Pranava Kailash
commited on
Commit
·
bd6328b
1
Parent(s):
6cc3bb2
CyNER2.0 Runtime Memory Optimized v2
Browse files
app.py
CHANGED
@@ -4,11 +4,14 @@ from collections import defaultdict
|
|
4 |
|
5 |
# Load model and tokenizer
|
6 |
path_to_checkpoint = 'PranavaKailash/CyNER-2.0-DeBERTa-v3-base'
|
7 |
-
tokenizer = AutoTokenizer.from_pretrained(path_to_checkpoint, use_fast=True)
|
8 |
model = AutoModelForTokenClassification.from_pretrained(path_to_checkpoint)
|
9 |
-
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)
|
10 |
|
11 |
-
|
|
|
|
|
|
|
|
|
12 |
|
13 |
def tag_sentence(sentence, entities_dict):
|
14 |
"""
|
@@ -53,8 +56,8 @@ def perform_ner(text):
|
|
53 |
Run NER pipeline and prepare results for display.
|
54 |
"""
|
55 |
entities = ner_pipeline(text)
|
56 |
-
|
57 |
entities_dict = defaultdict(list)
|
|
|
58 |
for entity in entities:
|
59 |
entities_dict[entity['entity']].append({
|
60 |
"entity": entity['entity'],
|
@@ -64,7 +67,7 @@ def perform_ner(text):
|
|
64 |
"start": entity['start'],
|
65 |
"end": entity['end']
|
66 |
})
|
67 |
-
|
68 |
tagged_sentence = tag_sentence(text, entities_dict)
|
69 |
return dict(entities_dict), tagged_sentence
|
70 |
|
@@ -75,9 +78,7 @@ st.write("Enter text to get named entity recognition results.")
|
|
75 |
input_text = st.text_area("Input Text", "Type your text here...")
|
76 |
|
77 |
if st.button("Analyze"):
|
78 |
-
if
|
79 |
-
st.warning(f"Text is too long! Please enter less than {MAX_INPUT_LENGTH} characters.")
|
80 |
-
elif input_text.strip():
|
81 |
entities_dict, tagged_sentence = perform_ner(input_text)
|
82 |
|
83 |
# Display results
|
@@ -87,4 +88,4 @@ if st.button("Analyze"):
|
|
87 |
st.subheader("Entities and Details")
|
88 |
st.json(entities_dict)
|
89 |
else:
|
90 |
-
st.warning("Please enter some text for analysis.")
|
|
|
4 |
|
5 |
# Load model and tokenizer
|
6 |
path_to_checkpoint = 'PranavaKailash/CyNER-2.0-DeBERTa-v3-base'
|
7 |
+
tokenizer = AutoTokenizer.from_pretrained(path_to_checkpoint, use_fast=True, max_length=768)
|
8 |
model = AutoModelForTokenClassification.from_pretrained(path_to_checkpoint)
|
|
|
9 |
|
10 |
+
# Ensure the model is loaded on CPU explicitly to avoid any device issues
|
11 |
+
model.to('cpu')
|
12 |
+
|
13 |
+
# Initialize the NER pipeline
|
14 |
+
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)
|
15 |
|
16 |
def tag_sentence(sentence, entities_dict):
|
17 |
"""
|
|
|
56 |
Run NER pipeline and prepare results for display.
|
57 |
"""
|
58 |
entities = ner_pipeline(text)
|
|
|
59 |
entities_dict = defaultdict(list)
|
60 |
+
|
61 |
for entity in entities:
|
62 |
entities_dict[entity['entity']].append({
|
63 |
"entity": entity['entity'],
|
|
|
67 |
"start": entity['start'],
|
68 |
"end": entity['end']
|
69 |
})
|
70 |
+
|
71 |
tagged_sentence = tag_sentence(text, entities_dict)
|
72 |
return dict(entities_dict), tagged_sentence
|
73 |
|
|
|
78 |
input_text = st.text_area("Input Text", "Type your text here...")
|
79 |
|
80 |
if st.button("Analyze"):
|
81 |
+
if input_text.strip():
|
|
|
|
|
82 |
entities_dict, tagged_sentence = perform_ner(input_text)
|
83 |
|
84 |
# Display results
|
|
|
88 |
st.subheader("Entities and Details")
|
89 |
st.json(entities_dict)
|
90 |
else:
|
91 |
+
st.warning("Please enter some text for analysis.")
|