More requirements

app.py

@@ -9,55 +9,55 @@ import torch.nn.functional as F
 
 
 #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
-#     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 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 training():
-#     dataset = load_dataset("glue", "cola")
-#     dataset = dataset["train"]
+def training():
+    dataset = load_dataset("glue", "cola")
+    dataset = dataset["train"]
 
-#     sentences = ["This is an example sentence", "Each sentence is converted"]
+    sentences = ["This is an example sentence", "Each sentence is converted"]
 
-#     model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
-#     embeddings = model.encode(sentences)
-#     print(embeddings)
+    model = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
+    embeddings = model.encode(sentences)
+    print(embeddings)
     
-#     # Sentences we want sentence embeddings for
-#     sentences = ['This is an example sentence', 'Each sentence is converted']
+    # Sentences we want sentence embeddings for
+    sentences = ['This is an example sentence', 'Each sentence is converted']
 
-#     # Load model from HuggingFace Hub
-#     tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
-#     model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
+    # Load model from HuggingFace Hub
+    tokenizer = AutoTokenizer.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
+    model = AutoModel.from_pretrained('sentence-transformers/all-MiniLM-L6-v2')
 
-#     # Tokenize sentences
-#     encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+    # Tokenize sentences
+    encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
 
-#     # Compute token embeddings
-#     with torch.no_grad():
-#         model_output = model(**encoded_input)
+    # Compute token embeddings
+    with torch.no_grad():
+        model_output = model(**encoded_input)
 
-#     # Perform pooling
-#     sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+    # Perform pooling
+    sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
 
-#     # Normalize embeddings
-#     sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
+    # Normalize embeddings
+    sentence_embeddings = F.normalize(sentence_embeddings, p=2, dim=1)
 
-#     print("Sentence embeddings:")
-#     print(sentence_embeddings)
+    print("Sentence embeddings:")
+    print(sentence_embeddings)
     
 
 def greet(name):
     return "Hello " + name + "!!"
 
 
-# def main():
-#     return 0
+def main():
+    iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+    iface.launch()
+
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
     
-# if __name__ == "__main__":
-#     main()
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -1 +1,4 @@
-spacy
+spacy
+sentence_transformers
+transformers
+torch