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 #13643] Model input character limit #34732

New Issue
Open
opened 2026-04-22 18:33:30 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-04-22 18:33:30 -05:00
Owner
Copy Link

Originally created by @vZzzv on GitHub (Jan 8, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/13643

What is the issue?

When using the embedding bge-m3:latest model, it was discovered that the latest versions of ollama have an input text limit of approximately 100-120 words.
In older versions, there was no such limit.

{
"error": "failed to encode response: json: unsupported value: NaN"
}

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @vZzzv on GitHub (Jan 8, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/13643 ### What is the issue? When using the embedding bge-m3:latest model, it was discovered that the latest versions of ollama have an input text limit of approximately 100-120 words. In older versions, there was no such limit. { "error": "failed to encode response: json: unsupported value: NaN" } ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-04-22 18:33:30 -05:00
GiteaMirror commented 2026-04-22 18:33:31 -05:00
Author
Owner
Copy Link

@noobyogi0010 commented on GitHub (Jan 12, 2026):

Hello @vZzzv
What do you expect here? Shall we remove the input limit?
Thanks

<!-- gh-comment-id:3737276752 --> @noobyogi0010 commented on GitHub (Jan 12, 2026): Hello @vZzzv What do you expect here? Shall we remove the input limit? Thanks
GiteaMirror commented 2026-04-22 18:33:32 -05:00
Author
Owner
Copy Link

@vZzzv commented on GitHub (Jan 12, 2026):

您发给我的信件已经收到。

<!-- gh-comment-id:3737278706 --> @vZzzv commented on GitHub (Jan 12, 2026): 您发给我的信件已经收到。
GiteaMirror commented 2026-04-22 18:33:33 -05:00
Author
Owner
Copy Link

@nicho2 commented on GitHub (Feb 3, 2026):

I see this bug too that didn't exist before with bge-m3:latest

time=2026-02-03T12:09:29.990Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c

time=2026-02-03T12:09:30.016Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32

time=2026-02-03T12:09:30.018Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=26 prompt=27 used=0 remaining=27

decode: cannot decode batches with this context (calling encode() instead)

init: embeddings required but some input tokens were not marked as outputs -> overriding

time=2026-02-03T12:09:30.024Z level=INFO source=server.go:1748 msg="llm embedding error: failed to encode response: json: unsupported value: NaN"

[GIN] 2026/02/03 - 12:09:30 | 500 |  121.408856ms |     10.2.142.71 | POST     "/api/embed"
<!-- gh-comment-id:3840947543 --> @nicho2 commented on GitHub (Feb 3, 2026): I see this bug too that didn't exist before with bge-m3:latest time=2026-02-03T12:09:29.990Z level=DEBUG source=sched.go:678 msg="evaluating already loaded" model=/root/.ollama/models/blobs/sha256-daec91ffb5dd0c27411bd71f29932917c49cf529a641d0168496c3a501e3062c time=2026-02-03T12:09:30.016Z level=DEBUG source=ggml.go:298 msg="key with type not found" key=general.alignment default=32 time=2026-02-03T12:09:30.018Z level=DEBUG source=cache.go:104 msg="loading cache slot" id=0 cache=26 prompt=27 used=0 remaining=27 decode: cannot decode batches with this context (calling encode() instead) init: embeddings required but some input tokens were not marked as outputs -> overriding time=2026-02-03T12:09:30.024Z level=INFO source=server.go:1748 msg="llm embedding error: failed to encode response: json: unsupported value: NaN" [GIN] 2026/02/03 - 12:09:30 | 500 | 121.408856ms | 10.2.142.71 | POST "/api/embed"
GiteaMirror commented 2026-04-22 18:33:33 -05:00
Author
Owner
Copy Link

@vZzzv commented on GitHub (Feb 3, 2026):

您发给我的信件已经收到。

<!-- gh-comment-id:3840949652 --> @vZzzv commented on GitHub (Feb 3, 2026): 您发给我的信件已经收到。
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#34732
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?