Hugging Face's logo

backzone1
/
FI-Chat-Classify-v2

Text Classification
PyTorch
Thai
deberta-v2
thai
fine-tuned
custom-model
Model card Files
xet
Community
1
backzone1 commited on
Commit
981f05c
·
verified ·
1 Parent(s): e21ab87

Upload folder using huggingface_hub

Browse files
Files changed (18) hide show
  1. .gitattributes +3 -0
  2. checkpoint-180/config.json +45 -0
  3. checkpoint-180/special_tokens_map.json +51 -0
  4. checkpoint-180/tokenizer.json +3 -0
  5. checkpoint-180/tokenizer_config.json +59 -0
  6. checkpoint-180/trainer_state.json +73 -0
  7. checkpoint-180/training_args.bin +3 -0
  8. checkpoint-270/config.json +45 -0
  9. checkpoint-270/special_tokens_map.json +51 -0
  10. checkpoint-270/tokenizer.json +3 -0
  11. checkpoint-270/tokenizer_config.json +59 -0
  12. checkpoint-270/trainer_state.json +96 -0
  13. checkpoint-270/training_args.bin +3 -0
  14. config.json +45 -0
  15. pytorch_model.bin +3 -0
  16. special_tokens_map.json +51 -0
  17. tokenizer.json +3 -0
  18. tokenizer_config.json +59 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ checkpoint-180/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
+ checkpoint-270/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
checkpoint-180/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27\u0e40\u0e14\u0e35\u0e22\u0e27",
11
+ "1": "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e2b\u0e25\u0e32\u0e22\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27",
12
+ "2": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e2b\u0e25\u0e32\u0e22\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27": 1,
18
+ "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27\u0e40\u0e14\u0e35\u0e22\u0e27": 0,
19
+ "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19": 2
20
+ },
21
+ "layer_norm_eps": 1e-07,
22
+ "legacy": true,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.52.4",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 251000
45
+ }
checkpoint-180/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-180/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
3
+ size 16316224
checkpoint-180/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-180/trainer_state.json ADDED
@@ -0,0 +1,73 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 180,
3
+ "best_metric": 0.8944444444444445,
4
+ "best_model_checkpoint": "./line-message-3class-classifier\\checkpoint-180",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 180,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5555555555555556,
14
+ "grad_norm": 10.0029935836792,
15
+ "learning_rate": 1.8189300411522635e-05,
16
+ "loss": 1.0551,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8833333333333333,
22
+ "eval_loss": 0.371074378490448,
23
+ "eval_runtime": 2.0349,
24
+ "eval_samples_per_second": 88.458,
25
+ "eval_steps_per_second": 11.303,
26
+ "step": 90
27
+ },
28
+ {
29
+ "epoch": 1.1111111111111112,
30
+ "grad_norm": 12.760857582092285,
31
+ "learning_rate": 1.4074074074074075e-05,
32
+ "loss": 0.4409,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 1.6666666666666665,
37
+ "grad_norm": 7.030289173126221,
38
+ "learning_rate": 9.958847736625515e-06,
39
+ "loss": 0.4766,
40
+ "step": 150
41
+ },
42
+ {
43
+ "epoch": 2.0,
44
+ "eval_accuracy": 0.8944444444444445,
45
+ "eval_loss": 0.3258688151836395,
46
+ "eval_runtime": 2.1545,
47
+ "eval_samples_per_second": 83.545,
48
+ "eval_steps_per_second": 10.675,
49
+ "step": 180
50
+ }
51
+ ],
52
+ "logging_steps": 50,
53
+ "max_steps": 270,
54
+ "num_input_tokens_seen": 0,
55
+ "num_train_epochs": 3,
56
+ "save_steps": 500,
57
+ "stateful_callbacks": {
58
+ "TrainerControl": {
59
+ "args": {
60
+ "should_epoch_stop": false,
61
+ "should_evaluate": false,
62
+ "should_log": false,
63
+ "should_save": true,
64
+ "should_training_stop": false
65
+ },
66
+ "attributes": {}
67
+ }
68
+ },
69
+ "total_flos": 191718563297040.0,
70
+ "train_batch_size": 8,
71
+ "trial_name": null,
72
+ "trial_params": null
73
+ }
checkpoint-180/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc50f1a33fe71b641d7bbbe876ab3c259c3d661b2f2a40b4852e8c5c75a2445
3
+ size 5713
checkpoint-270/config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27\u0e40\u0e14\u0e35\u0e22\u0e27",
11
+ "1": "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e2b\u0e25\u0e32\u0e22\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27",
12
+ "2": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e2b\u0e25\u0e32\u0e22\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27": 1,
18
+ "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27\u0e40\u0e14\u0e35\u0e22\u0e27": 0,
19
+ "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19": 2
20
+ },
21
+ "layer_norm_eps": 1e-07,
22
+ "legacy": true,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.52.4",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 251000
45
+ }
checkpoint-270/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-270/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
3
+ size 16316224
checkpoint-270/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }
checkpoint-270/trainer_state.json ADDED
