README.md

---
language:
  - en
license: apache-2.0
library_name: model2vec
tags:
  - model2vec
  - sentence-transformers
  - embeddings
  - static-embeddings
  - tokenlearn
  - compact
  - tiny
  - micro
base_model: mixedbread-ai/mxbai-embed-large-v1
model-index:
  - name: potion-mxbai-micro
    results:
      - task:
          type: STS
        dataset:
          type: mteb/stsbenchmark-sts
          name: MTEB STS (English, 10 tasks)
        metrics:
          - type: spearman_cosine
            value: 71.04
      - task:
          type: Classification
        dataset:
          type: mteb/banking77
          name: MTEB Classification (English, 12 tasks)
        metrics:
          - type: accuracy
            value: 59.66
      - task:
          type: PairClassification
        dataset:
          type: mteb/twittersemeval2015
          name: MTEB PairClassification (English, 3 tasks)
        metrics:
          - type: ap
            value: 76.02
---

# potion-mxbai-micro

A **700KB** static embedding model. Yes, really. Seven hundred kilobytes for useful sentence embeddings.

## Highlights

- **68.91 avg** on full MTEB English (STS + Classification + PairClassification, 25 tasks)
- **700KB** total model size — fits in an email attachment
- **256 dimensions** — same output dimensionality as the full model
- **80-88x faster** than all-MiniLM-L6-v2 on CPU
- Pure numpy inference — no GPU needed
- Drop-in compatible with model2vec and sentence-transformers

## How It Was Made

1. Start with our best 256D model ([potion-mxbai-256d-v2](https://huggingface.co/blobbybob/potion-mxbai-256d-v2), 70.98 avg)
2. Apply model2vec's vocabulary quantization: cluster the 29,525 token embeddings into 2,000 centroids using k-means
3. Each token maps to its nearest centroid via a token mapping table
4. The full tokenizer is preserved — all text still tokenizes correctly

The result is a 2,000-row embedding table at 256D with int8 quantization. Tokens that are semantically similar share the same embedding vector, which acts as a natural regularizer.

## Benchmark Results (Full MTEB English Suite)

| Model | STS | Classification | PairClassification | **Avg** | **Size** |
|-------|-----|----------------|-------------------|---------|----------|
| [potion-mxbai-2m-512d](https://huggingface.co/blobbybob/potion-mxbai-2m-512d) | 74.15 | 65.44 | 76.80 | **72.13** | ~125MB |
| [potion-mxbai-256d-v2](https://huggingface.co/blobbybob/potion-mxbai-256d-v2) | 73.79 | 63.23 | 77.33 | **71.45** | 7.5MB |
| [potion-mxbai-128d-v2](https://huggingface.co/blobbybob/potion-mxbai-128d-v2) | 72.56 | 61.48 | 75.45 | **69.83** | 3.9MB |
| **potion-mxbai-micro** (this) | 71.04 | 59.66 | 76.02 | **68.91** | **0.7MB** |

Evaluated on 25 tasks (10 STS, 12 Classification, 3 PairClassification), English subsets only.

## Usage

```python
from model2vec import StaticModel

model = StaticModel.from_pretrained("blobbybob/potion-mxbai-micro")
embeddings = model.encode(["Hello world", "Static embeddings are fast"])
```

With Sentence Transformers:

```python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer("blobbybob/potion-mxbai-micro")
embeddings = model.encode(["Hello world", "Static embeddings are fast"])
```

## When to use this model

- You need embeddings in **extremely constrained environments** (embedded systems, IoT, WASM)
- You're building a **browser extension** or **mobile app** where every KB counts
- You want a **fallback embedding model** that loads instantly
- You need to embed millions of documents and want to minimize **index storage**
- **Prototyping** — get semantic search working in seconds, upgrade to larger models later

## Model Family

| Model | Avg | Size | Best for |
|-------|-----|------|----------|
| [potion-mxbai-2m-512d](https://huggingface.co/blobbybob/potion-mxbai-2m-512d) | 72.13 | ~125MB | Maximum quality |
| [potion-mxbai-256d-v2](https://huggingface.co/blobbybob/potion-mxbai-256d-v2) | 71.45 | 7.5MB | Best quality/size balance |
| [potion-mxbai-128d-v2](https://huggingface.co/blobbybob/potion-mxbai-128d-v2) | 69.83 | 3.9MB | Compact deployments |
| **potion-mxbai-micro** | **68.91** | **0.7MB** | Ultra-tiny / embedded |

## Citation

```bibtex
@article{minishlab2024model2vec,
  author = {Tulkens, Stephan and {van Dongen}, Thomas},
  title = {Model2Vec: Fast State-of-the-Art Static Embeddings},
  year = {2024},
  url = {https://github.com/MinishLab/model2vec}
}
```