truongnguyenxuanvinh
commited on
Upload RobertaForSequenceClassification
Browse files- config.json +8 -9
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
@@ -9,7 +9,7 @@
|
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
-
"hidden_size":
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0",
|
15 |
"1": "LABEL_1",
|
@@ -18,7 +18,7 @@
|
|
18 |
"4": "LABEL_4"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
-
"intermediate_size":
|
22 |
"label2id": {
|
23 |
"LABEL_0": 0,
|
24 |
"LABEL_1": 1,
|
@@ -28,10 +28,9 @@
|
|
28 |
},
|
29 |
"layer_norm_eps": 1e-05,
|
30 |
"max_position_embeddings": 514,
|
31 |
-
"model_type": "
|
32 |
-
"num_attention_heads":
|
33 |
-
"num_hidden_layers":
|
34 |
-
"output_past": true,
|
35 |
"pad_token_id": 1,
|
36 |
"position_embedding_type": "absolute",
|
37 |
"problem_type": "multi_label_classification",
|
@@ -39,5 +38,5 @@
|
|
39 |
"transformers_version": "4.44.2",
|
40 |
"type_vocab_size": 1,
|
41 |
"use_cache": true,
|
42 |
-
"vocab_size":
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "roberta-large",
|
3 |
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"bos_token_id": 0,
|
|
|
9 |
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
"id2label": {
|
14 |
"0": "LABEL_0",
|
15 |
"1": "LABEL_1",
|
|
|
18 |
"4": "LABEL_4"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 4096,
|
22 |
"label2id": {
|
23 |
"LABEL_0": 0,
|
24 |
"LABEL_1": 1,
|
|
|
28 |
},
|
29 |
"layer_norm_eps": 1e-05,
|
30 |
"max_position_embeddings": 514,
|
31 |
+
"model_type": "roberta",
|
32 |
+
"num_attention_heads": 16,
|
33 |
+
"num_hidden_layers": 24,
|
|
|
34 |
"pad_token_id": 1,
|
35 |
"position_embedding_type": "absolute",
|
36 |
"problem_type": "multi_label_classification",
|
|
|
38 |
"transformers_version": "4.44.2",
|
39 |
"type_vocab_size": 1,
|
40 |
"use_cache": true,
|
41 |
+
"vocab_size": 50265
|
42 |
}
|
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:c720f359a3dd64508669bfb3aa9da46bb1273cd38d364a191780a0002766dac3
|
3 |
+
size 1421507716
|