github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-17 05:36:16 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #4276] bge-m3 #64707

New Issue
Open
opened 2026-05-03 18:35:01 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 18:35:01 -05:00
Owner
Copy Link

Originally created by @Mimicvat on GitHub (May 9, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/4276

https://huggingface.co/vonjack/bge-m3-gguf
from: https://github.com/ggerganov/llama.cpp/issues/6007
I am looking for recommendations on a high-quality multilingual embedder that includes support for Portuguese. Anything better than https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 would be nice.

Originally created by @Mimicvat on GitHub (May 9, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/4276 https://huggingface.co/vonjack/bge-m3-gguf from: https://github.com/ggerganov/llama.cpp/issues/6007 I am looking for recommendations on a high-quality multilingual embedder that includes support for Portuguese. Anything better than https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2 would be nice.
GiteaMirror added the model label 2026-05-03 18:35:01 -05:00
GiteaMirror commented 2026-05-03 18:35:03 -05:00
Author
Owner
Copy Link

@martinkozle commented on GitHub (May 10, 2024):

I've been using https://huggingface.co/intfloat/multilingual-e5-large and it is pretty good.
I think https://huggingface.co/intfloat/multilingual-e5-large-instruct is newer and a little bit better.

<!-- gh-comment-id:2104258310 --> @martinkozle commented on GitHub (May 10, 2024): I've been using <https://huggingface.co/intfloat/multilingual-e5-large> and it is pretty good. I think <https://huggingface.co/intfloat/multilingual-e5-large-instruct> is newer and a little bit better.
GiteaMirror commented 2026-05-03 18:35:04 -05:00
Author
Owner
Copy Link

@Mimicvat commented on GitHub (May 11, 2024):

I've been using https://huggingface.co/intfloat/multilingual-e5-large and it is pretty good. I think https://huggingface.co/intfloat/multilingual-e5-large-instruct is newer and a little bit better.

I wanted to use this embedding too! How are you using it on ollama?

<!-- gh-comment-id:2105654917 --> @Mimicvat commented on GitHub (May 11, 2024): > I've been using https://huggingface.co/intfloat/multilingual-e5-large and it is pretty good. I think https://huggingface.co/intfloat/multilingual-e5-large-instruct is newer and a little bit better. I wanted to use this embedding too! How are you using it on ollama?
GiteaMirror commented 2026-05-03 18:35:04 -05:00
Author
Owner
Copy Link

@martinkozle commented on GitHub (May 12, 2024):

I am using Text Embeddings Inference from HuggingFace. But it has it's differences. Like having separate images for different hardware acceleration, or that the model can't be changed dynamically at runtime like with Ollama. I haven't tried using custom embedding models in Ollama yet, but I am interested when I have the time to give it a go. I don't know how the performance compares, I would believe that Text Embeddings Inference is faster?
I am interested to know what you manage to do.

<!-- gh-comment-id:2106369775 --> @martinkozle commented on GitHub (May 12, 2024): I am using [Text Embeddings Inference from HuggingFace](https://github.com/huggingface/text-embeddings-inference). But it has it's differences. Like having separate images for different hardware acceleration, or that the model can't be changed dynamically at runtime like with Ollama. I haven't tried using custom embedding models in Ollama yet, but I am interested when I have the time to give it a go. I don't know how the performance compares, I would believe that Text Embeddings Inference is faster? I am interested to know what you manage to do.
GiteaMirror commented 2026-05-03 18:35:05 -05:00
Author
Owner
Copy Link

@Mimicvat commented on GitHub (May 13, 2024):

That's awesome! I wanted to create a simple RAG demo using AnythingLLM or another plug-and-play interface. However, I was looking for a good multilingual embedding to compare with the default one provided by AnythingLLM. I discovered that there are no state-of-the-art multilingual embeddings in ollama, even though it is integrated into every easy-to-use framework.

<!-- gh-comment-id:2107082922 --> @Mimicvat commented on GitHub (May 13, 2024): That's awesome! I wanted to create a simple RAG demo using AnythingLLM or another plug-and-play interface. However, I was looking for a good multilingual embedding to compare with the default one provided by AnythingLLM. I discovered that there are no state-of-the-art multilingual embeddings in ollama, even though it is integrated into every easy-to-use framework.
GiteaMirror commented 2026-05-03 18:35:06 -05:00
Author
Owner
Copy Link

@ciekawy commented on GitHub (May 21, 2024):

gguf gives major speedup on apple silicon, no support for XLMRobertaModel unfortunately yet so not possible to have e5 in gguf currently

<!-- gh-comment-id:2122725714 --> @ciekawy commented on GitHub (May 21, 2024): gguf gives major speedup on apple silicon, no support for XLMRobertaModel unfortunately yet so not possible to have e5 in gguf currently
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 model
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#64707
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?