cliang1453 commited on
Commit
7c16cb5
1 Parent(s): 254bdc9
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
all_results.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_exact": 83.59302619388528,
3
+ "eval_f1": 86.40908073158775,
4
+ "eval_total": 11873,
5
+ "eval_HasAns_exact": 80.06072874493927,
6
+ "eval_HasAns_f1": 85.70091355029372,
7
+ "eval_HasAns_total": 5928,
8
+ "eval_NoAns_exact": 87.1152228763667,
9
+ "eval_NoAns_f1": 87.1152228763667,
10
+ "eval_NoAns_total": 5945,
11
+ "eval_best_exact": 83.59302619388528,
12
+ "eval_best_exact_thresh": 0.0,
13
+ "eval_best_f1": 86.40908073158752,
14
+ "eval_best_f1_thresh": 0.0
15
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "cliang1453/deberta-v3-xsmall-squadv2-student-stage1",
3
+ "architectures": [
4
+ "TEDDebertaV2ForQuestionAnswering"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "filter_disabled": false,
8
+ "filter_interval": 1,
9
+ "filter_nonlinear": false,
10
+ "filter_output_dim": 768,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 384,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 1536,
16
+ "layer_norm_eps": 1e-07,
17
+ "max_position_embeddings": 512,
18
+ "max_relative_positions": -1,
19
+ "model_type": "ted-deberta-v2",
20
+ "norm_rel_ebd": "layer_norm",
21
+ "num_attention_heads": 6,
22
+ "num_hidden_layers": 12,
23
+ "pad_token_id": 0,
24
+ "pooler_dropout": 0,
25
+ "pooler_hidden_act": "gelu",
26
+ "pooler_hidden_size": 384,
27
+ "pos_att_type": [
28
+ "p2c",
29
+ "c2p"
30
+ ],
31
+ "position_biased_input": false,
32
+ "position_buckets": 256,
33
+ "relative_attention": true,
34
+ "share_att_key": true,
35
+ "torch_dtype": "float32",
36
+ "train_filters": false,
37
+ "transformers_version": "4.28.0",
38
+ "type_vocab_size": 0,
39
+ "vocab_size": 128100
40
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55e0c7fd115441f797be042bfe115112ee9e648755d15219896a631498b91b9c
3
+ size 297005585
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "[UNK]"
9
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "[CLS]",
5
+ "do_lower_case": false,
6
+ "eos_token": "[SEP]",
7
+ "mask_token": "[MASK]",
8
+ "model_max_length": 1000000000000000019884624838656,
9
+ "pad_token": "[PAD]",
10
+ "sep_token": "[SEP]",
11
+ "sp_model_kwargs": {},
12
+ "split_by_punct": false,
13
+ "tokenizer_class": "DebertaV2Tokenizer",
14
+ "unk_token": "[UNK]",
15
+ "vocab_type": "spm"
16
+ }