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 +83 -83
config.json
CHANGED
|
@@ -8,96 +8,96 @@
|
|
| 8 |
"hidden_dropout_prob": 0.1,
|
| 9 |
"hidden_size": 128,
|
| 10 |
"id2label": {
|
| 11 |
-
"0": "
|
| 12 |
-
"1": "
|
| 13 |
-
"2": "
|
| 14 |
-
"3": "
|
| 15 |
-
"4": "
|
| 16 |
-
"5": "
|
| 17 |
-
"6": "
|
| 18 |
-
"7": "
|
| 19 |
-
"8": "
|
| 20 |
-
"9": "
|
| 21 |
-
"10": "
|
| 22 |
-
"11": "
|
| 23 |
-
"12": "
|
| 24 |
-
"13": "
|
| 25 |
-
"14": "
|
| 26 |
-
"15": "
|
| 27 |
-
"16": "
|
| 28 |
-
"17": "
|
| 29 |
-
"18": "
|
| 30 |
-
"19": "
|
| 31 |
-
"20": "
|
| 32 |
-
"21": "
|
| 33 |
-
"22": "
|
| 34 |
-
"23": "
|
| 35 |
-
"24": "
|
| 36 |
-
"25": "
|
| 37 |
-
"26": "
|
| 38 |
-
"27": "
|
| 39 |
-
"28": "
|
| 40 |
-
"29": "
|
| 41 |
-
"30": "
|
| 42 |
-
"31": "
|
| 43 |
-
"32": "
|
| 44 |
-
"33": "
|
| 45 |
-
"34": "
|
| 46 |
-
"35": "
|
| 47 |
-
"36": "
|
| 48 |
-
"37": "
|
| 49 |
-
"38": "
|
| 50 |
-
"39": "
|
| 51 |
-
"40": "
|
| 52 |
"41": "LABEL_41",
|
| 53 |
"42": "LABEL_42"
|
| 54 |
},
|
| 55 |
"initializer_range": 0.02,
|
| 56 |
"intermediate_size": 512,
|
| 57 |
"label2id": {
|
| 58 |
-
"
|
| 59 |
-
"
|
| 60 |
-
"
|
| 61 |
-
"
|
| 62 |
-
"
|
| 63 |
-
"
|
| 64 |
-
"
|
| 65 |
-
"
|
| 66 |
-
"
|
| 67 |
-
"
|
| 68 |
-
"
|
| 69 |
-
"
|
| 70 |
-
"
|
| 71 |
-
"
|
| 72 |
-
"
|
| 73 |
-
"
|
| 74 |
-
"
|
| 75 |
-
"
|
| 76 |
-
"
|
| 77 |
-
"
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"
|
| 85 |
-
"
|
| 86 |
-
"
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
"
|
| 91 |
-
"
|
| 92 |
-
"
|
| 93 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 94 |
"LABEL_41": 41,
|
| 95 |
-
"LABEL_42": 42
|
| 96 |
-
"LABEL_5": 5,
|
| 97 |
-
"LABEL_6": 6,
|
| 98 |
-
"LABEL_7": 7,
|
| 99 |
-
"LABEL_8": 8,
|
| 100 |
-
"LABEL_9": 9
|
| 101 |
},
|
| 102 |
"layer_norm_eps": 1e-12,
|
| 103 |
"max_position_embeddings": 512,
|
|
|
|
| 8 |
"hidden_dropout_prob": 0.1,
|
| 9 |
"hidden_size": 128,
|
| 10 |
"id2label": {
|
| 11 |
+
"0": "O",
|
| 12 |
+
"1": "B-fromloc.city_name",
|
| 13 |
+
"2": "I-fromloc.city_name",
|
| 14 |
+
"3": "B-fromloc.city_name",
|
| 15 |
+
"4": "I-fromloc.state_name",
|
| 16 |
+
"5": "B-fromloc.country_name",
|
| 17 |
+
"6": "I-fromloc.country_name",
|
| 18 |
+
"7": "B-fromloc.address",
|
| 19 |
+
"8": "I-fromloc.address",
|
| 20 |
+
"9": "B-toloc.city_name",
|
| 21 |
+
"10": "O",
|
| 22 |
+
"11": "B-toloc.state_name",
|
| 23 |
+
"12": "I-toloc.state_name",
|
| 24 |
+
"13": "B-toloc.country_name",
|
| 25 |
+
"14": "I-toloc.country_name",
|
| 26 |
+
"15": "B-toloc.address",
