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 #2570] Potential Regression with Model switching #27270

New Issue
Closed
opened 2026-04-22 04:28:11 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-22 04:28:11 -05:00
Owner
Copy Link

Originally created by @libbaz on GitHub (Feb 18, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2570

Issue:
I just pulled the latest ollama docker image (Ollama v0.1.25) and have noticed api /chat requests are no longer switching the Model Template on templates based on the same Models. In the past this wasnt an issue.

Steps to reproduce:
create Foo-1 from model "Foo"
create Foo-2 from model "Foo"
create Bar-1 from model "Bar"

make a chat request with Foo-1 = response uses Foo-1
make a chat request with Foo-2 = response uses Foo-1
make a chat request with Bar-1 = (model is switched to Bar-1) response uses Bar-1
make a chat request with Foo-2 = (model is switched to Foo-2) response uses Foo-2

Expected:
make a chat request with Foo-1 = response uses Foo-1
make a chat request with Foo-2 = (model is switched to Foo-2) response uses Foo-2
make a chat request with Bar-1 = (model is switched to Bar-1) response uses Bar-1

Originally created by @libbaz on GitHub (Feb 18, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2570 **Issue:** I just pulled the latest ollama docker image (Ollama v0.1.25) and have noticed api `/chat` requests are no longer switching the Model Template on templates based on the same Models. In the past this wasnt an issue. **Steps to reproduce:** create Foo-1 from model "Foo" create Foo-2 from model "Foo" create Bar-1 from model "Bar" make a chat request with Foo-1 = response uses Foo-1 make a chat request with Foo-2 = response uses Foo-1 make a chat request with Bar-1 = (model is switched to Bar-1) response uses Bar-1 make a chat request with Foo-2 = (model is switched to Foo-2) response uses Foo-2 **Expected:** make a chat request with Foo-1 = response uses Foo-1 make a chat request with Foo-2 = (model is switched to Foo-2) response uses Foo-2 make a chat request with Bar-1 = (model is switched to Bar-1) response uses Bar-1
GiteaMirror commented 2026-04-22 04:28:15 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Feb 18, 2024):

Hi there, sorry about this issue. It was fixed recently on main and will be fixed in the next release. Here is the original issue: https://github.com/ollama/ollama/issues/2492

<!-- gh-comment-id:1950989164 --> @jmorganca commented on GitHub (Feb 18, 2024): Hi there, sorry about this issue. It was fixed recently on main and will be fixed in the next release. Here is the original issue: https://github.com/ollama/ollama/issues/2492
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#27270
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?