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 #1328] pull models by ID for reproducible research #47202

New Issue
Open
opened 2026-04-28 03:25:43 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 03:25:43 -05:00
Owner
Copy Link

Originally created by @leonmoonen on GitHub (Nov 30, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/1328

I love how ollama makes it easy to set up scientific experiments with various LLMs. However, one thing that is increasingly important in academia is the ability to reproduce and replicate research. For that, it would be extremely useful to pull a given model by its ID, even if a newer one has been published.

For example: last month I ran an experiment with then zephyr:latest (ID: 1629f2a8a495), but now my colleague can not reproduce my results because zephyr has been updated and zephyr:latest points to a model with ID 03af36d860cc. As far as I know, there is no tag associated with the older model and it can therefore not be pulled. Treating IDs as additional tags could solve this and make ollama a valuable component in a reproducible scientific workflow.

Originally created by @leonmoonen on GitHub (Nov 30, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/1328 I love how ollama makes it easy to set up scientific experiments with various LLMs. However, one thing that is increasingly important in academia is the ability to reproduce and replicate research. For that, it would be extremely useful to pull a given model by its ID, even if a newer one has been published. For example: last month I ran an experiment with then zephyr:latest (ID: 1629f2a8a495), but now my colleague can not reproduce my results because zephyr has been updated and zephyr:latest points to a model with ID 03af36d860cc. As far as I know, there is no tag associated with the older model and it can therefore not be pulled. Treating IDs as additional tags could solve this and make ollama a valuable component in a reproducible scientific workflow.
GiteaMirror added the feature request label 2026-04-28 03:25:43 -05:00
GiteaMirror commented 2026-04-28 03:25:44 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Nov 30, 2023):

When you use a LLM for an experiment, you can do it with docker and keep both the current Ollama version and the LLM version to reproduce the experiment. Be careful that some new versions of Ollama require new versions of LLM. This makes older LLM incompatible with new Ollama (seen with Falcon LLM).

<!-- gh-comment-id:1834685026 --> @igorschlum commented on GitHub (Nov 30, 2023): When you use a LLM for an experiment, you can do it with docker and keep both the current Ollama version and the LLM version to reproduce the experiment. Be careful that some new versions of Ollama require new versions of LLM. This makes older LLM incompatible with new Ollama (seen with Falcon LLM).
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 feature request
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#47202
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?