|
| 27 |
+
"16": "I-toloc.address",
|
| 28 |
+
"17": "B-transportation_mode",
|
| 29 |
+
"18": "I-transportation_mode",
|
| 30 |
+
"19": "B-date",
|
| 31 |
+
"20": "I-date",
|
| 32 |
+
"21": "B-time",
|
| 33 |
+
"22": "I-time",
|
| 34 |
+
"23": "B-departure_time",
|
| 35 |
+
"24": "I-departure_time",
|
| 36 |
+
"25": "B-arrival_time",
|
| 37 |
+
"26": "I-arrival_time",
|
| 38 |
+
"27": "B-company_name",
|
| 39 |
+
"28": "I-company_name",
|
| 40 |
+
"29": "B-organization_name",
|
| 41 |
+
"30": "I-organization_name",
|
| 42 |
+
"31": "B-person_name",
|
| 43 |
+
"32": "I-person_name",
|
| 44 |
+
"33": "B-job_title",
|
| 45 |
+
"34": "I-job_title",
|
| 46 |
+
"35": "B-phone_number",
|
| 47 |
+
"36": "I-phone_number",
|
| 48 |
+
"37": "B-email",
|
| 49 |
+
"38": "I-email",
|
| 50 |
+
"39": "B-url",
|
| 51 |
+
"40": "I-url",
|
| 52 |
"41": "LABEL_41",
|
| 53 |
"42": "LABEL_42"
|
| 54 |
},
|
| 55 |
"initializer_range": 0.02,
|
| 56 |
"intermediate_size": 512,
|
| 57 |
"label2id": {
|
| 58 |
+
"O": 0,
|
| 59 |
+
"B-fromloc.city_name": 3,
|
| 60 |
+
"I-fromloc.city_name": 2,
|
| 61 |
+
"B-fromloc.state_name": 4,
|
| 62 |
+
"I-fromloc.state_name": 4,
|
| 63 |
+
"B-fromloc.country_name": 5,
|
| 64 |
+
"I-fromloc.country_name": 6,
|
| 65 |
+
"B-fromloc.address": 7,
|
| 66 |
+
"I-fromloc.address": 8,
|
| 67 |
+
"B-toloc.city_name": 9,
|
| 68 |
+
"I-toloc.city_name": 10,
|
| 69 |
+
"B-toloc.state_name": 11,
|
| 70 |
+
"I-toloc.state_name": 12,
|
| 71 |
+
"B-toloc.country_name": 13,
|
| 72 |
+
"I-toloc.country_name": 14,
|
| 73 |
+
"B-toloc.address": 15,
|
| 74 |
+
"I-toloc.address": 16,
|
| 75 |
+
"B-transportation_mode": 17,
|
| 76 |
+
"I-transportation_mode": 18,
|
| 77 |
+
"B-date": 19,
|
| 78 |
+
"I-date": 20,
|
| 79 |
+
"B-time": 21,
|
| 80 |
+
"I-time": 22,
|
| 81 |
+
"B-departure_time": 23,
|
| 82 |
+
"I-departure_time": 24,
|
| 83 |
+
"B-arrival_time": 25,
|
| 84 |
+
"I-arrival_time": 26,
|
| 85 |
+
"B-company_name": 27,
|
| 86 |
+
"I-company_name": 28,
|
| 87 |
+
"B-organization_name": 29,
|
| 88 |
+
"I-organization_name": 30,
|
| 89 |
+
"B-person_name": 31,
|
| 90 |
+
"I-person_name": 32,
|
| 91 |
+
"B-job_title": 33,
|
| 92 |
+
"I-job_title": 34,
|
| 93 |
+
"B-phone_number": 35,
|
| 94 |
+
"I-phone_number": 36,
|
| 95 |
+
"B-email": 37,
|
| 96 |
+
"I-email": 38,
|
| 97 |
+
"B-url": 39,
|
| 98 |
+
"I-url": 40,
|
| 99 |
"LABEL_41": 41,
|
| 100 |
+
"LABEL_42": 42
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 101 |
},
|
| 102 |
"layer_norm_eps": 1e-12,
|
| 103 |
"max_position_embeddings": 512,
|