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 #6890] "/show parameters" command causes crashes when running Qwen 2.5 models, on version 0.3.11 #4359

New Issue
Closed
opened 2026-04-12 15:17:55 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 15:17:55 -05:00
Owner
Copy Link

Originally created by @ghost on GitHub (Sep 20, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6890

What is the issue?

This only happens after changing the parameters through /set parameter command.
Here's an example:
PS H:\ztmp> ollama run qwen2.5

/show parameters
No parameters were specified for this model.
/set parameter top_k 1
Set parameter 'top_k' to '1'
/show parameters
error: couldn't get model
Error: something went wrong, please see the ollama server logs for details
PS H:\ztmp>

This is on windows 11.

Here's the error message from the ollama serve terminal tab:
2024/09/20 08:47:43 [Recovery] 2024/09/20 - 08:47:43 panic recovered:
assignment to entry in nil map
runtime/map_faststr.go:205 (0x7a93ba)
github.com/ollama/ollama/server/routes.go:807 (0x12cc57e)
github.com/ollama/ollama/server/routes.go:732 (0x12cb497)
github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1287cca)
github.com/ollama/ollama/server/routes.go:1076 (0x12d0c14)
github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1295d39)
github.com/gin-gonic/gin@v1.10.0/recovery.go:102 (0x1295d27)
github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1294e64)
github.com/gin-gonic/gin@v1.10.0/logger.go:249 (0x1294e4b)
github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1294291)
github.com/gin-gonic/gin@v1.10.0/gin.go:633 (0x1293d00)
github.com/gin-gonic/gin@v1.10.0/gin.go:589 (0x1293831)
net/http/server.go:2688 (0xafaecc)
net/http/server.go:3142 (0xafc6cd)
net/http/server.go:2044 (0xaf79c7)
runtime/asm_amd64.s:1695 (0x8026a0)

OS

Windows

GPU

Nvidia

CPU

AMD

Ollama version

0.3.11

Originally created by @ghost on GitHub (Sep 20, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6890 ### What is the issue? This only happens after changing the parameters through /set parameter command. Here's an example: PS H:\ztmp> ollama run qwen2.5 >>> /show parameters No parameters were specified for this model. >>> /set parameter top_k 1 Set parameter 'top_k' to '1' >>> /show parameters error: couldn't get model Error: something went wrong, please see the ollama server logs for details PS H:\ztmp> This is on windows 11. Here's the error message from the ollama serve terminal tab: 2024/09/20 08:47:43 [Recovery] 2024/09/20 - 08:47:43 panic recovered: assignment to entry in nil map runtime/map_faststr.go:205 (0x7a93ba) github.com/ollama/ollama/server/routes.go:807 (0x12cc57e) github.com/ollama/ollama/server/routes.go:732 (0x12cb497) github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1287cca) github.com/ollama/ollama/server/routes.go:1076 (0x12d0c14) github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1295d39) github.com/gin-gonic/gin@v1.10.0/recovery.go:102 (0x1295d27) github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1294e64) github.com/gin-gonic/gin@v1.10.0/logger.go:249 (0x1294e4b) github.com/gin-gonic/gin@v1.10.0/context.go:185 (0x1294291) github.com/gin-gonic/gin@v1.10.0/gin.go:633 (0x1293d00) github.com/gin-gonic/gin@v1.10.0/gin.go:589 (0x1293831) net/http/server.go:2688 (0xafaecc) net/http/server.go:3142 (0xafc6cd) net/http/server.go:2044 (0xaf79c7) runtime/asm_amd64.s:1695 (0x8026a0) ### OS Windows ### GPU Nvidia ### CPU AMD ### Ollama version 0.3.11
GiteaMirror added the bug label 2026-04-12 15:17:55 -05:00
GiteaMirror commented 2026-04-12 15:17:57 -05:00
Author
Owner
Copy Link

@jonbuffington commented on GitHub (Dec 13, 2024):

I do not think this is model specific. For example, I can recreate using llama3.2:1b. My steps are:

% ollama --version      
ollama version is 0.5.1
% ollama run llama3.2:1b
>>> /set parameter temperature 0.5
Set parameter 'temperature' to '0.5'
>>> /show parameters
error: couldn't get model
Error: something went wrong, please see the ollama server logs for details
%
<!-- gh-comment-id:2541881748 --> @jonbuffington commented on GitHub (Dec 13, 2024): I do not think this is model specific. For example, I can recreate using `llama3.2:1b`. My steps are: ``` % ollama --version ollama version is 0.5.1 % ollama run llama3.2:1b >>> /set parameter temperature 0.5 Set parameter 'temperature' to '0.5' >>> /show parameters error: couldn't get model Error: something went wrong, please see the ollama server logs for details % ```
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#4359
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?