Changed to nomic

app.py

@@ -6,15 +6,16 @@ import spaces
 import torch
 
 # neuralmind/bert-base-portuguese-cased
-ModelName = "neuralmind/bert-base-portuguese-cased"
-model = AutoModel.from_pretrained(ModelName)
-tokenizer = AutoTokenizer.from_pretrained(ModelName, do_lower_case=False)
-processor = AutoImageProcessor.from_pretrained("nomic-ai/nomic-embed-vision-v1.5")
-vision_model = AutoModel.from_pretrained("nomic-ai/nomic-embed-vision-v1.5", trust_remote_code=True)
+#ModelName = "neuralmind/bert-base-portuguese-cased"
+#model = AutoModel.from_pretrained(ModelName)
+#tokenizer = AutoTokenizer.from_pretrained(ModelName, do_lower_case=False)
 
-# tokenizer = AutoTokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1.5')
-# text_model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', trust_remote_code=True)
-# text_model.eval()
+
+#processor = AutoImageProcessor.from_pretrained("nomic-ai/nomic-embed-vision-v1.5")
+#vision_model = AutoModel.from_pretrained("nomic-ai/nomic-embed-vision-v1.5", trust_remote_code=True)
+tokenizer = AutoTokenizer.from_pretrained('nomic-ai/nomic-embed-text-v1.5')
+text_model = AutoModel.from_pretrained('nomic-ai/nomic-embed-text-v1.5', trust_remote_code=True)
+text_model.eval()
 
 def mean_pooling(model_output, attention_mask):
     token_embeddings = model_output[0]
@@ -26,25 +27,25 @@ def TxtEmbed(text):
    
 
     
-    input_ids = tokenizer.encode(text, return_tensors='pt')
+    #input_ids = tokenizer.encode(text, return_tensors='pt')
     
-    with torch.no_grad():
-        outs = model(input_ids)
-        encoded = outs[0][0, 1:-1]  # Ignore [CLS] and [SEP] special tokens
-    return (encoded.tolist())[0];
+    #with torch.no_grad():
+    #    outs = model(input_ids)
+    #    encoded = outs[0][0, 1:-1]  # Ignore [CLS] and [SEP] special tokens
+    #return (encoded.tolist())[0];
 
     
-   #sentences = [text]
-   #encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
-   #
-   #with torch.no_grad():
-   #    model_output = text_model(**encoded_input)
-   #
-   #text_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
-   #text_embeddings = F.layer_norm(text_embeddings, normalized_shape=(text_embeddings.shape[1],))
-   #text_embeddings = F.normalize(text_embeddings, p=2, dim=1)
-   # 
-   # return (text_embeddings.tolist)[0]
+   sentences = [text]
+   encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+   
+   with torch.no_grad():
+       model_output = text_model(**encoded_input)
+   
+   text_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+   text_embeddings = F.layer_norm(text_embeddings, normalized_shape=(text_embeddings.shape[1],))
+   text_embeddings = F.normalize(text_embeddings, p=2, dim=1)
+    
+   return (text_embeddings.tolist)[0]