anismk commited on
Commit
00337a7
·
verified ·
1 Parent(s): b15cd9d

Upload DebertaV2ForSequenceClassification

Browse files
Files changed (2) hide show
  1. config.json +83 -0
  2. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-large",
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": 1024,
10
+ "id2label": {
11
+ "0": "LABEL_0",
12
+ "1": "LABEL_1",
13
+ "2": "LABEL_2",
14
+ "3": "LABEL_3",
15
+ "4": "LABEL_4",
16
+ "5": "LABEL_5",
17
+ "6": "LABEL_6",
18
+ "7": "LABEL_7",
19
+ "8": "LABEL_8",
20
+ "9": "LABEL_9",
21
+ "10": "LABEL_10",
22
+ "11": "LABEL_11",
23
+ "12": "LABEL_12",
24
+ "13": "LABEL_13"
25
+ },
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": 4096,
28
+ "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_11": 11,
33
+ "LABEL_12": 12,
34
+ "LABEL_13": 13,
35
+ "LABEL_2": 2,
36
+ "LABEL_3": 3,
37
+ "LABEL_4": 4,
38
+ "LABEL_5": 5,
39
+ "LABEL_6": 6,
40
+ "LABEL_7": 7,
41
+ "LABEL_8": 8,
42
+ "LABEL_9": 9
43
+ },
44
+ "layer_norm_eps": 1e-07,
45
+ "max_position_embeddings": 512,
46
+ "max_relative_positions": -1,
47
+ "model_type": "deberta-v2",
48
+ "norm_rel_ebd": "layer_norm",
49
+ "num_attention_heads": 16,
50
+ "num_hidden_layers": 24,
51
+ "pad_token_id": 2,
52
+ "pooler_dropout": 0,
53
+ "pooler_hidden_act": "gelu",
54
+ "pooler_hidden_size": 1024,
55
+ "pos_att_type": [
56
+ "p2c",
57
+ "c2p"
58
+ ],
59
+ "position_biased_input": false,
60
+ "position_buckets": 256,
61
+ "problem_type": "multi_label_classification",
62
+ "quantization_config": {
63
+ "_load_in_4bit": true,
64
+ "_load_in_8bit": false,
65
+ "bnb_4bit_compute_dtype": "bfloat16",
66
+ "bnb_4bit_quant_storage": "uint8",
67
+ "bnb_4bit_quant_type": "nf4",
68
+ "bnb_4bit_use_double_quant": true,
69
+ "llm_int8_enable_fp32_cpu_offload": false,
70
+ "llm_int8_has_fp16_weight": false,
71
+ "llm_int8_skip_modules": null,
72
+ "llm_int8_threshold": 6.0,
73
+ "load_in_4bit": true,
74
+ "load_in_8bit": false,
75
+ "quant_method": "bitsandbytes"
76
+ },
77
+ "relative_attention": true,
78
+ "share_att_key": true,
79
+ "torch_dtype": "float32",
80
+ "transformers_version": "4.46.2",
81
+ "type_vocab_size": 0,
82
+ "vocab_size": 128100
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51abc292c827974aaf92d9c07109ac652bcb65277e05016c01658e8833d7e9b
3
+ size 684809457