Token Classification
Transformers
Safetensors
English
bert
ner
named-entity-recognition
text-classification
transformer
pretrained-model
huggingface
real-time-inference
efficient-nlp
micro-nlp
chatbot
information-extraction
document-understanding
search-enhancement
medical-nlp
financial-nlp
legal-nlp
general-purpose-nlp
on-device-nlp
Instructions to use boltuix/EntityBERT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use boltuix/EntityBERT with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="boltuix/EntityBERT")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForTokenClassification tokenizer = AutoTokenizer.from_pretrained("boltuix/EntityBERT") model = AutoModelForTokenClassification.from_pretrained("boltuix/EntityBERT", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +7 -5
config.json
CHANGED
|
@@ -1,7 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"architectures": [
|
| 3 |
-
"BertForTokenClassification"
|
| 4 |
-
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
"classifier_dropout": null,
|
| 7 |
"hidden_act": "gelu",
|
|
@@ -48,7 +46,9 @@
|
|
| 48 |
"37": "B-email",
|
| 49 |
"38": "I-email",
|
| 50 |
"39": "B-url",
|
| 51 |
-
"40": "I-url"
|
|
|
|
|
|
|
| 52 |
},
|
| 53 |
"initializer_range": 0.02,
|
| 54 |
"intermediate_size": 512,
|
|
@@ -73,6 +73,7 @@
|
|
| 73 |
"B-toloc.state_name": 11,
|
| 74 |
"B-transportation_mode": 17,
|
| 75 |
"B-url": 39,
|
|
|
|
| 76 |
"I-arrival_time": 26,
|
| 77 |
"I-company_name": 28,
|
| 78 |
"I-date": 20,
|
|
@@ -93,6 +94,7 @@
|
|
| 93 |
"I-toloc.state_name": 12,
|
| 94 |
"I-transportation_mode": 18,
|
| 95 |
"I-url": 40,
|
|
|
|
| 96 |
"O": 0
|
| 97 |
},
|
| 98 |
"layer_norm_eps": 1e-12,
|
|
@@ -107,4 +109,4 @@
|
|
| 107 |
"type_vocab_size": 2,
|
| 108 |
"use_cache": true,
|
| 109 |
"vocab_size": 30522
|
| 110 |
-
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"architectures": ["BertForTokenClassification"],
|
|
|
|
|
|
|
| 3 |
"attention_probs_dropout_prob": 0.1,
|
| 4 |
"classifier_dropout": null,
|
| 5 |
"hidden_act": "gelu",
|
|
|
|
| 46 |
"37": "B-email",
|
| 47 |
"38": "I-email",
|
| 48 |
"39": "B-url",
|
| 49 |
+
"40": "I-url",
|
| 50 |
+
"41": "B-other",
|
| 51 |
+
"42": "I-other"
|
| 52 |
},
|
| 53 |
"initializer_range": 0.02,
|
| 54 |
"intermediate_size": 512,
|
|
|
|
| 73 |
"B-toloc.state_name": 11,
|
| 74 |
"B-transportation_mode": 17,
|
| 75 |
"B-url": 39,
|
| 76 |
+
"B-other": 41,
|
| 77 |
"I-arrival_time": 26,
|
| 78 |
"I-company_name": 28,
|
| 79 |
"I-date": 20,
|
|
|
|
| 94 |
"I-toloc.state_name": 12,
|
| 95 |
"I-transportation_mode": 18,
|
| 96 |
"I-url": 40,
|
| 97 |
+
"I-other": 42,
|
| 98 |
"O": 0
|
| 99 |
},
|
| 100 |
"layer_norm_eps": 1e-12,
|
|
|
|
| 109 |
"type_vocab_size": 2,
|
| 110 |
"use_cache": true,
|
| 111 |
"vocab_size": 30522
|
| 112 |
+
}
|