Upload DebertaV2ForSequenceClassification
Browse files- README.md +4 -4
- config.json +35 -35
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
library_name: transformers
|
| 3 |
-
language:
|
| 4 |
-
- ru
|
| 5 |
base_model:
|
| 6 |
- belyakoff/deberta_v2_nli
|
|
|
|
|
|
|
|
|
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
-
---
|
|
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
| 2 |
base_model:
|
| 3 |
- belyakoff/deberta_v2_nli
|
| 4 |
+
language:
|
| 5 |
+
- ru
|
| 6 |
+
library_name: transformers
|
| 7 |
pipeline_tag: text-classification
|
| 8 |
+
---
|
config.json
CHANGED
|
@@ -1,35 +1,35 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_name_or_path": "checkpoint-618",
|
| 3 |
-
"architectures": [
|
| 4 |
-
"DebertaV2ForSequenceClassification"
|
| 5 |
-
],
|
| 6 |
-
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"hidden_act": "gelu",
|
| 8 |
-
"hidden_dropout_prob": 0.1,
|
| 9 |
-
"hidden_size": 768,
|
| 10 |
-
"initializer_range": 0.02,
|
| 11 |
-
"intermediate_size": 3072,
|
| 12 |
-
"layer_norm_eps": 1e-07,
|
| 13 |
-
"max_position_embeddings": 512,
|
| 14 |
-
"max_relative_positions": -1,
|
| 15 |
-
"model_type": "deberta-v2",
|
| 16 |
-
"norm_rel_ebd": "layer_norm",
|
| 17 |
-
"num_attention_heads": 12,
|
| 18 |
-
"num_hidden_layers": 12,
|
| 19 |
-
"pad_token_id": 0,
|
| 20 |
-
"pooler_dropout": 0,
|
| 21 |
-
"pooler_hidden_act": "gelu",
|
| 22 |
-
"pooler_hidden_size": 768,
|
| 23 |
-
"pos_att_type": [
|
| 24 |
-
"p2c",
|
| 25 |
-
"c2p"
|
| 26 |
-
],
|
| 27 |
-
"position_biased_input": false,
|
| 28 |
-
"position_buckets": 256,
|
| 29 |
-
"relative_attention": true,
|
| 30 |
-
"share_att_key": true,
|
| 31 |
-
"torch_dtype": "float32",
|
| 32 |
-
"transformers_version": "4.45.2",
|
| 33 |
-
"type_vocab_size": 0,
|
| 34 |
-
"vocab_size": 251000
|
| 35 |
-
}
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "C:\\Users\\admin\\py\\mvp_cls_puzzle\\train_cls_personal\\error_support_model\\checkpoint-618",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DebertaV2ForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"hidden_act": "gelu",
|
| 8 |
+
"hidden_dropout_prob": 0.1,
|
| 9 |
+
"hidden_size": 768,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 3072,
|
| 12 |
+
"layer_norm_eps": 1e-07,
|
| 13 |
+
"max_position_embeddings": 512,
|
| 14 |
+
"max_relative_positions": -1,
|
| 15 |
+
"model_type": "deberta-v2",
|
| 16 |
+
"norm_rel_ebd": "layer_norm",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"pad_token_id": 0,
|
| 20 |
+
"pooler_dropout": 0,
|
| 21 |
+
"pooler_hidden_act": "gelu",
|
| 22 |
+
"pooler_hidden_size": 768,
|
| 23 |
+
"pos_att_type": [
|
| 24 |
+
"p2c",
|
| 25 |
+
"c2p"
|
| 26 |
+
],
|
| 27 |
+
"position_biased_input": false,
|
| 28 |
+
"position_buckets": 256,
|
| 29 |
+
"relative_attention": true,
|
| 30 |
+
"share_att_key": true,
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.45.2",
|
| 33 |
+
"type_vocab_size": 0,
|
| 34 |
+
"vocab_size": 251000
|
| 35 |
+
}
|