Model reference · open weights
mxbai-embed-2d-large is an open-weight embedding model from mixedbread-ai, 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
🪆mxbai-embed-2d-large-v1🪆 This is our 2DMSE sentence embedding model. It supports the adaptive transformer layer and embedding size. Find out more in our blog post. TLDR: 2D-🪆 allows you to shrink the model and the embeddings layer. Shrinking only the embeddings model yields competetive results to other models like nomics embeddings model. Shrinking the model to ~50% maintains upto 85% of the performance without further training. Quickstart Here, we provide several ways to produce sentence embeddings with adaptive layers and embedding sizes. For this version, it is recommended to set adaptive layers from 20 to 24. sentence-transformers Currently, the best way to use our models is with the most recent version of sentence-transformers. angle-emb You can also use the lastest angle-emb for inference, as follows: Transformers.js If you haven't already, you can install the Transformers.js JavaScript library from NPM using: You can then use the model to compute embeddings as follows: Using API You can use the model via our API as follows: The API comes with native INT8 and binary quantization support! Check out the docs for more information. Evaluation Please find more information in our blog post. Community Please join our Discord Community and share your feedback and thoughts! We are here to help and also always happy to chat. License Apache 2.0
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | mixedbread-ai |
|---|---|
| Type | Embedding models |
| Parameters (lead) | 335M |
| Context | 512 tokens |
| Variants | 1 |
| Runs with | sentence-transformers |
| Released | 2024-03-04 |
| Popularity | 184k downloads / month |
| Likes | 43 |
| 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 |
|---|---|---|---|---|---|
| mxbai-embed-2d-large-v1 | 335M | BF16 | ~0.8 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 | 74.761 |
| Classification | MTEB AmazonCounterfactualClassification (en) | ap | 37.906 |
| Classification | MTEB AmazonCounterfactualClassification (en) | f1 | 68.808 |
| Classification | MTEB AmazonPolarityClassification | accuracy | 93.256 |
| Classification | MTEB AmazonPolarityClassification | ap | 90.069 |
| Classification | MTEB AmazonPolarityClassification | f1 | 93.248 |
| Classification | MTEB AmazonReviewsClassification (en) | accuracy | 46.162 |
| Classification | MTEB AmazonReviewsClassification (en) | f1 | 45.67 |
| Retrieval | MTEB ArguAna | map_at_1 | 37.98 |
| Retrieval | MTEB ArguAna | map_at_10 | 54.918 |
| Retrieval | MTEB ArguAna | map_at_100 | 55.401 |
| Retrieval | MTEB ArguAna | map_at_1000 | 55.403 |
| Retrieval | MTEB ArguAna | map_at_3 | 50.249 |
| Retrieval | MTEB ArguAna | map_at_5 | 53.4 |
| Retrieval | MTEB ArguAna | mrr_at_1 | 38.834 |
| Retrieval | MTEB ArguAna | mrr_at_10 | 55.24 |
| Retrieval | MTEB ArguAna | mrr_at_100 | 55.737 |
| Retrieval | MTEB ArguAna | mrr_at_1000 | 55.738 |
| Retrieval | MTEB ArguAna | mrr_at_3 | 50.581 |
| Retrieval | MTEB ArguAna | mrr_at_5 | 53.71 |
| Retrieval | MTEB ArguAna | ndcg_at_1 | 37.98 |
| Retrieval | MTEB ArguAna | ndcg_at_10 | 63.629 |
| Retrieval | MTEB ArguAna | ndcg_at_100 | 65.567 |
| Retrieval | MTEB ArguAna | ndcg_at_1000 | 65.614 |
Using it via the API
Once AxForge deploys mxbai-embed-2d-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (mxbai-embed-2d-large 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":"mxbai-embed-2d-large","input":"text to embed"}'
Licence
Open weights under apache-2.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗
Explore