github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 05:05:37 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4969] Error pulling Quen2 models: unknown pre-tokenizer type: 'qwen2' #49650

New Issue
Closed
opened 2026-04-28 12:29:16 -05:00 by GiteaMirror · 9 comments
GiteaMirror commented 2026-04-28 12:29:16 -05:00
Owner
Copy Link

Originally created by @agilebean on GitHub (Jun 11, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4969

What is the issue?

After downloading any Qwen2 model, e.g.

ollama run qwen2:1.5b

the following error is shown:

Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

tested on Ollama versions 0.1.38 and 0.1.42

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.1.38

Originally created by @agilebean on GitHub (Jun 11, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4969 ### What is the issue? After downloading any Qwen2 model, e.g. ``` ollama run qwen2:1.5b ``` the following error is shown: ``` Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' ``` tested on Ollama versions `0.1.38` and `0.1.42` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.1.38
GiteaMirror added the bug label 2026-04-28 12:29:16 -05:00
GiteaMirror commented 2026-04-28 12:29:23 -05:00
Author
Owner
Copy Link

@agilebean commented on GitHub (Jun 11, 2024):

This bug could be related to the MacOS app. Removing and reinstalling didn't help.
However, installing with brew did solve the problem.

<!-- gh-comment-id:2159569019 --> @agilebean commented on GitHub (Jun 11, 2024): This bug could be related to the MacOS app. Removing and reinstalling didn't help. However, installing with brew did solve the problem.
GiteaMirror commented 2026-04-28 12:29:26 -05:00
Author
Owner
Copy Link

@ChenCheng2Cs commented on GitHub (Jun 11, 2024):

This bug could be related to the MacOS app. Removing and reinstalling didn't help. However, installing with brew did solve the problem.

how do you solve it? To be precised, how do you install with brew? Thanks

<!-- gh-comment-id:2159859190 --> @ChenCheng2Cs commented on GitHub (Jun 11, 2024): > This bug could be related to the MacOS app. Removing and reinstalling didn't help. However, installing with brew did solve the problem. how do you solve it? To be precised, how do you install with brew? Thanks
GiteaMirror commented 2026-04-28 12:29:27 -05:00
Author
Owner
Copy Link

@MrSuddenJoy commented on GitHub (Jun 11, 2024):

@ChenCheng2Cs brew install <pkg-name>. Classic way of installing packages with brew.......

<!-- gh-comment-id:2160478921 --> @MrSuddenJoy commented on GitHub (Jun 11, 2024): @ChenCheng2Cs `brew install <pkg-name>`. Classic way of installing packages with `brew`.......
GiteaMirror commented 2026-04-28 12:29:29 -05:00
Author
Owner
Copy Link

@0x2CA commented on GitHub (Jun 14, 2024):

The same problem,But there's no problem with qwen:14b

➜ ～ brew search ollama
==> Formulae
ollama

==> Casks
notesollama                ollama ✔                   ollamac
➜  ~ ollama run qwen2:7b
Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'
<!-- gh-comment-id:2167041052 --> @0x2CA commented on GitHub (Jun 14, 2024): The same problem,But there's no problem with qwen:14b ```shell ➜ ～ brew search ollama ==> Formulae ollama ==> Casks notesollama ollama ✔ ollamac ➜ ~ ollama run qwen2:7b Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' ```
GiteaMirror commented 2026-04-28 12:29:31 -05:00
Author
Owner
Copy Link

@smg1024 commented on GitHub (Jun 14, 2024):

The same problem,But there's no problem with qwen:14b

➜ ～ brew search ollama
==> Formulae
ollama

==> Casks
notesollama                ollama ✔                   ollamac
➜  ~ ollama run qwen2:7b
Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

@0x2CA
Reinstall ollama with homebrew brew reinstall ollama and restart the service with brew services restart ollama
This fixed the problem for me

<!-- gh-comment-id:2168195294 --> @smg1024 commented on GitHub (Jun 14, 2024): > The same problem,But there's no problem with qwen:14b > > ```shell > ➜ ～ brew search ollama > ==> Formulae > ollama > > ==> Casks > notesollama ollama ✔ ollamac > ➜ ~ ollama run qwen2:7b > Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' > ``` @0x2CA Reinstall ollama with homebrew `brew reinstall ollama` and restart the service with `brew services restart ollama` This fixed the problem for me
GiteaMirror commented 2026-04-28 12:29:32 -05:00
Author
Owner
Copy Link

@0x2CA commented on GitHub (Jun 17, 2024):

The same problem,But there's no problem with qwen:14b

➜ ～ brew search ollama
==> Formulae
ollama

==> Casks
notesollama                ollama ✔                   ollamac
➜  ~ ollama run qwen2:7b
Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2'

@0x2CA Reinstall ollama with homebrew brew reinstall ollama and restart the service with brew services restart ollama This fixed the problem for me

