Upload BertForSequenceClassification
Browse files- config.json +48 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "cointegrated/rubert-tiny2",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"emb_size": 312,
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 312,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "\u041a\u043e\u043d\u0441\u0443\u043b\u044c\u0442\u0430\u0446\u0438\u044f \u041a\u0426",
|
| 15 |
+
"1": "\u041a\u043e\u043c\u043f\u0435\u0442\u0435\u043d\u0442\u043d\u043e\u0441\u0442\u044c \u043f\u0440\u043e\u0434\u0430\u0432\u0446\u043e\u0432/ \u043a\u043e\u043d\u0441\u0443\u043b\u044c\u0442\u0430\u043d\u0442\u043e\u0432",
|
| 16 |
+
"2": "\u042d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u0430\u044f \u043e\u0447\u0435\u0440\u0435\u0434\u044c",
|
| 17 |
+
"3": "\u0414\u043e\u0441\u0442\u0443\u043f\u043d\u043e\u0441\u0442\u044c \u043f\u0435\u0440\u0441\u043e\u043d\u0430\u043b\u0430 \u0432 \u043c\u0430\u0433\u0430\u0437\u0438\u043d\u0435",
|
| 18 |
+
"4": "\u0412\u0435\u0436\u043b\u0438\u0432\u043e\u0441\u0442\u044c \u0441\u043e\u0442\u0440\u0443\u0434\u043d\u0438\u043a\u043e\u0432 \u043c\u0430\u0433\u0430\u0437\u0438\u043d\u0430",
|
| 19 |
+
"5": "\u041e\u0431\u0441\u043b\u0443\u0436\u0438\u0432\u0430\u043d\u0438\u0435 \u043d\u0430 \u043a\u0430\u0441\u0441\u0435",
|
| 20 |
+
"6": "\u041e\u0431\u0441\u043b\u0443\u0436\u0438\u0432\u0430\u043d\u0438\u0435 \u043f\u0440\u043e\u0434\u0430\u0432\u0446\u0430\u043c\u0438/ \u043a\u043e\u043d\u0441\u0443\u043b\u044c\u0442\u0430\u043d\u0442\u0430\u043c\u0438",
|
| 21 |
+
"7": "\u0412\u0440\u0435\u043c\u044f \u043e\u0436\u0438\u0434\u0430\u043d\u0438\u044f \u0443 \u043a\u0430\u0441\u0441\u044b"
|
| 22 |
+
},
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"intermediate_size": 600,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"\u0412\u0435\u0436\u043b\u0438\u0432\u043e\u0441\u0442\u044c \u0441\u043e\u0442\u0440\u0443\u0434\u043d\u0438\u043a\u043e\u0432 \u043c\u0430\u0433\u0430\u0437\u0438\u043d\u0430": 4,
|
| 27 |
+
"\u0412\u0440\u0435\u043c\u044f \u043e\u0436\u0438\u0434\u0430\u043d\u0438\u044f \u0443 \u043a\u0430\u0441\u0441\u044b": 7,
|
| 28 |
+
"\u0414\u043e\u0441\u0442\u0443\u043f\u043d\u043e\u0441\u0442\u044c \u043f\u0435\u0440\u0441\u043e\u043d\u0430\u043b\u0430 \u0432 \u043c\u0430\u0433\u0430\u0437\u0438\u043d\u0435": 3,
|
| 29 |
+
"\u041a\u043e\u043c\u043f\u0435\u0442\u0435\u043d\u0442\u043d\u043e\u0441\u0442\u044c \u043f\u0440\u043e\u0434\u0430\u0432\u0446\u043e\u0432/ \u043a\u043e\u043d\u0441\u0443\u043b\u044c\u0442\u0430\u043d\u0442\u043e\u0432": 1,
|
| 30 |
+
"\u041a\u043e\u043d\u0441\u0443\u043b\u044c\u0442\u0430\u0446\u0438\u044f \u041a\u0426": 0,
|
| 31 |
+
"\u041e\u0431\u0441\u043b\u0443\u0436\u0438\u0432\u0430\u043d\u0438\u0435 \u043d\u0430 \u043a\u0430\u0441\u0441\u0435": 5,
|
| 32 |
+
"\u041e\u0431\u0441\u043b\u0443\u0436\u0438\u0432\u0430\u043d\u0438\u0435 \u043f\u0440\u043e\u0434\u0430\u0432\u0446\u0430\u043c\u0438/ \u043a\u043e\u043d\u0441\u0443\u043b\u044c\u0442\u0430\u043d\u0442\u0430\u043c\u0438": 6,
|
| 33 |
+
"\u042d\u043b\u0435\u043a\u0442\u0440\u043e\u043d\u043d\u0430\u044f \u043e\u0447\u0435\u0440\u0435\u0434\u044c": 2
|
| 34 |
+
},
|
| 35 |
+
"layer_norm_eps": 1e-12,
|
| 36 |
+
"max_position_embeddings": 2048,
|
| 37 |
+
"model_type": "bert",
|
| 38 |
+
"num_attention_heads": 12,
|
| 39 |
+
"num_hidden_layers": 3,
|
| 40 |
+
"pad_token_id": 0,
|
| 41 |
+
"position_embedding_type": "absolute",
|
| 42 |
+
"problem_type": "single_label_classification",
|
| 43 |
+
"torch_dtype": "float32",
|
| 44 |
+
"transformers_version": "4.36.0",
|
| 45 |
+
"type_vocab_size": 2,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 83828
|
| 48 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf2d3277b81912d1301ce18fb3d5fb473e686fc7c1236f52cad6c87efd26cc15
|
| 3 |
+
size 116791648
|