@@ -0,0 +1,96 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 270,
3
+ "best_metric": 0.9,
4
+ "best_model_checkpoint": "./line-message-3class-classifier\\checkpoint-270",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 270,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.5555555555555556,
14
+ "grad_norm": 10.0029935836792,
15
+ "learning_rate": 1.8189300411522635e-05,
16
+ "loss": 1.0551,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_accuracy": 0.8833333333333333,
22
+ "eval_loss": 0.371074378490448,
23
+ "eval_runtime": 2.0349,
24
+ "eval_samples_per_second": 88.458,
25
+ "eval_steps_per_second": 11.303,
26
+ "step": 90
27
+ },
28
+ {
29
+ "epoch": 1.1111111111111112,
30
+ "grad_norm": 12.760857582092285,
31
+ "learning_rate": 1.4074074074074075e-05,
32
+ "loss": 0.4409,
33
+ "step": 100
34
+ },
35
+ {
36
+ "epoch": 1.6666666666666665,
37
+ "grad_norm": 7.030289173126221,
38
+ "learning_rate": 9.958847736625515e-06,
39
+ "loss": 0.4766,
40
+ "step": 150
41
+ },
42
+ {
43
+ "epoch": 2.0,
44
+ "eval_accuracy": 0.8944444444444445,
45
+ "eval_loss": 0.3258688151836395,
46
+ "eval_runtime": 2.1545,
47
+ "eval_samples_per_second": 83.545,
48
+ "eval_steps_per_second": 10.675,
49
+ "step": 180
50
+ },
51
+ {
52
+ "epoch": 2.2222222222222223,
53
+ "grad_norm": 7.4092326164245605,
54
+ "learning_rate": 5.843621399176955e-06,
55
+ "loss": 0.2314,
56
+ "step": 200
57
+ },
58
+ {
59
+ "epoch": 2.7777777777777777,
60
+ "grad_norm": 8.098183631896973,
61
+ "learning_rate": 1.7283950617283952e-06,
62
+ "loss": 0.1985,
63
+ "step": 250
64
+ },
65
+ {
66
+ "epoch": 3.0,
67
+ "eval_accuracy": 0.9,
68
+ "eval_loss": 0.32884183526039124,
69
+ "eval_runtime": 2.3491,
70
+ "eval_samples_per_second": 76.627,
71
+ "eval_steps_per_second": 9.791,
72
+ "step": 270
73
+ }
74
+ ],
75
+ "logging_steps": 50,
76
+ "max_steps": 270,
77
+ "num_input_tokens_seen": 0,
78
+ "num_train_epochs": 3,
79
+ "save_steps": 500,
80
+ "stateful_callbacks": {
81
+ "TrainerControl": {
82
+ "args": {
83
+ "should_epoch_stop": false,
84
+ "should_evaluate": false,
85
+ "should_log": false,
86
+ "should_save": true,
87
+ "should_training_stop": true
88
+ },
89
+ "attributes": {}
90
+ }
91
+ },
92
+ "total_flos": 291539006263440.0,
93
+ "train_batch_size": 8,
94
+ "trial_name": null,
95
+ "trial_params": null
96
+ }
checkpoint-270/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc50f1a33fe71b641d7bbbe876ab3c259c3d661b2f2a40b4852e8c5c75a2445
3
+ size 5713
config.json ADDED
@@ -0,0 +1,45 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "DebertaV2ForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "hidden_act": "gelu",
7
+ "hidden_dropout_prob": 0.1,
8
+ "hidden_size": 768,
9
+ "id2label": {
10
+ "0": "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27\u0e40\u0e14\u0e35\u0e22\u0e27",
11
+ "1": "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e2b\u0e25\u0e32\u0e22\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27",
12
+ "2": "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19"
13
+ },
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "label2id": {
17
+ "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e2b\u0e25\u0e32\u0e22\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27": 1,
18
+ "\u0e07\u0e32\u0e19\u0e27\u0e34\u0e48\u0e07\u0e40\u0e17\u0e35\u0e48\u0e22\u0e27\u0e40\u0e14\u0e35\u0e22\u0e27": 0,
19
+ "\u0e44\u0e21\u0e48\u0e43\u0e0a\u0e48\u0e07\u0e32\u0e19": 2
20
+ },
21
+ "layer_norm_eps": 1e-07,
22
+ "legacy": true,
23
+ "max_position_embeddings": 512,
24
+ "max_relative_positions": -1,
25
+ "model_type": "deberta-v2",
26
+ "norm_rel_ebd": "layer_norm",
27
+ "num_attention_heads": 12,
28
+ "num_hidden_layers": 12,
29
+ "pad_token_id": 0,
30
+ "pooler_dropout": 0,
31
+ "pooler_hidden_act": "gelu",
32
+ "pooler_hidden_size": 768,
33
+ "pos_att_type": [
34
+ "p2c",
35
+ "c2p"
36
+ ],
37
+ "position_biased_input": false,
38
+ "position_buckets": 256,
39
+ "relative_attention": true,
40
+ "share_att_key": true,
41
+ "torch_dtype": "float32",
42
+ "transformers_version": "4.52.4",
43
+ "type_vocab_size": 0,
44
+ "vocab_size": 251000
45
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d43b4fdfd514dc95ac998ac356e428b5da1be09eb67baafdd405f194b74f44
3
+ size 1115317067
special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "[SEP]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "[MASK]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "[PAD]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "[SEP]",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "[UNK]",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:824e7d82bc5560a30dcf36d84d4598ddcb0ca3c1b3fe38e698105f778bf89d3e
3
+ size 16316224
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "250101": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "extra_special_tokens": {},
50
+ "mask_token": "[MASK]",
51
+ "model_max_length": 512,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "sp_model_kwargs": {},
55
+ "split_by_punct": false,
56
+ "tokenizer_class": "DebertaV2Tokenizer",
57
+ "unk_token": "[UNK]",
58
+ "vocab_type": "spm"
59
+ }