vocabulary: unknown pre-tokenizer type: 'refact'
time=2024-05-25T03:28:13.829-04:00 level=ERROR source=sched.go:344 msg="error loading llama server" error="llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'refact'"
[GIN] 2024/05/25 - 03:28:13 | 500 | 446.67725ms | | POST "/v1/chat/completions"

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.38

Originally created by @ekolawole on GitHub (May 25, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4629 Originally assigned to: @BruceMacD on GitHub. ### What is the issue? llama_model_loader: - type f32: 419 tensors llama_model_loader: - type q8_0: 209 tensors llama_model_load: error loading model: error loading model vocabulary: unknown pre-tokenizer type: 'refact' llama_load_model_from_file: exception loading model libc++abi: terminating due to uncaught exception of type std::runtime_error: error loading model vocabulary: unknown pre-tokenizer type: 'refact' time=2024-05-25T03:28:13.829-04:00 level=ERROR source=sched.go:344 msg="error loading llama server" error="llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'refact'" [GIN] 2024/05/25 - 03:28:13 | 500 | 446.67725ms | | POST "/v1/chat/completions" ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.38
GiteaMirror added the bug label 2026-04-12 13:15:40 -05:00
GiteaMirror commented 2026-04-12 13:15:42 -05:00
Author
Owner
Copy Link

@nurena24 commented on GitHub (May 26, 2024):

getting the same error with granite-code:20b-instruct-q3_K_M model in docker desktop running on 4090 GPU

<!-- gh-comment-id:2132060554 --> @nurena24 commented on GitHub (May 26, 2024): getting the same error with granite-code:20b-instruct-q3_K_M model in docker desktop running on 4090 GPU
GiteaMirror commented 2026-04-12 13:15:42 -05:00
Author
Owner
Copy Link

@wang-junjian commented on GitHub (May 26, 2024):

Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'refact'

macOS 14.5
ollama version is 0.1.38

<!-- gh-comment-id:2132276493 --> @wang-junjian commented on GitHub (May 26, 2024): Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'refact' macOS 14.5 ollama version is 0.1.38
GiteaMirror commented 2026-04-12 13:15:43 -05:00
Author
Owner
Copy Link

@wang-junjian commented on GitHub (May 28, 2024):

Install 0.1.39 version.
https://github.com/ollama/ollama/releases/tag/v0.1.39

<!-- gh-comment-id:2135332601 --> @wang-junjian commented on GitHub (May 28, 2024): Install 0.1.39 version. https://github.com/ollama/ollama/releases/tag/v0.1.39
GiteaMirror commented 2026-04-12 13:15:43 -05:00
Author
Owner
Copy Link

@BruceMacD commented on GitHub (May 30, 2024):

Thanks for the report. As noted above this model (and other granite family models) will work in ollama v0.1.39+ now.

<!-- gh-comment-id:2140902028 --> @BruceMacD commented on GitHub (May 30, 2024): Thanks for the report. As noted above this model (and other granite family models) will work in ollama v0.1.39+ now.
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#2907
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?