zeroshot commited on
Commit
5babcd7
1 Parent(s): 35ac0f3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +22 -0
README.md CHANGED
@@ -21,6 +21,28 @@ Current list of sparse and quantized gte ONNX models:
21
  | [zeroshot/gte-small-sparse](https://huggingface.co/zeroshot/gte-small-sparse) | Quantization (INT8) & 50% Pruning |
22
  | [zeroshot/gte-small-quant](https://huggingface.co/zeroshot/gte-small-quant) | Quantization (INT8) |
23
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
 
25
  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).
26
 
 
21
  | [zeroshot/gte-small-sparse](https://huggingface.co/zeroshot/gte-small-sparse) | Quantization (INT8) & 50% Pruning |
22
  | [zeroshot/gte-small-quant](https://huggingface.co/zeroshot/gte-small-quant) | Quantization (INT8) |
23
 
24
+ ```bash
25
+ pip install -U deepsparse-nightly[sentence_transformers]
26
+ ```
27
+
28
+ ```python
29
+ from deepsparse.sentence_transformers import SentenceTransformer
30
+ model = SentenceTransformer('zeroshot/gte-base-sparse', export=False)
31
+
32
+ # Our sentences we like to encode
33
+ sentences = ['This framework generates embeddings for each input sentence',
34
+ 'Sentences are passed as a list of string.',
35
+ 'The quick brown fox jumps over the lazy dog.']
36
+
37
+ # Sentences are encoded by calling model.encode()
38
+ embeddings = model.encode(sentences)
39
+
40
+ # Print the embeddings
41
+ for sentence, embedding in zip(sentences, embeddings):
42
+ print("Sentence:", sentence)
43
+ print("Embedding:", embedding.shape)
44
+ print("")
45
+ ```
46
 
47
  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).
48