Update README.md

README.md

@@ -9,13 +9,13 @@ language:
 - he
 library_name: sentence-transformers
 ---
-# WIP!!!
 
-# {MODEL_NAME} 
+
+# imvladikon/sentence-transformers-alephbert[WIP]
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 768 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
-<!--- Describe your model here -->
+
 
 ## Usage (Sentence-Transformers)
 
@@ -29,11 +29,16 @@ Then you can use the model like this:
 
 ```python
 from sentence_transformers import SentenceTransformer
-sentences = ["This is an example sentence", "Each sentence is converted"]
+from sentence_transformers.util import cos_sim
 
-model = SentenceTransformer('{MODEL_NAME}')
+sentences = ["הם היו שמחים לראות את האירוע שהתקיים.", "לראות את האירוע שהתקיים היה מאוד משמח להם."]
+
+model = SentenceTransformer('imvladikon/sentence-transformers-alephbert')
 embeddings = model.encode(sentences)
-print(embeddings)
+
+
+print(cos_sim(*tuple(embeddings)).item())
+# 0.883316159248352
 ```
 
 
@@ -42,8 +47,9 @@ print(embeddings)
 Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
 
 ```python
-from transformers import AutoTokenizer, AutoModel
 import torch
+from torch import nn
+from transformers import AutoTokenizer, AutoModel
 
 
 #Mean Pooling - Take attention mask into account for correct averaging
@@ -54,11 +60,11 @@ def mean_pooling(model_output, attention_mask):
 
 
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+sentences = ["הם היו שמחים לראות את האירוע שהתקיים.", "לראות את האירוע שהתקיים היה מאוד משמח להם."]
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained('imvladikon/sentence-transformers-alephbert')
+model = AutoModel.from_pretrained('imvladikon/sentence-transformers-alephbert')
 
 # Tokenize sentences
 encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
@@ -70,16 +76,14 @@ with torch.no_grad():
 # Perform pooling. In this case, mean pooling.
 sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
+cos_sim = nn.CosineSimilarity(dim=0, eps=1e-6)
+print(cos_sim(sentence_embeddings[0], sentence_embeddings[1]).item())
 ```
 
 
 
 ## Evaluation Results
 
-<!--- Describe how your model was evaluated -->
-
 For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
 
 
@@ -129,4 +133,3 @@ SentenceTransformer(
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->