Testing for output

main.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():
+#     return 0
 
 iface = gr.Interface(fn=greet, inputs="text", outputs="text")
 iface.launch()
     
-if __name__ == "__main__":
-    main()
+# if __name__ == "__main__":
+#     main()