github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15270] [Bug] Gemma4 reduces words to two literals #71827

New Issue
Open
opened 2026-05-05 02:38:33 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-05 02:38:33 -05:00
Owner
Copy Link

Originally created by @ErfolgreichCharismatisch on GitHub (Apr 3, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15270

The new gemma4 is really exciting. It has a great context understanding. Question is also which context lengths to give it with Ollama. There's just one problem that I experienced in German and that is words are sometimes reduced to two literals. That might be the case in other languages as well. I only tried it in German. So even though otherwise understanding, grammar and all of that is really good, but sometimes it's just the first literal and the last literal of a word instead of the full word. And I don't think this is a model problem. I think this is an internal alignment problem. So in other words this is something that you can fix and it's not due to the model itself. Of course it could also be due to a badly converted model.
If you fix this, gemma4 would definitely be a state of the art offline model.

Originally created by @ErfolgreichCharismatisch on GitHub (Apr 3, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15270 The new gemma4 is really exciting. It has a great context understanding. Question is also which context lengths to give it with Ollama. There's just one problem that I experienced in German and that is words are sometimes reduced to two literals. That might be the case in other languages as well. I only tried it in German. So even though otherwise understanding, grammar and all of that is really good, but sometimes it's just the first literal and the last literal of a word instead of the full word. And I don't think this is a model problem. I think this is an internal alignment problem. So in other words this is something that you can fix and it's not due to the model itself. Of course it could also be due to a badly converted model. If you fix this, gemma4 would definitely be a state of the art offline model.
GiteaMirror commented 2026-05-05 02:38:35 -05:00
Author
Owner
Copy Link

@szmarczak commented on GitHub (Apr 3, 2026):

You're using an out of date ollama. Upgrade to newest version.

<!-- gh-comment-id:4183377431 --> @szmarczak commented on GitHub (Apr 3, 2026): You're using an out of date ollama. Upgrade to newest version.
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#71827
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?