Create README.md

README.md

@@ -0,0 +1,75 @@
+---
+pipeline_tag: sentence-similarity
+language: en
+license: apache-2.0
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+- onnx
+---
+
+# 
+
+This is the ONNX model of sentence-transformers/all-MiniLM-L6-v2 [https://seb.sbert.net]. Currently, Hugging Face does not support downloading ONNX model and generate embeddings. I have created a workaround using sbert and optimum together to generate embeddings.
+
+```
+pip install onnx
+pip install onnxruntime==1.10.0
+pip install transformers>4.6.1
+pip install sentencepiece
+pip install sentence-transformers
+pip install optimum
+pip install torch==1.9.0
+```
+
+Then you can use the model like this:
+
+```python
+import os
+from sentence_transformers.util import snapshot_download
+from transformers import AutoTokenizer
+from optimum.onnxruntime import ORTModelForFeatureExtraction
+from sentence_transformers.models import Transformer, Pooling, Dense
+import torch
+from transformers.modeling_outputs import BaseModelOutput
+import torch.nn.functional as F
+import shutil
+
+model_name = 'vamsibanda/sbert-onnx-all-MiniLM-L12-v2'
+cache_folder = './'
+model_path =  os.path.join(cache_folder, model_name.replace("/", "_"))
+
+def generate_embedding(text):
+    token = tokenizer(text, return_tensors='pt')
+    embeddings = model(input_ids=token['input_ids'], attention_mask=token['attention_mask'])
+    sbert_embeddings = mean_pooling(embeddings, token['attention_mask'])
+    sbert_embeddings = F.normalize(sbert_embeddings, p=2, dim=1)
+    return sbert_embeddings.tolist()[0]
+    
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+def download_onnx_model(model_name, cache_folder, model_path, force_download = False):
+    if force_download and os.path.exists(model_path):
+       shutil.rmtree(model_path)
+    elif os.path.exists(model_path):
+       return 
+    snapshot_download(model_name,
+                     cache_dir=cache_folder,
+                     library_name='sentence-transformers'
+                     )
+    return
+                    
+     
+_ = download_onnx_model(model_name, cache_folder, model_path)                
+tokenizer = AutoTokenizer.from_pretrained(model_path)
+model = ORTModelForFeatureExtraction.from_pretrained(model_path, force_download=False)
+pooling_layer = Pooling.load(f"{model_path}/1_Pooling")
+
+generate_embedding('That is a happy person')
+                    
+```