tokenizer update

app.py

@@ -4,24 +4,26 @@ import torch
 
 device = 'cuda' if torch.cuda.is_available() else 'cpu'
 
-tokenizer = AutoTokenizer.from_pretrained("distilbert-base-uncased")
-model = AutoModelForSequenceClassification.from_pretrained("Rahmat82/DistilBERT-finetuned-on-emotion")
+model_id = "Rahmat82/DistilBERT-finetuned-on-emotion"
+tokenizer = AutoTokenizer.from_pretrained(model_id, return_tensors="pt", use_fast=True)
+model = AutoModelForSequenceClassification.from_pretrained(model_id)
 model.to(device)
 
+label2ids = {
+                "sadness": 0,
+                "joy": 1,
+                "love": 2,
+                "anger": 3,
+                "fear": 4,
+                "surprise": 5,
+            }
+
 def predict(query: str) -> dict:
     inputs = tokenizer(query, return_tensors='pt')
     inputs.to(device)
     outputs = model(**inputs)
     outputs = torch.sigmoid(outputs.logits)
     outputs = outputs.detach().cpu().numpy()
-    label2ids = {
-        "sadness": 0,
-        "joy": 1,
-        "love": 2,
-        "anger": 3,
-        "fear": 4,
-        "surprise": 5,
-    }
 
     for i, k in enumerate(label2ids.keys()):
         label2ids[k] = outputs[0][i]