github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-06 16:11:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #8376] Ollama version doesn't properly truncate tokens to 512 max for official snowflake-arctic-embed-l model #67433

New Issue
Open
opened 2026-05-04 10:19:48 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-05-04 10:19:48 -05:00
Owner
Copy Link

Originally created by @shuaiscott on GitHub (Jan 10, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/8376

What is the issue?

When using the official Ollama model of snowflake-arctic-embed-l (latest/335m - 21ab8b9b0545), if input is greater than 512 tokens, instead of truncating, the model encounters an error.

On a previous version (0.3.9) when you pass it more than 512 tokens, it returns only [0,0,0...] embeddings.
In 0.5.4, Ollama returns a 500 error and the logs show that "Process xxxxxx (ollama_llama_se) of user xxx dumped core"

Logs:

llama_model_load: vocab only - skipping tensors
ggml-cpu.c:8400: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed
ggml-cpu.c:8400: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed
SIGSEGV: segmentation violation
PC=0x7fcc733ecc57 m=5 sigcode=1 addr=0x207203fe0
signal arrived during ago violation
goroutine 8 gp=0xc0000f21c0 m=5 mp=0xc000100008 [syscall]:
runtime.cgocall(0x562b649d47d0, 0xc000073b90)
        runtime/cgocall.go:167
github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7fcbf115bfa0, {0x2, 0x7fcbf0b80590, 0x0, 0x0, 0x7fcbf0b80da0, 0x7fcbf0b815b, 0x7fcbf0b81dc0, 0x7fcbf1144dc0})
...

I've checked my Ollama parameters and this occurs when "truncate": true. Other embedding models properly truncates the input and I see the INFO log in Ollama say "input truncated". I don't see this message with snowflake-arctic-embed-l.

When "truncate" is set to false, I get the expected "input length exceeds maximum context length".

https://ollama.com/library/snowflake-arctic-embed

OS

Linux

GPU

Nvidia

CPU

Intel

Ollama version

0.5.4

Originally created by @shuaiscott on GitHub (Jan 10, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/8376 ### What is the issue? When using the official Ollama model of snowflake-arctic-embed-l (latest/335m - 21ab8b9b0545), if input is greater than 512 tokens, instead of truncating, the model encounters an error. On a previous version (0.3.9) when you pass it more than 512 tokens, it returns only [0,0,0...] embeddings. In 0.5.4, Ollama returns a 500 error and the logs show that "Process xxxxxx (ollama_llama_se) of user xxx dumped core" Logs: ``` llama_model_load: vocab only - skipping tensors ggml-cpu.c:8400: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed ggml-cpu.c:8400: GGML_ASSERT(i01 >= 0 && i01 < ne01) failed SIGSEGV: segmentation violation PC=0x7fcc733ecc57 m=5 sigcode=1 addr=0x207203fe0 signal arrived during ago violation goroutine 8 gp=0xc0000f21c0 m=5 mp=0xc000100008 [syscall]: runtime.cgocall(0x562b649d47d0, 0xc000073b90) runtime/cgocall.go:167 github.com/ollama/ollama/llama._Cfunc_llama_decode(0x7fcbf115bfa0, {0x2, 0x7fcbf0b80590, 0x0, 0x0, 0x7fcbf0b80da0, 0x7fcbf0b815b, 0x7fcbf0b81dc0, 0x7fcbf1144dc0}) ... ``` I've checked my Ollama parameters and this occurs when "truncate": true. Other embedding models properly truncates the input and I see the INFO log in Ollama say "input truncated". I don't see this message with snowflake-arctic-embed-l. When "truncate" is set to false, I get the expected "input length exceeds maximum context length". https://ollama.com/library/snowflake-arctic-embed ### OS Linux ### GPU Nvidia ### CPU Intel ### Ollama version 0.5.4
GiteaMirror added the bug label 2026-05-04 10:19:48 -05:00
GiteaMirror commented 2026-05-04 10:19:50 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Jan 10, 2025):

https://github.com/ollama/ollama/issues/7288

The problem can be worked around by setting num_ctx for the model to the actual context length of the model, rather than the default value of 2048 that ollama uses. You can either do that by setting num_ctx in the API call ("options":{"num_ctx":512}) or by creating a copy of the model with the parameter:

$ ollama show --modelfile  snowflake-arctic-embed:l > Modelfile
$ echo PARAMETER num_ctx 512 >> Modelfile
$ ollama create snowflake-arctic-embed:l-c512

and then adjust the client to use snowflake-arctic-embed:l-c512 instead of snowflake-arctic-embed:l.

<!-- gh-comment-id:2583021192 --> @rick-github commented on GitHub (Jan 10, 2025): https://github.com/ollama/ollama/issues/7288 The problem can be worked around by setting `num_ctx` for the model to the actual context length of the model, rather than the default value of 2048 that ollama uses. You can either do that by setting `num_ctx` in the API call (`"options":{"num_ctx":512}`) or by creating a copy of the model with the parameter: ```console $ ollama show --modelfile snowflake-arctic-embed:l > Modelfile $ echo PARAMETER num_ctx 512 >> Modelfile $ ollama create snowflake-arctic-embed:l-c512 ``` and then adjust the client to use `snowflake-arctic-embed:l-c512` instead of `snowflake-arctic-embed:l`.
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#67433
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?