Upload BertForSequenceClassification
Browse files- config.json +17 -18
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,26 +1,22 @@
|
|
1 |
{
|
2 |
"_name_or_path": "ft-models",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0,
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"embedding_size": 128,
|
11 |
-
"eos_token_id": 3,
|
12 |
-
"gap_size": 0,
|
13 |
"hidden_act": "gelu",
|
14 |
-
"hidden_dropout_prob": 0,
|
15 |
-
"hidden_size":
|
16 |
"id2label": {
|
17 |
"0": "LABEL_0",
|
18 |
"1": "LABEL_1",
|
19 |
"2": "LABEL_2"
|
20 |
},
|
21 |
"initializer_range": 0.02,
|
22 |
-
"
|
23 |
-
"intermediate_size": 1248,
|
24 |
"label2id": {
|
25 |
"LABEL_0": 0,
|
26 |
"LABEL_1": 1,
|
@@ -28,17 +24,20 @@
|
|
28 |
},
|
29 |
"layer_norm_eps": 1e-12,
|
30 |
"max_position_embeddings": 512,
|
31 |
-
"model_type": "
|
32 |
-
"net_structure_type": 0,
|
33 |
"num_attention_heads": 12,
|
34 |
-
"
|
35 |
-
"num_hidden_layers": 4,
|
36 |
-
"num_memory_blocks": 0,
|
37 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
38 |
"position_embedding_type": "absolute",
|
39 |
"problem_type": "single_label_classification",
|
40 |
"torch_dtype": "float32",
|
41 |
"transformers_version": "4.26.0",
|
42 |
"type_vocab_size": 2,
|
43 |
-
"
|
|
|
44 |
}
|
|
|
1 |
{
|
2 |
"_name_or_path": "ft-models",
|
3 |
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"directionality": "bidi",
|
9 |
+
"gradient_checkpointing": false,
|
|
|
|
|
|
|
10 |
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0",
|
15 |
"1": "LABEL_1",
|
16 |
"2": "LABEL_2"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
|
|
20 |
"label2id": {
|
21 |
"LABEL_0": 0,
|
22 |
"LABEL_1": 1,
|
|
|
24 |
},
|
25 |
"layer_norm_eps": 1e-12,
|
26 |
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
|
|
28 |
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
|
|
|
|
30 |
"pad_token_id": 0,
|
31 |
+
"pooler_fc_size": 768,
|
32 |
+
"pooler_num_attention_heads": 12,
|
33 |
+
"pooler_num_fc_layers": 3,
|
34 |
+
"pooler_size_per_head": 128,
|
35 |
+
"pooler_type": "first_token_transform",
|
36 |
"position_embedding_type": "absolute",
|
37 |
"problem_type": "single_label_classification",
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.26.0",
|
40 |
"type_vocab_size": 2,
|
41 |
+
"use_cache": true,
|
42 |
+
"vocab_size": 48871
|
43 |
}
|
pytorch_model.bin
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 sha256:9f00cb3b3655d3dc1cf0209359bc23571c3abe91f05e4e8f2d3892f980cb2bfb
|
3 |
+
size 494376309
|