zeroshot commited on
Commit
ebea0f0
1 Parent(s): a0d82d6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -18
README.md CHANGED
@@ -724,18 +724,9 @@ model-index:
724
 
725
  # bge-base-en-v1.5-sparse
726
 
727
- This is the sparsified ONNX variant of the [bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) embeddings model created with [DeepSparse Optimum](https://github.com/neuralmagic/optimum-deepsparse) for ONNX export/inference pipeline and Neural Magic's [Sparsify](https://github.com/neuralmagic/sparsify) for one-shot quantization (INT8) and unstructured pruning (50%).
728
 
729
- Current list of sparse and quantized bge ONNX models:
730
-
731
- | Links | Sparsification Method |
732
- | --------------------------------------------------------------------------------------------------- | ---------------------- |
733
- | [zeroshot/bge-large-en-v1.5-sparse](https://huggingface.co/zeroshot/bge-large-en-v1.5-sparse) | Quantization (INT8) & 50% Pruning |
734
- | [zeroshot/bge-large-en-v1.5-quant](https://huggingface.co/zeroshot/bge-large-en-v1.5-quant) | Quantization (INT8) |
735
- | [zeroshot/bge-base-en-v1.5-sparse](https://huggingface.co/zeroshot/bge-base-en-v1.5-sparse) | Quantization (INT8) & 50% Pruning |
736
- | [zeroshot/bge-base-en-v1.5-quant](https://huggingface.co/zeroshot/bge-base-en-v1.5-quant) | Quantization (INT8) |
737
- | [zeroshot/bge-small-en-v1.5-sparse](https://huggingface.co/zeroshot/bge-small-en-v1.5-sparse) | Quantization (INT8) & 50% Pruning |
738
- | [zeroshot/bge-small-en-v1.5-quant](https://huggingface.co/zeroshot/bge-small-en-v1.5-quant) | Quantization (INT8) |
739
 
740
  ```bash
741
  pip install -U deepsparse-nightly[sentence_transformers]
@@ -743,7 +734,7 @@ pip install -U deepsparse-nightly[sentence_transformers]
743
 
744
  ```python
745
  from deepsparse.sentence_transformers import DeepSparseSentenceTransformer
746
- model = DeepSparseSentenceTransformer('zeroshot/bge-base-en-v1.5-sparse', export=False)
747
 
748
  # Our sentences we like to encode
749
  sentences = ['This framework generates embeddings for each input sentence',
@@ -760,9 +751,4 @@ for sentence, embedding in zip(sentences, embeddings):
760
  print("")
761
  ```
762
 
763
- For further details regarding DeepSparse & Sentence Transformers integration, refer to the [DeepSparse README](https://github.com/neuralmagic/deepsparse/tree/main/src/deepsparse/sentence_transformers).
764
-
765
-
766
- 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).
767
-
768
- ![;)](https://media.giphy.com/media/bYg33GbNbNIVzSrr84/giphy-downsized-large.gif)
 
724
 
725
  # bge-base-en-v1.5-sparse
726
 
727
+ ## Usage
728
 
729
+ 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.
 
 
 
 
 
 
 
 
 
730
 
731
  ```bash
732
  pip install -U deepsparse-nightly[sentence_transformers]
 
734
 
735
  ```python
736
  from deepsparse.sentence_transformers import DeepSparseSentenceTransformer
737
+ model = DeepSparseSentenceTransformer('neuralmagic/bge-base-en-v1.5-sparse', export=False)
738
 
739
  # Our sentences we like to encode
740
  sentences = ['This framework generates embeddings for each input sentence',
 
751
  print("")
752
  ```
753
 
754
+ 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).