Rename config (1).json to config.json
Browse files- config (1).json +0 -22
- config.json +42 -0
config (1).json
DELETED
|
@@ -1,22 +0,0 @@
|
|
| 1 |
-
{"architectures": [
|
| 2 |
-
"BertForMaskedLM"
|
| 3 |
-
],
|
| 4 |
-
"attention_probs_dropout_prob": 0.1,
|
| 5 |
-
"directionality": "bidi",
|
| 6 |
-
"hidden_act": "gelu",
|
| 7 |
-
"hidden_dropout_prob": 0.1,
|
| 8 |
-
"hidden_size": 768,
|
| 9 |
-
"initializer_range": 0.02,
|
| 10 |
-
"intermediate_size": 3072,
|
| 11 |
-
"max_position_embeddings": 512,
|
| 12 |
-
"num_attention_heads": 12,
|
| 13 |
-
"num_hidden_layers": 12,
|
| 14 |
-
"pooler_fc_size": 768,
|
| 15 |
-
"pooler_num_attention_heads": 12,
|
| 16 |
-
"pooler_num_fc_layers": 3,
|
| 17 |
-
"pooler_size_per_head": 128,
|
| 18 |
-
"pooler_type": "first_token_transform",
|
| 19 |
-
"type_vocab_size": 2,
|
| 20 |
-
"vocab_size": 120138,
|
| 21 |
-
"model_type": "bert"
|
| 22 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
config.json
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
_name_or_path: "ai-forever/ruBert-large",
|
| 3 |
+
architectures: [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
attention_probs_dropout_prob: 0.1,
|
| 7 |
+
classifier_dropout: null,
|
| 8 |
+
directionality: "bidi",
|
| 9 |
+
hidden_act: "gelu",
|
| 10 |
+
hidden_dropout_prob: 0.1,
|
| 11 |
+
hidden_size: 1024,
|
| 12 |
+
id2label: {
|
| 13 |
+
0: "LABEL_0",
|
| 14 |
+
1: "LABEL_1",
|
| 15 |
+
2: "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
initializer_range: 0.02,
|
| 18 |
+
intermediate_size: 4096,
|
| 19 |
+
label2id: {
|
| 20 |
+
LABEL_0: 0,
|
| 21 |
+
LABEL_1: 1,
|
| 22 |
+
LABEL_2: 2
|
| 23 |
+
},
|
| 24 |
+
layer_norm_eps: 1e-12,
|
| 25 |
+
max_position_embeddings: 512,
|
| 26 |
+
model_type: "bert",
|
| 27 |
+
num_attention_heads: 16,
|
| 28 |
+
num_hidden_layers: 24,
|
| 29 |
+
pad_token_id: 0,
|
| 30 |
+
pooler_fc_size: 768,
|
| 31 |
+
pooler_num_attention_heads: 12,
|
| 32 |
+
pooler_num_fc_layers: 3,
|
| 33 |
+
pooler_size_per_head: 128,
|
| 34 |
+
pooler_type: "first_token_transform",
|
| 35 |
+
position_embedding_type: "absolute",
|
| 36 |
+
problem_type: "single_label_classification",
|
| 37 |
+
torch_dtype: "float32",
|
| 38 |
+
transformers_version: "4.45.1",
|
| 39 |
+
type_vocab_size: 2,
|
| 40 |
+
use_cache: true,
|
| 41 |
+
vocab_size: 120138
|
| 42 |
+
}
|