github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6908] How to use embedding models from huggingface hub? #4370

New Issue
Open
opened 2026-04-12 15:18:33 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-04-12 15:18:33 -05:00
Owner
Copy Link

Originally created by @fzyzcjy on GitHub (Sep 22, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6908

Hi thanks for the lib! I want to use some embedding models (arch is bert) from hf hub. I have tried gguf, but the converter says bert arch cannot be converted to that. I have also tried directly have a modelfile to import safetensors, but it says Error: unsupported content type: unknown

Originally created by @fzyzcjy on GitHub (Sep 22, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6908 Hi thanks for the lib! I want to use some embedding models (arch is bert) from hf hub. I have tried gguf, but the converter says bert arch cannot be converted to that. I have also tried directly have a modelfile to import safetensors, but it says `Error: unsupported content type: unknown`
GiteaMirror added the feature request label 2026-04-12 15:18:33 -05:00
GiteaMirror commented 2026-04-12 15:18:34 -05:00
Author
Owner
Copy Link

@neuwcodebox commented on GitHub (Oct 14, 2024):

We need a manual to import embedding models.

<!-- gh-comment-id:2409860974 --> @neuwcodebox commented on GitHub (Oct 14, 2024): We need a manual to import embedding models.
GiteaMirror commented 2026-04-12 15:18:34 -05:00
Author
Owner
Copy Link

@E218PQ commented on GitHub (Oct 22, 2024):

I also have the same experience and the same needs. I hope there can be a better solution. I hope ollama can increase support for RAG models and TTS models.

<!-- gh-comment-id:2427985229 --> @E218PQ commented on GitHub (Oct 22, 2024): I also have the same experience and the same needs. I hope there can be a better solution. I hope ollama can increase support for RAG models and TTS models.
GiteaMirror commented 2026-04-12 15:18:34 -05:00
Author
Owner
Copy Link

@EntropyYue commented on GitHub (Oct 29, 2024):

In the llama.cpp convert it to gguf, and then import it like a regular model.

<!-- gh-comment-id:2445175976 --> @EntropyYue commented on GitHub (Oct 29, 2024): In the llama.cpp convert it to gguf, and then import it like a regular model.
GiteaMirror commented 2026-04-12 15:18:35 -05:00
Author
Owner
Copy Link

@E218PQ commented on GitHub (Oct 30, 2024):

In the llama.cpp convert it to gguf, and then import it like a regular model.

Thank you for your response,
Sorry, I tried many times but couldn't complete the conversion and kept showing unsupported types. For this reason, I also built a separate llama.cpp environment.In the end, I had no choice but to run an additional xinference environment, running RAG and TTS separately. In addition, some frameworks such as dify do not support adding TTS or RAG models to the preset ollama model function module. I hope that all of this can run in a single environment of ollama, which is both simple and stable, and very easy to maintain.

<!-- gh-comment-id:2445778827 --> @E218PQ commented on GitHub (Oct 30, 2024): > In the llama.cpp convert it to gguf, and then import it like a regular model. Thank you for your response, Sorry, I tried many times but couldn't complete the conversion and kept showing unsupported types. For this reason, I also built a separate llama.cpp environment.In the end, I had no choice but to run an additional xinference environment, running RAG and TTS separately. In addition, some frameworks such as dify do not support adding TTS or RAG models to the preset ollama model function module. I hope that all of this can run in a single environment of ollama, which is both simple and stable, and very easy to maintain.
GiteaMirror commented 2026-04-12 15:18:35 -05:00
Author
Owner
Copy Link

@AlgorithmicKing737 commented on GitHub (Jan 18, 2025):

any solution yet?

<!-- gh-comment-id:2599573029 --> @AlgorithmicKing737 commented on GitHub (Jan 18, 2025): any solution yet?
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#4370
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?