Upload BertForTokenClassification
Browse files- config.json +104 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "rmihaylov/bert-base-bg",
|
| 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": "B-CMA",
|
| 44 |
+
"2": "I-CMA",
|
| 45 |
+
"3": "B-DOT",
|
| 46 |
+
"4": "I-DOT",
|
| 47 |
+
"5": "B-EXC",
|
| 48 |
+
"6": "I-EXC",
|
| 49 |
+
"7": "B-QUE",
|
| 50 |
+
"8": "I-QUE",
|
| 51 |
+
"9": "B-COL",
|
| 52 |
+
"10": "I-COL",
|
| 53 |
+
"11": "B-QUO1",
|
| 54 |
+
"12": "I-QUO1",
|
| 55 |
+
"13": "B-QUO2",
|
| 56 |
+
"14": "I-QUO2",
|
| 57 |
+
"15": "B-QUO3",
|
| 58 |
+
"16": "I-QUO3"
|
| 59 |
+
},
|
| 60 |
+
"init_optimizer_variables": true,
|
| 61 |
+
"initializer_range": 0.02,
|
| 62 |
+
"intermediate_size": 3072,
|
| 63 |
+
"label2id": {
|
| 64 |
+
"B-CMA": 1,
|
| 65 |
+
"B-COL": 9,
|
| 66 |
+
"B-DOT": 3,
|
| 67 |
+
"B-EXC": 5,
|
| 68 |
+
"B-QUE": 7,
|
| 69 |
+
"B-QUO1": 11,
|
| 70 |
+
"B-QUO2": 13,
|
| 71 |
+
"B-QUO3": 15,
|
| 72 |
+
"I-CMA": 2,
|
| 73 |
+
"I-COL": 10,
|
| 74 |
+
"I-DOT": 4,
|
| 75 |
+
"I-EXC": 6,
|
| 76 |
+
"I-QUE": 8,
|
| 77 |
+
"I-QUO1": 12,
|
| 78 |
+
"I-QUO2": 14,
|
| 79 |
+
"I-QUO3": 16,
|
| 80 |
+
"O": 0
|
| 81 |
+
},
|
| 82 |
+
"layer_norm_eps": 1e-12,
|
| 83 |
+
"max_position_embeddings": 512,
|
| 84 |
+
"model_type": "bert",
|
| 85 |
+
"num_attention_heads": 12,
|
| 86 |
+
"num_hidden_layers": 12,
|
| 87 |
+
"pad_token_id": 0,
|
| 88 |
+
"pooler_fc_size": 768,
|
| 89 |
+
"pooler_num_attention_heads": 12,
|
| 90 |
+
"pooler_num_fc_layers": 3,
|
| 91 |
+
"pooler_size_per_head": 128,
|
| 92 |
+
"pooler_trainable": true,
|
| 93 |
+
"pooler_type": "first_token_transform",
|
| 94 |
+
"position_embedding_type": "absolute",
|
| 95 |
+
"position_embeddings_trainable": true,
|
| 96 |
+
"token_type_trainable": true,
|
| 97 |
+
"torch_dtype": "float32",
|
| 98 |
+
"transformer_trainable": true,
|
| 99 |
+
"transformers_version": "4.36.0",
|
| 100 |
+
"type_vocab_size": 2,
|
| 101 |
+
"use_cache": true,
|
| 102 |
+
"vocab_size": 119549,
|
| 103 |
+
"word_embeddings_trainable": true
|
| 104 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37cd3b28108658077d6e5a2fcef724a132b99d014a9f00278d9594b97d2b2bc4
|
| 3 |
+
size 709133188
|