add model
Browse files- config.json +96 -0
- pytorch_model.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,96 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/content/drive/MyDrive/ColabModels/MBERT_NER_THESEUS/pytorch_model/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"by_layer_is_trainable": {
|
| 8 |
+
"0": true,
|
| 9 |
+
"1": true,
|
| 10 |
+
"10": true,
|
| 11 |
+
"11": true,
|
| 12 |
+
"12": true,
|
| 13 |
+
"13": true,
|
| 14 |
+
"14": true,
|
| 15 |
+
"15": true,
|
| 16 |
+
"16": true,
|
| 17 |
+
"17": true,
|
| 18 |
+
"18": true,
|
| 19 |
+
"19": true,
|
| 20 |
+
"2": true,
|
| 21 |
+
"20": true,
|
| 22 |
+
"21": true,
|
| 23 |
+
"22": true,
|
| 24 |
+
"23": true,
|
| 25 |
+
"3": true,
|
| 26 |
+
"4": true,
|
| 27 |
+
"5": true,
|
| 28 |
+
"6": true,
|
| 29 |
+
"7": true,
|
| 30 |
+
"8": true,
|
| 31 |
+
"9": true
|
| 32 |
+
},
|
| 33 |
+
"classifier_dropout": null,
|
| 34 |
+
"cls_trainable": true,
|
| 35 |
+
"directionality": "bidi",
|
| 36 |
+
"embedding_postprocessor_trainable": true,
|
| 37 |
+
"embeddings_layer_norm_trainable": true,
|
| 38 |
+
"hidden_act": "gelu",
|
| 39 |
+
"hidden_dropout_prob": 0.1,
|
| 40 |
+
"hidden_size": 768,
|
| 41 |
+
"id2label": {
|
| 42 |
+
"0": "O",
|
| 43 |
+
"1": "[PAD]",
|
| 44 |
+
"2": "[SEP]",
|
| 45 |
+
"3": "B-PRO",
|
| 46 |
+
"4": "I-PRO",
|
| 47 |
+
"5": "B-PER",
|
| 48 |
+
"6": "I-PER",
|
| 49 |
+
"7": "B-ORG",
|
| 50 |
+
"8": "I-ORG",
|
| 51 |
+
"9": "B-LOC",
|
| 52 |
+
"10": "I-LOC",
|
| 53 |
+
"11": "B-EVT",
|
| 54 |
+
"12": "I-EVT"
|
| 55 |
+
},
|
| 56 |
+
"init_optimizer_variables": true,
|
| 57 |
+
"initializer_range": 0.02,
|
| 58 |
+
"intermediate_size": 3072,
|
| 59 |
+
"label2id": {
|
| 60 |
+
"B-EVT": 11,
|
| 61 |
+
"B-LOC": 9,
|
| 62 |
+
"B-ORG": 7,
|
| 63 |
+
"B-PER": 5,
|
| 64 |
+
"B-PRO": 3,
|
| 65 |
+
"I-EVT": 12,
|
| 66 |
+
"I-LOC": 10,
|
| 67 |
+
"I-ORG": 8,
|
| 68 |
+
"I-PER": 6,
|
| 69 |
+
"I-PRO": 4,
|
| 70 |
+
"O": 0,
|
| 71 |
+
"[PAD]": 1,
|
| 72 |
+
"[SEP]": 2
|
| 73 |
+
},
|
| 74 |
+
"layer_norm_eps": 1e-12,
|
| 75 |
+
"max_position_embeddings": 512,
|
| 76 |
+
"model_type": "bert",
|
| 77 |
+
"num_attention_heads": 12,
|
| 78 |
+
"num_hidden_layers": 6,
|
| 79 |
+
"pad_token_id": 0,
|
| 80 |
+
"pooler_fc_size": 768,
|
| 81 |
+
"pooler_num_attention_heads": 12,
|
| 82 |
+
"pooler_num_fc_layers": 3,
|
| 83 |
+
"pooler_size_per_head": 128,
|
| 84 |
+
"pooler_trainable": true,
|
| 85 |
+
"pooler_type": "first_token_transform",
|
| 86 |
+
"position_embedding_type": "absolute",
|
| 87 |
+
"position_embeddings_trainable": true,
|
| 88 |
+
"token_type_trainable": true,
|
| 89 |
+
"torch_dtype": "float32",
|
| 90 |
+
"transformer_trainable": true,
|
| 91 |
+
"transformers_version": "4.18.0",
|
| 92 |
+
"type_vocab_size": 2,
|
| 93 |
+
"use_cache": true,
|
| 94 |
+
"vocab_size": 119547,
|
| 95 |
+
"word_embeddings_trainable": true
|
| 96 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:135b66bd60a7fb30ab9eef7fb41976455f9fbb006a754ff0592e142221f45f38
|
| 3 |
+
size 539018929
|