Model reference · open weights
bge-en-angle is an open-weight embedding model from khoa-klaytn. 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 | khoa-klaytn |
|---|---|
| Type | Embedding models |
| Task | Embeddings |
| Parameters (lead) | 109M |
| Context | 512 tokens |
| Runs with | sentence-transformers |
| Released | 2024-01-10 |
| Popularity | 1k 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🌟 *************
10/12/2023: Release LLM-Embedder, a unified embedding model to support diverse retrieval augmentation needs for LLMs. Paper :fire:
09/15/2023: The technical report of BGE has been released
09/15/2023: The masive training data of BGE has been released
09/12/2023: New models:
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.09/07/2023: Update fine-tune code: Add script to mine hard negatives and support adding instruction during fine-tuning.
08/09/2023: BGE Models are integrated into Langchain, you can use it like this; C-MTEB leaderboard is available.
08/05/2023: Release base-scale and small-scale models, best performance among the models of the same size 🤗
08/02/2023: Release bge-large-*(short for BAAI General Embedding) Models, rank 1st on MTEB and C-MTEB benchmark! :tada: :tada:
08/01/2023: We release the Chinese Massive Text Embedding Benchmark (C-MTEB), consisting of 31 test dataset.
bge is short for BAAI general embedding.
| Model | Language | Description | query instruction for retrieval [1] | |
|---|---|---|---|---|
| BAAI/llm-embedder | English | Inference Fine-tune | a unified embedding model to support diverse retrieval augmentation needs for LLMs | See README |
| BAAI/bge-reranker-large | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient [2] | |
| BAAI/bge-reranker-base | Chinese and English | Inference Fine-tune | a cross-encoder model which is more accurate but less efficient [2] | |
| 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](https://huggingface.co |
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 | 76.149 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 39.323 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 70.169 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 93.387 |
| Classification | MTEB AmazonPolarityClassification | ap | 90.213 |
| Classification | MTEB AmazonPolarityClassification | f1 | 93.377 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 48.846 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 48.146 |
| Retrieval | MTEB ArguAna | map_at_1 | 40.754 |
| Retrieval | MTEB ArguAna | map_at_10 | 55.761 |
| Retrieval | MTEB ArguAna | map_at_100 | 56.331 |
| Retrieval | MTEB ArguAna | map_at_1000 | 56.334 |
| Retrieval | MTEB ArguAna | map_at_3 | 51.920 |
| Retrieval | MTEB ArguAna | map_at_5 | 54.011 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 41.181 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 55.968 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 56.538 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 56.542 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 51.980 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 54.209 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 40.754 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 63.605 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 66.052 |
| Retrieval | MTEB ArguAna | ndcg_at_1000 | 66.120 |
Using it via the API
Once AxForge deploys bge-en-angle for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (bge-en-angle 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-en-angle","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.