Update README.md

README.md

@@ -8,7 +8,7 @@ tags:
 
 ---
 
-# {MODEL_NAME}
+# mmarco-sentence-flare-it
 
 This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
 
@@ -25,12 +25,31 @@ pip install -U sentence-transformers
 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 import SentenceTransformer, util
+
+query = "Quante persone vivono a Londra?"
+docs = ["A Londra vivono circa 9 milioni di persone", "Londra è conosciuta per il suo quartiere finanziario"]
+
+#Load the model
+model = SentenceTransformer('nickprock/mmarco-sentence-flare-it')
+
+#Encode query and documents
+query_emb = model.encode(query)
+doc_emb = model.encode(docs)
+
+#Compute dot score between query and all document embeddings
+scores = util.dot_score(query_emb, doc_emb)[0].cpu().tolist()
+
+#Combine docs & scores
+doc_score_pairs = list(zip(docs, scores))
+
+#Sort by decreasing score
+doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
+
+#Output passages & scores
+for doc, score in doc_score_pairs:
+    print(score, doc)
 
-model = SentenceTransformer('{MODEL_NAME}')
-embeddings = model.encode(sentences)
-print(embeddings)
 ```
 
 
@@ -42,33 +61,54 @@ Without [sentence-transformers](https://www.SBERT.net), you can use the model li
 from transformers import AutoTokenizer, AutoModel
 import torch
 
-
 #Mean Pooling - Take attention mask into account for correct averaging
 def mean_pooling(model_output, attention_mask):
-    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    token_embeddings = model_output.last_hidden_state
     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)
 
 
+#Encode text
+def encode(texts):
+    # Tokenize sentences
+    encoded_input = tokenizer(texts, padding=True, truncation=True, return_tensors='pt')
+
+    # Compute token embeddings
+    with torch.no_grad():
+        model_output = model(**encoded_input, return_dict=True)
+
+    # Perform pooling
+    embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+    return embeddings
+
+
 # Sentences we want sentence embeddings for
-sentences = ['This is an example sentence', 'Each sentence is converted']
+query = "Quante persone vivono a Londra?"
+docs = ["A Londra vivono circa 9 milioni di persone", "Londra è conosciuta per il suo quartiere finanziario"]
 
 # Load model from HuggingFace Hub
-tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
-model = AutoModel.from_pretrained('{MODEL_NAME}')
+tokenizer = AutoTokenizer.from_pretrained("nickprock/mmarco-sentence-flare-it")
+model = AutoModel.from_pretrained("nickprock/mmarco-sentence-flare-it")
+
+#Encode query and docs
+query_emb = encode(query)
+doc_emb = encode(docs)
+
+#Compute dot score between query and all document embeddings
+scores = torch.mm(query_emb, doc_emb.transpose(0, 1))[0].cpu().tolist()
 
-# Tokenize sentences
-encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+#Combine docs & scores
+doc_score_pairs = list(zip(docs, scores))
 
-# Compute token embeddings
-with torch.no_grad():
-    model_output = model(**encoded_input)
+#Sort by decreasing score
+doc_score_pairs = sorted(doc_score_pairs, key=lambda x: x[1], reverse=True)
 
-# Perform pooling. In this case, mean pooling.
-sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+#Output passages & scores
+print("Query:", query)
+for doc, score in doc_score_pairs:
+    print(score, doc)
 
-print("Sentence embeddings:")
-print(sentence_embeddings)
 ```
 
 
@@ -126,4 +166,4 @@ SentenceTransformer(
 
 ## Citing & Authors
 
-<!--- Describe where people can find more information -->
+More information about the [base model here](https://huggingface.co/osiria/flare-it/)