Update config.json
Browse files- config.json +4 -8
config.json
CHANGED
|
@@ -3,30 +3,26 @@
|
|
| 3 |
"RobertaForMaskedLM"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 6 |
"directionality": "bidi",
|
| 7 |
-
"
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
"hidden_size": 768,
|
| 11 |
"initializer_range": 0.02,
|
| 12 |
"intermediate_size": 3072,
|
| 13 |
-
"is_decoder": false,
|
| 14 |
"layer_norm_eps": 1e-12,
|
| 15 |
"max_position_embeddings": 512,
|
|
|
|
| 16 |
"num_attention_heads": 12,
|
| 17 |
"num_hidden_layers": 12,
|
| 18 |
-
"num_labels": 2,
|
| 19 |
-
"output_attentions": false,
|
| 20 |
-
"output_hidden_states": false,
|
| 21 |
"output_past": true,
|
|
|
|
| 22 |
"pooler_fc_size": 768,
|
| 23 |
"pooler_num_attention_heads": 12,
|
| 24 |
"pooler_num_fc_layers": 3,
|
| 25 |
"pooler_size_per_head": 128,
|
| 26 |
"pooler_type": "first_token_transform",
|
| 27 |
-
"pruned_heads": {},
|
| 28 |
-
"torchscript": false,
|
| 29 |
"type_vocab_size": 2,
|
| 30 |
-
"use_bfloat16": false,
|
| 31 |
"vocab_size": 21128
|
| 32 |
}
|
| 3 |
"RobertaForMaskedLM"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
"directionality": "bidi",
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
"intermediate_size": 3072,
|
|
|
|
| 14 |
"layer_norm_eps": 1e-12,
|
| 15 |
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "roberta",
|
| 17 |
"num_attention_heads": 12,
|
| 18 |
"num_hidden_layers": 12,
|
|
|
|
|
|
|
|
|
|
| 19 |
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
"pooler_fc_size": 768,
|
| 22 |
"pooler_num_attention_heads": 12,
|
| 23 |
"pooler_num_fc_layers": 3,
|
| 24 |
"pooler_size_per_head": 128,
|
| 25 |
"pooler_type": "first_token_transform",
|
|
|
|
|
|
|
| 26 |
"type_vocab_size": 2,
|
|
|
|
| 27 |
"vocab_size": 21128
|
| 28 |
}
|