debajyotidatta
commited on
Commit
•
7cc9ede
1
Parent(s):
795a492
Upload DebertaV2ForSequenceClassification
Browse files- config.json +29 -22
- pytorch_model.bin +2 -2
config.json
CHANGED
@@ -1,40 +1,47 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
-
"bos_token_id": 0,
|
8 |
-
"classifier_dropout": null,
|
9 |
-
"eos_token_id": 2,
|
10 |
"hidden_act": "gelu",
|
11 |
"hidden_dropout_prob": 0.1,
|
12 |
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
-
"0": "
|
15 |
-
"1": "
|
16 |
-
"2": "
|
17 |
-
"3": "
|
18 |
},
|
19 |
"initializer_range": 0.02,
|
20 |
"intermediate_size": 3072,
|
21 |
"label2id": {
|
22 |
-
"expository":
|
23 |
-
"other":
|
24 |
-
"probing_exploring":
|
25 |
-
"procedural":
|
26 |
},
|
27 |
-
"layer_norm_eps": 1e-
|
28 |
-
"max_position_embeddings":
|
29 |
-
"
|
|
|
|
|
30 |
"num_attention_heads": 12,
|
31 |
"num_hidden_layers": 12,
|
32 |
-
"pad_token_id":
|
33 |
-
"
|
34 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
35 |
"torch_dtype": "float32",
|
36 |
"transformers_version": "4.25.1",
|
37 |
-
"type_vocab_size":
|
38 |
-
"
|
39 |
-
"vocab_size": 50265
|
40 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
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 |
"id2label": {
|
11 |
+
"0": "probing_exploring",
|
12 |
+
"1": "expository",
|
13 |
+
"2": "procedural",
|
14 |
+
"3": "other"
|
15 |
},
|
16 |
"initializer_range": 0.02,
|
17 |
"intermediate_size": 3072,
|
18 |
"label2id": {
|
19 |
+
"expository": 1,
|
20 |
+
"other": 3,
|
21 |
+
"probing_exploring": 0,
|
22 |
+
"procedural": 2
|
23 |
},
|
24 |
+
"layer_norm_eps": 1e-07,
|
25 |
+
"max_position_embeddings": 512,
|
26 |
+
"max_relative_positions": -1,
|
27 |
+
"model_type": "deberta-v2",
|
28 |
+
"norm_rel_ebd": "layer_norm",
|
29 |
"num_attention_heads": 12,
|
30 |
"num_hidden_layers": 12,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"pooler_dropout": 0,
|
33 |
+
"pooler_hidden_act": "gelu",
|
34 |
+
"pooler_hidden_size": 768,
|
35 |
+
"pos_att_type": [
|
36 |
+
"p2c",
|
37 |
+
"c2p"
|
38 |
+
],
|
39 |
+
"position_biased_input": false,
|
40 |
+
"position_buckets": 256,
|
41 |
+
"relative_attention": true,
|
42 |
+
"share_att_key": true,
|
43 |
"torch_dtype": "float32",
|
44 |
"transformers_version": "4.25.1",
|
45 |
+
"type_vocab_size": 0,
|
46 |
+
"vocab_size": 128100
|
|
|
47 |
}
|
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:ada9e61ab6f9b23bdc8e70551745f33548b4def15ef618be45725090cb0f32d7
|
3 |
+
size 737774905
|