Update README.md
Browse files
README.md
CHANGED
@@ -42,22 +42,19 @@ label_list = ["O", "B-PER", "I-PER", "B-ORG", "I-ORG", "B-LOC", "I-LOC", "B-MISC
|
|
42 |
|
43 |
```
|
44 |
def predict_entities(text, model):
|
45 |
-
|
46 |
tokens = tokenizer(text, return_tensors="pt", truncation=True)
|
47 |
tokens = {key: val.to(device) for key, val in tokens.items()} # Move to CUDA
|
48 |
|
49 |
-
# ✅ Run model inference
|
50 |
with torch.no_grad():
|
51 |
outputs = model(**tokens)
|
52 |
|
53 |
logits = outputs.logits # Extract logits
|
54 |
predictions = torch.argmax(logits, dim=2) # Get highest probability labels
|
55 |
|
56 |
-
# ✅ Convert token IDs back to words
|
57 |
tokens_list = tokenizer.convert_ids_to_tokens(tokens["input_ids"][0])
|
58 |
predicted_labels = [label_list[pred] for pred in predictions[0].cpu().numpy()]
|
59 |
|
60 |
-
# ✅ Group subword tokens into whole words
|
61 |
final_tokens = []
|
62 |
final_labels = []
|
63 |
for token, label in zip(tokens_list, predicted_labels):
|
@@ -67,7 +64,6 @@ def predict_entities(text, model):
|
|
67 |
final_tokens.append(token)
|
68 |
final_labels.append(label)
|
69 |
|
70 |
-
# ✅ Display results (ignore special tokens)
|
71 |
for token, label in zip(final_tokens, final_labels):
|
72 |
if token not in ["[CLS]", "[SEP]"]:
|
73 |
print(f"{token}: {label}")
|
|
|
42 |
|
43 |
```
|
44 |
def predict_entities(text, model):
|
45 |
+
|
46 |
tokens = tokenizer(text, return_tensors="pt", truncation=True)
|
47 |
tokens = {key: val.to(device) for key, val in tokens.items()} # Move to CUDA
|
48 |
|
|
|
49 |
with torch.no_grad():
|
50 |
outputs = model(**tokens)
|
51 |
|
52 |
logits = outputs.logits # Extract logits
|
53 |
predictions = torch.argmax(logits, dim=2) # Get highest probability labels
|
54 |
|
|
|
55 |
tokens_list = tokenizer.convert_ids_to_tokens(tokens["input_ids"][0])
|
56 |
predicted_labels = [label_list[pred] for pred in predictions[0].cpu().numpy()]
|
57 |
|
|
|
58 |
final_tokens = []
|
59 |
final_labels = []
|
60 |
for token, label in zip(tokens_list, predicted_labels):
|
|
|
64 |
final_tokens.append(token)
|
65 |
final_labels.append(label)
|
66 |
|
|
|
67 |
for token, label in zip(final_tokens, final_labels):
|
68 |
if token not in ["[CLS]", "[SEP]"]:
|
69 |
print(f"{token}: {label}")
|