Feature Extraction
sentence-transformers
PyTorch
ONNX
English
bert
splade++
document-expansion
sparse representation
bag-of-words
passage-retrieval
knowledge-distillation
document encoder
sparse-encoder
sparse
splade
text-embeddings-inference
Instructions to use prithivida/Splade_PP_en_v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use prithivida/Splade_PP_en_v1 with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("prithivida/Splade_PP_en_v1") 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
added expansion image
Browse files
README.md
CHANGED
|
@@ -57,9 +57,9 @@ Getting pros of both searches made sense and that gave rise to interest in learn
|
|
| 57 |
|
| 58 |
4. What a Sparse model learns ?
|
| 59 |
|
| 60 |
-
The model learns to project it's learned dense representations over a MLM head to give a vocabulary distribution.
|
| 61 |
|
| 62 |
-
|
| 63 |
|
| 64 |
</details>
|
| 65 |
|
|
|
|
| 57 |
|
| 58 |
4. What a Sparse model learns ?
|
| 59 |
|
| 60 |
+
The model learns to project it's learned dense representations over a MLM head to give a vocabulary distribution. Which is just to say the model can do automatic token expansion. (Image courtesy of pinecone)
|
| 61 |
|
| 62 |
+
<img src="./expansion.png" width=650 height=500/>
|
| 63 |
|
| 64 |
</details>
|
| 65 |
|