Upload DebertaV2ForSequenceClassification
Browse files- config.json +48 -0
- model.safetensors +3 -0
config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/mnt/hdd/projects/gca_tab_nlp/bert-finetuned-your-dataset/checkpoint-165",
|
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": "LABEL_0",
|
12 |
+
"1": "LABEL_1",
|
13 |
+
"2": "LABEL_2",
|
14 |
+
"3": "LABEL_3"
|
15 |
+
},
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 3072,
|
18 |
+
"label2id": {
|
19 |
+
"LABEL_0": 0,
|
20 |
+
"LABEL_1": 1,
|
21 |
+
"LABEL_2": 2,
|
22 |
+
"LABEL_3": 3
|
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": 6,
|
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 |
+
"problem_type": "multi_label_classification",
|
42 |
+
"relative_attention": true,
|
43 |
+
"share_att_key": true,
|
44 |
+
"torch_dtype": "float32",
|
45 |
+
"transformers_version": "4.36.0",
|
46 |
+
"type_vocab_size": 0,
|
47 |
+
"vocab_size": 128100
|
48 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58d4751575fc5d71b4b18365381dcf2f27f414c9d23fe9b22c90a65debb11b8c
|
3 |
+
size 567604704
|