➜  0x2ca brew uninstall ollama
==> Uninstalling Cask ollama
==> Backing App 'Ollama.app' up to '/opt/homebrew/Caskroom/ollama/0.1.36/Olla
==> Removing App '/Applications/Ollama.app'
==> Unlinking Binary '/opt/homebrew/bin/ollama'
==> Purging files for version 0.1.36 of Cask ollama
==> Autoremoving 1 unneeded formula:
jsoncpp
Uninstalling /opt/homebrew/Cellar/jsoncpp/1.9.5... (18 files, 300.2KB)
➜  0x2ca brew install ollama
==> Auto-updating Homebrew...
Adjust how often this is run with HOMEBREW_AUTO_UPDATE_SECS or disable with
HOMEBREW_NO_AUTO_UPDATE. Hide these hints with HOMEBREW_NO_ENV_HINTS (see `man brew`).
==> Auto-updated Homebrew!
Updated 4 taps (homebrew/bundle, homebrew/services, homebrew/core and homebrew/cask).
==> New Formulae
codecov-cli        geni               kubelogin          poutine
==> New Casks
font-beiruti                           font-palemonasmufi-regular
font-palemonasmufi-bold                impel
font-palemonasmufi-bolditalic          xnapper
font-palemonasmufi-italic

You have 3 outdated formulae and 3 outdated casks installed.

Warning: Treating ollama as a formula. For the cask, use homebrew/cask/ollama or specify the `--cask` flag.
==> Downloading https://ghcr.io/v2/homebrew/core/ollama/manifests/0.1.44
###################################################################### 100.0%
==> Fetching ollama
==> Downloading https://ghcr.io/v2/homebrew/core/ollama/blobs/sha256:59b3c5ad
###################################################################### 100.0%
==> Pouring ollama--0.1.44.arm64_sonoma.bottle.tar.gz
==> Caveats
To start ollama now and restart at login:
  brew services start ollama
Or, if you don't want/need a background service you can just run:
  /opt/homebrew/opt/ollama/bin/ollama serve
==> Summary
🍺  /opt/homebrew/Cellar/ollama/0.1.44: 8 files, 22.8MB
==> Running `brew cleanup ollama`...
Disable this behaviour by setting HOMEBREW_NO_INSTALL_CLEANUP.
Hide these hints with HOMEBREW_NO_ENV_HINTS (see `man brew`).
Removing: /Users/admin/Library/Caches/Homebrew/ollama_bottle_manifest--0.1.43... (7.6KB)
Removing: /Users/admin/Library/Caches/Homebrew/ollama--0.1.43... (8.7MB)
➜  0x2ca  brew reinstall ollama
Warning: Treating ollama as a formula. For the cask, use homebrew/cask/ollama or specify the `--cask` flag.
==> Downloading https://ghcr.io/v2/homebrew/core/ollama/manifests/0.1.44
Already downloaded: /Users/admin/Library/Caches/Homebrew/downloads/83b152ad7c5a778f288d7f789241a76f790ed1f6ec9ed3bedeb0a8ac99f32ff6--ollama-0.1.44.bottle_manifest.json
==> Fetching ollama
==> Downloading https://ghcr.io/v2/homebrew/core/ollama/blobs/sha256:59b3c5ad
Already downloaded: /Users/admin/Library/Caches/Homebrew/downloads/da923370403cf7cf18885ec7d844b00becda22650ff2e2aadfde85da96680eb6--ollama--0.1.44.arm64_sonoma.bottle.tar.gz
==> Reinstalling ollama
==> Pouring ollama--0.1.44.arm64_sonoma.bottle.tar.gz
==> Caveats
To start ollama now and restart at login:
  brew services start ollama
Or, if you don't want/need a background service you can just run:
  /opt/homebrew/opt/ollama/bin/ollama serve
==> Summary
🍺  /opt/homebrew/Cellar/ollama/0.1.44: 8 files, 22.8MB
==> Running `brew cleanup ollama`...
Disable this behaviour by setting HOMEBREW_NO_INSTALL_CLEANUP.
Hide these hints with HOMEBREW_NO_ENV_HINTS (see `man brew`).
➜  0x2ca brew services restart ollama
Could not enable service: 125: Domain does not support specified action
Error: Failure while executing; `/bin/launchctl enable gui/501/homebrew.mxcl.ollama` exited with 125.
<!-- gh-comment-id:2172469424 --> @0x2CA commented on GitHub (Jun 17, 2024): > > The same problem,But there's no problem with qwen:14b > > ```shell > > ➜ ～ brew search ollama > > ==> Formulae > > ollama > > > > ==> Casks > > notesollama ollama ✔ ollamac > > ➜ ~ ollama run qwen2:7b > > Error: llama runner process has terminated: signal: abort trap error:error loading model vocabulary: unknown pre-tokenizer type: 'qwen2' > > ``` > > @0x2CA Reinstall ollama with homebrew `brew reinstall ollama` and restart the service with `brew services restart ollama` This fixed the problem for me ``` shell ➜ 0x2ca brew uninstall ollama ==> Uninstalling Cask ollama ==> Backing App 'Ollama.app' up to '/opt/homebrew/Caskroom/ollama/0.1.36/Olla ==> Removing App '/Applications/Ollama.app' ==> Unlinking Binary '/opt/homebrew/bin/ollama' ==> Purging