Upload BertForSequenceClassification
Browse files- config.json +7 -2
- model.safetensors +2 -2
config.json
CHANGED
|
@@ -5,7 +5,7 @@
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
-
"
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
|
@@ -17,11 +17,16 @@
|
|
| 17 |
"num_attention_heads": 12,
|
| 18 |
"num_hidden_layers": 12,
|
| 19 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
"position_embedding_type": "absolute",
|
| 21 |
"problem_type": "single_label_classification",
|
| 22 |
"torch_dtype": "float32",
|
| 23 |
"transformers_version": "4.47.0",
|
| 24 |
"type_vocab_size": 2,
|
| 25 |
"use_cache": true,
|
| 26 |
-
"vocab_size":
|
| 27 |
}
|
|
|
|
| 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": 768,
|
|
|
|
| 17 |
"num_attention_heads": 12,
|
| 18 |
"num_hidden_layers": 12,
|
| 19 |
"pad_token_id": 0,
|
| 20 |
+
"pooler_fc_size": 768,
|
| 21 |
+
"pooler_num_attention_heads": 12,
|
| 22 |
+
"pooler_num_fc_layers": 3,
|
| 23 |
+
"pooler_size_per_head": 128,
|
| 24 |
+
"pooler_type": "first_token_transform",
|
| 25 |
"position_embedding_type": "absolute",
|
| 26 |
"problem_type": "single_label_classification",
|
| 27 |
"torch_dtype": "float32",
|
| 28 |
"transformers_version": "4.47.0",
|
| 29 |
"type_vocab_size": 2,
|
| 30 |
"use_cache": true,
|
| 31 |
+
"vocab_size": 105879
|
| 32 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc4cd989b3fdfea951ba63c77383862456cfa1fdff9382ed2b56b0e33f4c4eb2
|
| 3 |
+
size 669455360
|