Model reference · open weights
bge-small-en is an open-weight embedding model from vectoriseai. 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 | vectoriseai |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Context | 512 tokens |
| Runs with | sentence-transformers |
| Released | 2023-10-09 |
| Popularity | 2k downloads / month |
| Licence | Open weights |
About
More details please refer to our Github: FlagEmbedding.
FlagEmbedding can map any text to a low-dimensional dense vector which can be used for tasks like retrieval, classification, clustering, or semantic search. And it also can be used in vector databases for LLMs.
************* 🌟Updates🌟 *************
BAAI/bge-reranker-base and BAAI/bge-reranker-large, which are more powerful than embedding model. We recommend to use/fine-tune them to re-rank top-k documents returned by embedding models.bge-*-v1.5 embedding model to alleviate the issue of the similarity distribution, and enhance its retrieval ability without instruction.bge-large-*(short for BAAI General Embedding) Models, rank 1st on MTEB and C-MTEB benchmark! :tada: :tada:bge is short for BAAI general embedding.
| Model | Language | Description | query instruction for retrieval* | |
|---|---|---|---|---|
| BAAI/bge-reranker-large | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient ** | |
| BAAI/bge-reranker-base | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient ** | |
| BAAI/bge-large-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | Represent this sentence for searching relevant passages: |
| BAAI/bge-base-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | Represent this sentence for searching relevant passages: |
| BAAI/bge-small-en-v1.5 | English | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | Represent this sentence for searching relevant passages: |
| BAAI/bge-large-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-base-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-small-zh-v1.5 | Chinese | Inference Fine-tune | version 1.5 with more reasonable similarity distribution | 为这个句子生成表示以用于检索相关文章： |
| BAAI/bge-large-en | English | Inference Fine-tune | :trophy: rank 1st in MTEB leaderboard | Represent this sentence for searching relevant passages: |
| BAAI/bge-base-en | English | Inference Fine-tune | a base-scale model but with similar ability to bge-large-en | Represent this sentence for searching relevant passages: |
| BAAI/bge-small-en | English | Inference Fine-tune | a small-scale model but with competitive performance | Represent this sentence for searching relevant passages: |
| BAAI/bge-large-zh | Chinese | Inference Fine-tune | :trophy: rank 1st in C-MTEB benchmark | 为这个句子生成表示以用于检索相关文章： |
| [BAAI/b |
From the published model card. Full card on the HuggingFace links in the sidebar.
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Classification | MTEB AmazonCounterfactualClassification (en) | accuracy | 73.791 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 37.219 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 68.091 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 92.754 |
| Classification | MTEB AmazonPolarityClassification | ap | 89.468 |
| Classification | MTEB AmazonPolarityClassification | f1 | 92.739 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 46.986 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 46.559 |
| Retrieval | MTEB ArguAna | map_at_1 | 35.846 |
| Retrieval | MTEB ArguAna | map_at_10 | 51.388 |
| Retrieval | MTEB ArguAna | map_at_100 | 52.133 |
| Retrieval | MTEB ArguAna | map_at_1000 | 52.141 |
| Retrieval | MTEB ArguAna | map_at_3 | 47.037 |
| Retrieval | MTEB ArguAna | map_at_5 | 49.579 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 36.558 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 51.658 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 52.402 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 52.410 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 47.345 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 49.798 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 35.846 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 59.550 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 62.596 |
| Retrieval | MTEB ArguAna | ndcg_at_1000 | 62.759 |
Using it via the API
Once AxForge deploys vectoriseai-bge-small-en for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (vectoriseai-bge-small-en 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":"vectoriseai-bge-small-en","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.