files for version 0.1.36 of Cask ollama ==> Autoremoving 1 unneeded formula: jsoncpp Uninstalling /opt/homebrew/Cellar/jsoncpp/1.9.5... (18 files, 300.2KB) ➜ 0x2ca brew install ollama ==> Auto-updating Homebrew... Adjust how often this is run with HOMEBREW_AUTO_UPDATE_SECS or disable with HOMEBREW_NO_AUTO_UPDATE. Hide these hints with HOMEBREW_NO_ENV_HINTS (see `man brew`). ==> Auto-updated Homebrew! Updated 4 taps (homebrew/bundle, homebrew/services, homebrew/core and homebrew/cask). ==> New Formulae codecov-cli geni kubelogin poutine ==> New Casks font-beiruti font-palemonasmufi-regular font-palemonasmufi-bold impel font-palemonasmufi-bolditalic xnapper font-palemonasmufi-italic You have 3 outdated formulae and 3 outdated casks installed. Warning: Treating ollama as a formula. For the cask, use homebrew/cask/ollama or specify the `--cask` flag. ==> Downloading https://ghcr.io/v2/homebrew/core/ollama/manifests/0.1.44 ###################################################################### 100.0% ==> Fetching ollama ==> Downloading https://ghcr.io/v2/homebrew/core/ollama/blobs/sha256:59b3c5ad ###################################################################### 100.0% ==> Pouring ollama--0.1.44.arm64_sonoma.bottle.tar.gz ==> Caveats To start ollama now and restart at login: brew services start ollama Or, if you don't want/need a background service you can just run: /opt/homebrew/opt/ollama/bin/ollama serve ==> Summary 🍺 /opt/homebrew/Cellar/ollama/0.1.44: 8 files, 22.8MB ==> Running `brew cleanup ollama`... Disable this behaviour by setting HOMEBREW_NO_INSTALL_CLEANUP. Hide these hints with HOMEBREW_NO_ENV_HINTS (see `man brew`). Removing: /Users/admin/Library/Caches/Homebrew/ollama_bottle_manifest--0.1.43... (7.6KB) Removing: /Users/admin/Library/Caches/Homebrew/ollama--0.1.43... (8.7MB) ➜ 0x2ca brew reinstall ollama Warning: Treating ollama as a formula. For the cask, use homebrew/cask/ollama or specify the `--cask` flag. ==> Downloading https://ghcr.io/v2/homebrew/core/ollama/manifests/0.1.44 Already downloaded: /Users/admin/Library/Caches/Homebrew/downloads/83b152ad7c5a778f288d7f789241a76f790ed1f6ec9ed3bedeb0a8ac99f32ff6--ollama-0.1.44.bottle_manifest.json ==> Fetching ollama ==> Downloading https://ghcr.io/v2/homebrew/core/ollama/blobs/sha256:59b3c5ad Already downloaded: /Users/admin/Library/Caches/Homebrew/downloads/da923370403cf7cf18885ec7d844b00becda22650ff2e2aadfde85da96680eb6--ollama--0.1.44.arm64_sonoma.bottle.tar.gz ==> Reinstalling ollama ==> Pouring ollama--0.1.44.arm64_sonoma.bottle.tar.gz ==> Caveats To start ollama now and restart at login: brew services start ollama Or, if you don't want/need a background service you can just run: /opt/homebrew/opt/ollama/bin/ollama serve ==> Summary 🍺 /opt/homebrew/Cellar/ollama/0.1.44: 8 files, 22.8MB ==> Running `brew cleanup ollama`... Disable this behaviour by setting HOMEBREW_NO_INSTALL_CLEANUP. Hide these hints with HOMEBREW_NO_ENV_HINTS (see `man brew`). ➜ 0x2ca brew services restart ollama Could not enable service: 125: Domain does not support specified action Error: Failure while executing; `/bin/launchctl enable gui/501/homebrew.mxcl.ollama` exited with 125. ```
GiteaMirror commented 2026-04-28 12:29:33 -05:00
Author
Owner
Copy Link

@0x2CA commented on GitHub (Jun 18, 2024):

Oh sorry, I installed it wrong, I reinstalled it and it's working!
brew install ollama --cask

<!-- gh-comment-id:2174701991 --> @0x2CA commented on GitHub (Jun 18, 2024): Oh sorry, I installed it wrong, I reinstalled it and it's working! `brew install ollama --cask`
GiteaMirror commented 2026-04-28 12:29:38 -05:00
Author
Owner
Copy Link

@QiuZiXian commented on GitHub (Jun 18, 2024):

升级ollama

<!-- gh-comment-id:2175507315 --> @QiuZiXian commented on GitHub (Jun 18, 2024): 升级ollama
GiteaMirror commented 2026-04-28 12:29:42 -05:00
Author
Owner
Copy Link

@dhiltgen commented on GitHub (Jun 18, 2024):

Support for this model was fixed in a newer version (confirmed on 0.1.44). Please upgrade and it should work.

<!-- gh-comment-id:2176917893 --> @dhiltgen commented on GitHub (Jun 18, 2024): Support for this model was fixed in a newer version (confirmed on 0.1.44). Please upgrade and it should work.
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#49650
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?