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 #15229] gemma4:31b drops all Unicode diacritics (accented characters) in output #56251

New Issue
Closed
opened 2026-04-29 10:29:01 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-29 10:29:01 -05:00
Owner
Copy Link

Originally created by @hydropix on GitHub (Apr 2, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15229

Originally assigned to: @dhiltgen on GitHub.

What is the issue?

gemma4:31b strips all multi-byte UTF-8 characters (accents, diacritics) from both the content and thinking fields. The output is intelligible but every accented character is silently removed.

Example: asking for a short French sentence with accents produces:

"L' a mang g  for."

instead of something like "L'élève a mangé gâteau en forêt." — every é, è, ê, ù, ç, à is dropped.

This does not happen with gemma3:27b on the same Ollama instance, which correctly outputs accented characters.

Steps to reproduce

# Non-streaming — accents missing
curl -s http://localhost:11434/api/chat -d '{
  "model": "gemma4:31b",
  "messages": [{"role":"user","content":"Écris une phrase courte en français avec des accents (é, è, ê, ù, ç, à)."}],
  "stream": false
}'
# Response: {"message":{"content":"L' a mang g  for.", ...}}

# Same prompt with gemma3:27b — accents present
curl -s http://localhost:11434/api/chat -d '{
  "model": "gemma3:27b",
  "messages": [{"role":"user","content":"Écris une phrase courte en français avec des accents (é, è, ê, ù, ç, à)."}],
  "stream": false
}'
# Response: {"message":{"content":"L'élu a dû gérer l'événement malgré..."}}

The thinking field is also affected — diacritics are missing there too.

Disabling thinking with "think": false does not fix the issue.

Environment

  • Ollama version: 0.20.0-rc0
  • OS: Windows (remote server)
  • Model: gemma4:31b (also tested gemma4:latest)
  • Comparison: gemma3:27b works correctly on the same instance

Expected behavior

Accented characters (é, è, ê, ù, ç, à, etc.) should be preserved in the output, as they are with gemma3.

Additional context

Likely related to the tokenizer/detokenizer for the new Gemma4 architecture introduced in PR #15214. The issue affects all output fields (content and thinking), suggesting it happens at the token decoding stage.

Originally created by @hydropix on GitHub (Apr 2, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15229 Originally assigned to: @dhiltgen on GitHub. ### What is the issue? `gemma4:31b` strips all multi-byte UTF-8 characters (accents, diacritics) from both the `content` and `thinking` fields. The output is intelligible but every accented character is silently removed. **Example:** asking for a short French sentence with accents produces: ``` "L' a mang g for." ``` instead of something like `"L'élève a mangé gâteau en forêt."` — every `é`, `è`, `ê`, `ù`, `ç`, `à` is dropped. This does **not** happen with `gemma3:27b` on the same Ollama instance, which correctly outputs accented characters. ### Steps to reproduce ```bash # Non-streaming — accents missing curl -s http://localhost:11434/api/chat -d '{ "model": "gemma4:31b", "messages": [{"role":"user","content":"Écris une phrase courte en français avec des accents (é, è, ê, ù, ç, à)."}], "stream": false }' # Response: {"message":{"content":"L' a mang g for.", ...}} # Same prompt with gemma3:27b — accents present curl -s http://localhost:11434/api/chat -d '{ "model": "gemma3:27b", "messages": [{"role":"user","content":"Écris une phrase courte en français avec des accents (é, è, ê, ù, ç, à)."}], "stream": false }' # Response: {"message":{"content":"L'élu a dû gérer l'événement malgré..."}} ``` The `thinking` field is also affected — diacritics are missing there too. Disabling thinking with `"think": false` does **not** fix the issue. ### Environment - **Ollama version:** 0.20.0-rc0 - **OS:** Windows (remote server) - **Model:** `gemma4:31b` (also tested `gemma4:latest`) - **Comparison:** `gemma3:27b` works correctly on the same instance ### Expected behavior Accented characters (é, è, ê, ù, ç, à, etc.) should be preserved in the output, as they are with gemma3. ### Additional context Likely related to the tokenizer/detokenizer for the new Gemma4 architecture introduced in PR #15214. The issue affects all output fields (`content` and `thinking`), suggesting it happens at the token decoding stage.
GiteaMirror commented 2026-04-29 10:29:03 -05:00
Author
Owner
Copy Link

@szmarczak commented on GitHub (Apr 2, 2026):

Not all characters are dropped: https://github.com/ollama/ollama/issues/15231

<!-- gh-comment-id:4179727697 --> @szmarczak commented on GitHub (Apr 2, 2026): Not all characters are dropped: https://github.com/ollama/ollama/issues/15231
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
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#56251
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?