binhcode25 commited on
Commit
2fd3907
·
verified ·
1 Parent(s): fef0213

Add new SentenceTransformer model.

Browse files
Files changed (2) hide show
  1. README.md +45 -3
  2. model_description.json +6 -0
README.md CHANGED
@@ -1,3 +1,45 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: light-embed
3
+ pipeline_tag: sentence-similarity
4
+ tags:
5
+ - sentence-transformers
6
+ - feature-extraction
7
+ - sentence-similarity
8
+
9
+ ---
10
+
11
+ # baai-llm-embedder-onnx
12
+
13
+ This is the ONNX version of the Sentence Transformers model BAAI/llm-embedder for sentence embedding, optimized for speed and lightweight performance. By utilizing onnxruntime and tokenizers instead of heavier libraries like sentence-transformers and transformers, this version ensures a smaller library size and faster execution. Below are the details of the model:
14
+ - Base model: BAAI/llm-embedder
15
+ - Embedding dimension: 768
16
+ - Max sequence length: 512
17
+ - File size on disk: 0.41 GB
18
+
19
+ This ONNX model consists all components in the original sentence transformer model:
20
+ Transformer, Pooling, Normalize
21
+
22
+ <!--- Describe your model here -->
23
+
24
+ ## Usage (LightEmbed)
25
+
26
+ Using this model becomes easy when you have [LightEmbed](https://www.light-embed.net) installed:
27
+
28
+ ```
29
+ pip install -U light-embed
30
+ ```
31
+
32
+ Then you can use the model like this:
33
+
34
+ ```python
35
+ from light_embed import TextEmbedding
36
+ sentences = ["This is an example sentence", "Each sentence is converted"]
37
+
38
+ model = TextEmbedding('BAAI/llm-embedder')
39
+ embeddings = model.encode(sentences)
40
+ print(embeddings)
41
+ ```
42
+
43
+ ## Citing & Authors
44
+
45
+ Binh Nguyen / [email protected]
model_description.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "base_model": "BAAI/llm-embedder",
3
+ "embedding_dim": 768,
4
+ "max_seq_length": 512,
5
+ "model_file_size (GB)": 0.41
6
+ }