github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 08:30:05 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #165] Make it simple to add new models from Huggingface #65

New Issue
Closed
opened 2026-04-12 09:36:34 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-12 09:36:34 -05:00
Owner
Copy Link

Originally created by @joshlewis on GitHub (Jul 21, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/165

I love ollama! This is sweet.

I'm a beginner with LLM stuff. I see ollama has built-in support for several models like Nous-Hermes, Orca Mini, and a couple varieties of Llama2. I'd love it if it were just as easy (or at least almost as easy?) to add support for other models we find on huggingface.co with a simple command. Then once I had done that, I could run ollama pull whatevermodel and it would just do what it was supposed to do.

Originally created by @joshlewis on GitHub (Jul 21, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/165 I love ollama! This is sweet. I'm a beginner with LLM stuff. I see ollama has built-in support for several models like Nous-Hermes, Orca Mini, and a couple varieties of Llama2. I'd love it if it were just as easy (or at least almost as easy?) to add support for other models we find on huggingface.co with a simple command. Then once I had done that, I could run `ollama pull whatevermodel` and it would just do what it was supposed to do.
GiteaMirror commented 2026-04-12 09:36:35 -05:00
Author
Owner
Copy Link

@mchiang0610 commented on GitHub (Jul 21, 2023):

@joshlewis Thank you! There is a workaround right now in that you can create a modelfile for the custom GGML models.

In the modelfile, you can specify FROM ./custom_model_name.bin and then create a model from there.

<!-- gh-comment-id:1646209341 --> @mchiang0610 commented on GitHub (Jul 21, 2023): @joshlewis Thank you! There is a workaround right now in that you can create a modelfile for the custom GGML models. In the modelfile, you can specify `FROM ./custom_model_name.bin` and then create a model from there.
GiteaMirror commented 2026-04-12 09:36:35 -05:00
Author
Owner
Copy Link

@joshlewis commented on GitHub (Jul 21, 2023):

I don't agree this is completed. There's a workaround that sometimes works if you known enough to figure out how to set everything up, but it's not "simple". What I'm asking for is to make it simple.

<!-- gh-comment-id:1646328558 --> @joshlewis commented on GitHub (Jul 21, 2023): I don't agree this is completed. There's a workaround that sometimes works if you known enough to figure out how to set everything up, but it's not "simple". What I'm asking for is to make it simple.
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#65
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?