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 #2471] Adding Bert-Embeddings server / how to add torch #47956

New Issue
Closed
opened 2026-04-28 06:10:35 -05:00 by GiteaMirror · 3 comments
GiteaMirror commented 2026-04-28 06:10:35 -05:00
Owner
Copy Link

Originally created by @michaelfeil on GitHub (Feb 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2471

I am building https://github.com/michaelfeil/infinity and would love to contribute to ollama. It is compatible with cuda, cpu and mps, with the option to run onnx models. Beta also for torch + ROCm.

torch or onnx are required, I would recommend going with torch for speed (flash attn integration).

import asyncio
from infinity_emb import AsyncEmbeddingEngine

engine = AsyncEmbeddingEngine(model_name_or_path = "BAAI/bge-small-en-v1.5", engine="torch")

async def main(sentences = ["Embed this is sentence via Infinity.", "Paris is in France."]): 
    # invoke this function however you can from go
    async with engine: # engine starts with engine.astart()
        embeddings, usage = await engine.embed(sentences=sentences)
asyncio.run(main())

PS: Had a chat at the SF meetup earlier today thanks for hosting, a lot of interesting people here. Great work @mchiang0610

Originally created by @michaelfeil on GitHub (Feb 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2471 I am building https://github.com/michaelfeil/infinity and would love to contribute to ollama. It is compatible with cuda, cpu and mps, with the option to run onnx models. Beta also for torch + ROCm. torch or onnx are required, I would recommend going with torch for speed (flash attn integration). ```python import asyncio from infinity_emb import AsyncEmbeddingEngine engine = AsyncEmbeddingEngine(model_name_or_path = "BAAI/bge-small-en-v1.5", engine="torch") async def main(sentences = ["Embed this is sentence via Infinity.", "Paris is in France."]): # invoke this function however you can from go async with engine: # engine starts with engine.astart() embeddings, usage = await engine.embed(sentences=sentences) asyncio.run(main()) ``` PS: Had a chat at the SF meetup earlier today thanks for hosting, a lot of interesting people here. Great work @mchiang0610
GiteaMirror added the feature request label 2026-04-28 06:10:36 -05:00
GiteaMirror commented 2026-04-28 06:11:02 -05:00
Author
Owner
Copy Link

@jmorganca commented on GitHub (Mar 13, 2024):

@michaelfeil so great to see you there! Bert models should new be possible to run with Ollama (e.g. see https://ollama.com/library/all-minilm or https://ollama.com/library/nomic-embed-text). Let me know if this helps!

<!-- gh-comment-id:1993513689 --> @jmorganca commented on GitHub (Mar 13, 2024): @michaelfeil so great to see you there! Bert models should new be possible to run with Ollama (e.g. see https://ollama.com/library/all-minilm or https://ollama.com/library/nomic-embed-text). Let me know if this helps!
GiteaMirror commented 2026-04-28 06:11:04 -05:00
Author
Owner
Copy Link

@michaelfeil commented on GitHub (Mar 13, 2024):

Great - thanks for closing the issue!

<!-- gh-comment-id:1993563106 --> @michaelfeil commented on GitHub (Mar 13, 2024): Great - thanks for closing the issue!
GiteaMirror commented 2026-04-28 06:11:05 -05:00
Author
Owner
Copy Link

@spike-xiong commented on GitHub (Feb 19, 2025):

@michaelfeil so great to see you there! Bert models should new be possible to run with Ollama (e.g. see https://ollama.com/library/all-minilm or https://ollama.com/library/nomic-embed-text). Let me know if this helps!

Hello @jmorganca ! Is there any guide for importing a fine-tuned Bert structure model into Ollama?

<!-- gh-comment-id:2667582030 --> @spike-xiong commented on GitHub (Feb 19, 2025): > [@michaelfeil](https://github.com/michaelfeil) so great to see you there! Bert models should new be possible to run with Ollama (e.g. see https://ollama.com/library/all-minilm or https://ollama.com/library/nomic-embed-text). Let me know if this helps! Hello @jmorganca ! Is there any guide for importing a fine-tuned Bert structure model into Ollama?
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#47956
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?