Update README.md
Browse files
README.md
CHANGED
|
@@ -1621,15 +1621,9 @@ language:
|
|
| 1621 |
|
| 1622 |
# bge-small-en-v1.5-sparse
|
| 1623 |
|
| 1624 |
-
|
| 1625 |
|
| 1626 |
-
|
| 1627 |
-
|
| 1628 |
-
| Links | Sparsification Method |
|
| 1629 |
-
| --------------------------------------------------------------------------------------------------- | ---------------------- |
|
| 1630 |
-
| [zeroshot/bge-large-en-v1.5-sparse](https://huggingface.co/zeroshot/bge-large-en-v1.5-sparse) | Quantization (INT8) & 50% Pruning | |
|
| 1631 |
-
| [zeroshot/bge-base-en-v1.5-sparse](https://huggingface.co/zeroshot/bge-base-en-v1.5-sparse) | Quantization (INT8) & 50% Pruning |
|
| 1632 |
-
| [zeroshot/bge-small-en-v1.5-sparse](https://huggingface.co/zeroshot/bge-small-en-v1.5-sparse) | Quantization (INT8) & 50% Pruning |
|
| 1633 |
|
| 1634 |
```bash
|
| 1635 |
pip install -U deepsparse-nightly[sentence_transformers]
|
|
@@ -1637,7 +1631,7 @@ pip install -U deepsparse-nightly[sentence_transformers]
|
|
| 1637 |
|
| 1638 |
```python
|
| 1639 |
from deepsparse.sentence_transformers import DeepSparseSentenceTransformer
|
| 1640 |
-
model = DeepSparseSentenceTransformer('
|
| 1641 |
|
| 1642 |
# Our sentences we like to encode
|
| 1643 |
sentences = ['This framework generates embeddings for each input sentence',
|
|
@@ -1654,9 +1648,4 @@ for sentence, embedding in zip(sentences, embeddings):
|
|
| 1654 |
print("")
|
| 1655 |
```
|
| 1656 |
|
| 1657 |
-
For
|
| 1658 |
-
|
| 1659 |
-
|
| 1660 |
-
For general questions on these models and sparsification methods, reach out to the engineering team on our [community Slack](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ).
|
| 1661 |
-
|
| 1662 |
-

|
|
|
|
| 1621 |
|
| 1622 |
# bge-small-en-v1.5-sparse
|
| 1623 |
|
| 1624 |
+
## Usage
|
| 1625 |
|
| 1626 |
+
This is the sparse ONNX variant of the [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) embeddings model accelerated with [Sparsify](https://github.com/neuralmagic/sparsify) for quantization/pruning and [DeepSparseSentenceTransformers](https://github.com/neuralmagic/deepsparse/tree/main/src/deepsparse/sentence_transformers) for inference.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1627 |
|
| 1628 |
```bash
|
| 1629 |
pip install -U deepsparse-nightly[sentence_transformers]
|
|
|
|
| 1631 |
|
| 1632 |
```python
|
| 1633 |
from deepsparse.sentence_transformers import DeepSparseSentenceTransformer
|
| 1634 |
+
model = DeepSparseSentenceTransformer('neuralmagic/bge-small-en-v1.5-sparse', export=False)
|
| 1635 |
|
| 1636 |
# Our sentences we like to encode
|
| 1637 |
sentences = ['This framework generates embeddings for each input sentence',
|
|
|
|
| 1648 |
print("")
|
| 1649 |
```
|
| 1650 |
|
| 1651 |
+
For general questions on these models and sparsification methods, reach out to the engineering team on our [community Slack](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ).
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|