Model reference · open weights
bge-m3-dim-384 is an open-weight embedding model from RishabJ. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | RishabJ |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 568M |
| Context | 8194 tokens |
| Runs with | sentence-transformers |
| Released | 2024-07-18 |
| Popularity | 549 downloads / month |
| Licence | Open weights |
About
For more details please refer to our github repo: https://github.com/FlagOpen/FlagEmbedding
In this project, we introduce BGE-M3, which is distinguished for its versatility in Multi-Functionality, Multi-Linguality, and Multi-Granularity.
Some suggestions for retrieval pipeline in RAG
We recommend to use the following pipeline: hybrid retrieval + re-ranking.
Hybrid retrieval leverages the strengths of various methods, offering higher accuracy and stronger generalization capabilities. A classic example: using both embedding retrieval and the BM25 algorithm. Now, you can try to use BGE-M3, which supports both embedding and sparse retrieval. This allows you to obtain token weights (similar to the BM25) without any additional cost when generate dense embeddings. To use hybrid retrieval, you can refer to Vespa and Milvus.
As cross-encoder models, re-ranker demonstrates higher accuracy than bi-encoder embedding model. Utilizing the re-ranking model (e.g., bge-reranker, bge-reranker-v2) after retrieval can further filter the selected text.
| Model Name | Dimension | Sequence Length | Introduction |
|---|---|---|---|
| BAAI/bge-m3 | 1024 | 8192 | multilingual; unified fine-tuning (dense, sparse, and colbert) from bge-m3-unsupervised |
| BAAI/bge-m3-unsupervised | 1024 | 8192 | multilingual; contrastive learning from bge-m3-retromae |
| BAAI/bge-m3-retromae | -- | 8192 | multilingual; extend the max_length of xlm-roberta to 8192 and further pretrained via retromae |
| BAAI/bge-large-en-v1.5 | 1024 | 512 | English model |
| BAAI/bge-base-en-v1.5 | 768 | 512 | English model |
| BAAI/bge-small-en-v1.5 | 384 | 512 | English model |
| Dataset | Introduction |
|---|---|
| MLDR | Docuemtn Retrieval Dataset, covering 13 languages |
| bge-m3-data | Fine-tuning data used by bge-m3 |
1. Introduction for different retrieval methods
2. How to use BGE-M3 in other projects?
For embedding retrieval, you can employ the BGE-M3 model using the same approach as BGE. The only difference is that the BGE-M3 model no longer requires adding instructions to the queries.
For hybrid retrieval, you can use Vespa and Milvus.
3. How to fine-tune bge-M3 model?
You can follow the common in this example to fine
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys bge-m3-dim-384 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (bge-m3-dim-384 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/embeddings \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"bge-m3-dim-384","input":"text to embed"}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.