adfdaf

app.py

@@ -64,10 +64,12 @@
 # # Launch the app
 # if __name__ == "__main__":
 #     interface.launch()
-
+from sentence_transformers import CrossEncoder
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 import py_vncorenlp
-py_vncorenlp.download_model(save_dir='./absolute/path/to/vncorenlp')
-rdrsegmenter = py_vncorenlp.VnCoreNLP(annotators=["wseg"], save_dir='./absolute/path/to/vncorenlp')
+py_vncorenlp.download_model(save_dir='/absolute/path/to/vncorenlp')
+rdrsegmenter = py_vncorenlp.VnCoreNLP(annotators=["wseg"], save_dir='/absolute/path/to/vncorenlp')
 
 query = "Trường UIT là gì?"
 sentences = [
@@ -83,3 +85,34 @@ tokenized_pairs = [[tokenized_query, sent] for sent in tokenized_sentences]
 
 MODEL_ID = 'itdainb/PhoRanker'
 MAX_LENGTH = 256
+
+model = CrossEncoder(MODEL_ID, max_length=MAX_LENGTH)
+
+# For fp16 usage
+model.model.half()
+
+scores = model.predict(tokenized_pairs)
+
+# 0.982, 0.2444, 0.9253
+print(scores)
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model = AutoModelForSequenceClassification.from_pretrained(MODEL_ID)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+# For fp16 usage
+model.half()
+
+features = tokenizer(tokenized_pairs, padding=True, truncation="longest_first", return_tensors="pt", max_length=MAX_LENGTH)
+
+model.eval()
+with torch.no_grad():
+    model_predictions = model(**features, return_dict=True)
+
+    logits = model_predictions.logits
+    logits = torch.nn.Sigmoid()(logits)
+    scores = [logit[0] for logit in logits]
+
+# 0.9819, 0.2444, 0.9253
+print(scores)