zeroshot commited on
Commit
4800c91
1 Parent(s): f7fad3b

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -15
README.md CHANGED
@@ -1621,15 +1621,9 @@ language:
1621
 
1622
  # bge-small-en-v1.5-sparse
1623
 
1624
- This is the sparse ONNX variant of the [bge-small-en-v1.5](https://huggingface.co/BAAI/bge-small-en-v1.5) embeddings model created with [DeepSparse Optimum](https://github.com/neuralmagic/optimum-deepsparse) for ONNX export and Neural Magic's [Sparsify](https://github.com/neuralmagic/sparsify) for one-shot quantization (INT8) and unstructured pruning (50%).
1625
 
1626
- Current list of sparse and quantized bge ONNX models:
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('zeroshot/bge-small-en-v1.5-sparse', export=False)
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 further details regarding DeepSparse & Sentence Transformers integration, refer to the [DeepSparse README](https://github.com/neuralmagic/deepsparse/tree/main/src/deepsparse/sentence_transformers).
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
- ![;)](https://media.giphy.com/media/bYg33GbNbNIVzSrr84/giphy-downsized-large.gif)
 
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).