Feature Extraction
Model2Vec
Safetensors
sentence-transformers
English
embeddings
static-embeddings
sentence-similarity
Instructions to use minishlab/blink-8M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Model2Vec
How to use minishlab/blink-8M with Model2Vec:
from model2vec import StaticModel model = StaticModel.from_pretrained("minishlab/blink-8M") embeddings = model.encode(["It's dangerous to go alone!", "It's a secret to everybody."]) print(embeddings.shape) - sentence-transformers
How to use minishlab/blink-8M with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("minishlab/blink-8M") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Add library authors and citation
Browse files
README.md
CHANGED
|
@@ -376,3 +376,23 @@ Again following Erik's work, we then perform hard-negative fine-tuning on [light
|
|
| 376 |
### 4. Weight averaging
|
| 377 |
|
| 378 |
We found that weight averaging then caused the model to outperform either of the stages separately: the final model is 30% of the contrastive model from step 2 and 70% of the hard-negative model from step 3, giving us a boost on MTEB without sacrificing retrieval quality.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 376 |
### 4. Weight averaging
|
| 377 |
|
| 378 |
We found that weight averaging then caused the model to outperform either of the stages separately: the final model is 30% of the contrastive model from step 2 and 70% of the hard-negative model from step 3, giving us a boost on MTEB without sacrificing retrieval quality.
|
| 379 |
+
|
| 380 |
+
## Library Authors
|
| 381 |
+
|
| 382 |
+
Model2Vec was developed by the [Minish Lab](https://github.com/MinishLab) team consisting of [Stephan Tulkens](https://github.com/stephantul) and [Thomas van Dongen](https://github.com/Pringled).
|
| 383 |
+
|
| 384 |
+
## Citation
|
| 385 |
+
|
| 386 |
+
Please cite the [Model2Vec repository](https://github.com/MinishLab/model2vec) if you use this model in your work.
|
| 387 |
+
|
| 388 |
+
```bibtex
|
| 389 |
+
@software{minishlab2024model2vec,
|
| 390 |
+
author = {Stephan Tulkens and {van Dongen}, Thomas},
|
| 391 |
+
title = {Model2Vec: Fast State-of-the-Art Static Embeddings},
|
| 392 |
+
year = {2024},
|
| 393 |
+
publisher = {Zenodo},
|
| 394 |
+
doi = {10.5281/zenodo.17270888},
|
| 395 |
+
url = {https://github.com/MinishLab/model2vec},
|
| 396 |
+
license = {MIT}
|
| 397 |
+
}
|
| 398 |
+
```
|