Model reference · open weights
bge-micro is an open-weight embedding model from TaylorAI, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
bge-micro-v2 This is a sentence-transformers model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search. Distilled in a 2-step training process (bge-micro was step 1) from BAAI/bge-small-en-v1.5. Usage (Sentence-Transformers) Using this model becomes easy when you have sentence-transformers installed: Then you can use the model like this: Usage (HuggingFace Transformers) Without sentence-transformers, you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings. Evaluation Results For an automated evaluation of this model, see the Sentence Embeddings Benchmark: https://seb.sbert.net Full Model Architecture Citing & Authors
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | TaylorAI |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 17M |
| Context | 512 tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Released | 2023-10-11 |
| Popularity | 973k downloads / month |
| Likes | 65 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| bge-micro-v2 | 17M | BF16 | ~0 GB | ✓ | Weights ↗ |
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 | 67.761 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 29.638 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 61.312 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 79.755 |
| Classification | MTEB AmazonPolarityClassification | ap | 74.214 |
| Classification | MTEB AmazonPolarityClassification | f1 | 79.653 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 37.452 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 37.025 |
| Retrieval | MTEB ArguAna | map_at_1 | 31.152 |
| Retrieval | MTEB ArguAna | map_at_10 | 46.702 |
| Retrieval | MTEB ArguAna | map_at_100 | 47.563 |
| Retrieval | MTEB ArguAna | map_at_1000 | 47.567 |
| Retrieval | MTEB ArguAna | map_at_3 | 42.058 |
| Retrieval | MTEB ArguAna | map_at_5 | 44.608 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 32.006 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 47.064 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 47.91 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 47.915 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 42.283 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 44.968 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 31.152 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 55.308 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 58.965 |
| Retrieval | MTEB ArguAna | ndcg_at_1000 | 59.067 |
Using it via the API
Once AxForge deploys bge-micro for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (bge-micro 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-micro","input":"text to embed"}'
Details
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore