Hugging Face's logo

RepalleHanumansai
/
billing-subscription-bert

Safetensors
bert
Model card Files
xet
 Community
Hanumansai commited on
Commit
1486c24
·
verified ·
1 Parent(s): b665226

Initial commit: BERT intent + sub-intent model

Browse files
Files changed (30) hide show
  1. checkpoint-28/config.json +48 -0
  2. checkpoint-28/model.safetensors +3 -0
  3. checkpoint-28/optimizer.pt +3 -0
  4. checkpoint-28/rng_state.pth +3 -0
  5. checkpoint-28/scaler.pt +3 -0
  6. checkpoint-28/scheduler.pt +3 -0
  7. checkpoint-28/trainer_state.json +49 -0
  8. checkpoint-28/training_args.bin +3 -0
  9. checkpoint-56/config.json +48 -0
  10. checkpoint-56/model.safetensors +3 -0
  11. checkpoint-56/optimizer.pt +3 -0
  12. checkpoint-56/rng_state.pth +3 -0
  13. checkpoint-56/scaler.pt +3 -0
  14. checkpoint-56/scheduler.pt +3 -0
  15. checkpoint-56/trainer_state.json +64 -0
  16. checkpoint-56/training_args.bin +3 -0
  17. checkpoint-84/config.json +48 -0
  18. checkpoint-84/model.safetensors +3 -0
  19. checkpoint-84/optimizer.pt +3 -0
  20. checkpoint-84/rng_state.pth +3 -0
  21. checkpoint-84/scaler.pt +3 -0
  22. checkpoint-84/scheduler.pt +3 -0
  23. checkpoint-84/trainer_state.json +86 -0
  24. checkpoint-84/training_args.bin +3 -0
  25. config.json +48 -0
  26. label_encoder.pkl +3 -0
  27. model.safetensors +3 -0
  28. special_tokens_map.json +7 -0
  29. tokenizer_config.json +58 -0
  30. vocab.txt +0 -0
checkpoint-28/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.2",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-28/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ca544a4f0d33358ab21506d093377e2f541b31d0b2fe90c5848f58d5ace565
3
+ size 437980180
checkpoint-28/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db8516dfc9c12ae86636d69dd42b6f0c534a43aeabdb26f13f660cba9f39710e
3
+ size 876084619
checkpoint-28/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c506c253ef23168b9d0c5e7518320637288fd274058072121ad3cfea8fc2f04e
3
+ size 14645
checkpoint-28/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e2b913b0f901f80a1e35e8f1137d218d95c68d76b7d730e016715684b4c55f
3
+ size 1383
checkpoint-28/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9001498ec83768bc3fe671a65ef2552b04ac5230373b6d50f12aad62af734020
3
+ size 1465
checkpoint-28/trainer_state.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 28,
3
+ "best_metric": 1.9462890625,
4
+ "best_model_checkpoint": "./final_intent_model/checkpoint-28",
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 28,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7142857142857143,
14
+ "grad_norm": 6.867106914520264,
15
+ "learning_rate": 1.5476190476190476e-05,
16
+ "loss": 2.1539,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 1.9462890625,
22
+ "eval_runtime": 0.1331,
23
+ "eval_samples_per_second": 420.644,
24
+ "eval_steps_per_second": 52.581,
25
+ "step": 28
26
+ }
27
+ ],
28
+ "logging_steps": 20,
29
+ "max_steps": 84,
30
+ "num_input_tokens_seen": 0,
31
+ "num_train_epochs": 3,
32
+ "save_steps": 500,
33
+ "stateful_callbacks": {
34
+ "TrainerControl": {
35
+ "args": {
36
+ "should_epoch_stop": false,
37
+ "should_evaluate": false,
38
+ "should_log": false,
39
+ "should_save": true,
40
+ "should_training_stop": false
41
+ },
42
+ "attributes": {}
43
+ }
44
+ },
45
+ "total_flos": 14472017556480.0,
46
+ "train_batch_size": 8,
47
+ "trial_name": null,
48
+ "trial_params": null
49
+ }
checkpoint-28/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b187d6545a6add2d493c88a2933240f32944d38ab96c27f88801dc7f2514c2e0
3
+ size 5841
checkpoint-56/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.2",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-56/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d39ef46c03763d9d5b9999adb1ce99b6cefc8958b2107ce74ca7ef2073319bbf
3
+ size 437980180
checkpoint-56/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9dac0368891441668253f8f0611f611bc7b1a43cc853f8e93220a6532a3597d
3
+ size 876084619
checkpoint-56/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c7d255aaecf99971af7743447fbcbd039ee15c701cda88e044a079b53d4b60
3
+ size 14645
checkpoint-56/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d011c62b21f2c6f291654a1b16e52cea3df018a40532531500f90fb38b095b8c
3
+ size 1383
checkpoint-56/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f2a69bc6727db4da10659284d7d7749e4047d71e072dc68fe7c252ea40d1977
3
+ size 1465
checkpoint-56/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 56,
3
+ "best_metric": 1.5284249782562256,
4
+ "best_model_checkpoint": "./final_intent_model/checkpoint-56",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 56,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7142857142857143,
14
+ "grad_norm": 6.867106914520264,
15
+ "learning_rate": 1.5476190476190476e-05,
16
+ "loss": 2.1539,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 1.9462890625,
22
+ "eval_runtime": 0.1331,
23
+ "eval_samples_per_second": 420.644,
24
+ "eval_steps_per_second": 52.581,
25
+ "step": 28
26
+ },
27
+ {
28
+ "epoch": 1.4285714285714286,
29
+ "grad_norm": 6.846766471862793,
30
+ "learning_rate": 1.0714285714285714e-05,
31
+ "loss": 1.9324,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 1.5284249782562256,
37
+ "eval_runtime": 0.2241,
38
+ "eval_samples_per_second": 249.932,
39
+ "eval_steps_per_second": 31.241,
40
+ "step": 56
41
+ }
42
+ ],
43
+ "logging_steps": 20,
44
+ "max_steps": 84,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 3,
47
+ "save_steps": 500,
48
+ "stateful_callbacks": {
49
+ "TrainerControl": {
50
+ "args": {
51
+ "should_epoch_stop": false,
52
+ "should_evaluate": false,
53
+ "should_log": false,
54
+ "should_save": true,
55
+ "should_training_stop": false
56
+ },
57
+ "attributes": {}
58
+ }
59
+ },
60
+ "total_flos": 28944035112960.0,
61
+ "train_batch_size": 8,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-56/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b187d6545a6add2d493c88a2933240f32944d38ab96c27f88801dc7f2514c2e0
3
+ size 5841
checkpoint-84/config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.2",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
checkpoint-84/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ee2a9fb762a390561fa7d8f674b4d6562481dcb0c26758660b0cdce0e67c74
3
+ size 437980180
checkpoint-84/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27d2a7fcb6adf096f5678b1fc37fcc29f695cd27f61852e3130b32174f674ba4
3
+ size 876084619
checkpoint-84/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aba125d2ab62835f61785ebd9e1d85122c27999aace2243d276de325b3664b33
3
+ size 14645
checkpoint-84/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b374f525f261516982436cbdd52f264a2fa16b745265e4769916ed5719b55e
3
+ size 1383
checkpoint-84/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1285a88c01a0045a6da87c873b54d888596fc01dfd1375cf54df25901b1ef277
3
+ size 1465
checkpoint-84/trainer_state.json ADDED
@@ -0,0 +1,86 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 84,
3
+ "best_metric": 1.3734480142593384,
4
+ "best_model_checkpoint": "./final_intent_model/checkpoint-84",
5
+ "epoch": 3.0,
6
+ "eval_steps": 500,
7
+ "global_step": 84,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.7142857142857143,
14
+ "grad_norm": 6.867106914520264,
15
+ "learning_rate": 1.5476190476190476e-05,
16
+ "loss": 2.1539,
17
+ "step": 20
18
+ },
19
+ {
20
+ "epoch": 1.0,
21
+ "eval_loss": 1.9462890625,
22
+ "eval_runtime": 0.1331,
23
+ "eval_samples_per_second": 420.644,
24
+ "eval_steps_per_second": 52.581,
25
+ "step": 28
26
+ },
27
+ {
28
+ "epoch": 1.4285714285714286,
29
+ "grad_norm": 6.846766471862793,
30
+ "learning_rate": 1.0714285714285714e-05,
31
+ "loss": 1.9324,
32
+ "step": 40
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_loss": 1.5284249782562256,
37
+ "eval_runtime": 0.2241,
38
+ "eval_samples_per_second": 249.932,
39
+ "eval_steps_per_second": 31.241,
40
+ "step": 56
41
+ },
42
+ {
43
+ "epoch": 2.142857142857143,
44
+ "grad_norm": 9.248769760131836,
45
+ "learning_rate": 5.9523809523809525e-06,
46
+ "loss": 1.6384,
47
+ "step": 60
48
+ },
49
+ {
50
+ "epoch": 2.857142857142857,
51
+ "grad_norm": 8.236637115478516,
52
+ "learning_rate": 1.1904761904761906e-06,
53
+ "loss": 1.469,
54
+ "step": 80
55
+ },
56
+ {
57
+ "epoch": 3.0,
58
+ "eval_loss": 1.3734480142593384,
59
+ "eval_runtime": 0.1798,
60
+ "eval_samples_per_second": 311.39,
61
+ "eval_steps_per_second": 38.924,
62
+ "step": 84
63
+ }
64
+ ],
65
+ "logging_steps": 20,
66
+ "max_steps": 84,
67
+ "num_input_tokens_seen": 0,
68
+ "num_train_epochs": 3,
69
+ "save_steps": 500,
70
+ "stateful_callbacks": {
71
+ "TrainerControl": {
72
+ "args": {
73
+ "should_epoch_stop": false,
74
+ "should_evaluate": false,
75
+ "should_log": false,
76
+ "should_save": true,
77
+ "should_training_stop": true
78
+ },
79
+ "attributes": {}
80
+ }
81
+ },
82
+ "total_flos": 43416052669440.0,
83
+ "train_batch_size": 8,
84
+ "trial_name": null,
85
+ "trial_params": null
86
+ }
checkpoint-84/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b187d6545a6add2d493c88a2933240f32944d38ab96c27f88801dc7f2514c2e0
3
+ size 5841
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "BertForSequenceClassification"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "classifier_dropout": null,
7
+ "dtype": "float32",
8
+ "gradient_checkpointing": false,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 768,
12
+ "id2label": {
13
+ "0": "LABEL_0",
14
+ "1": "LABEL_1",
15
+ "2": "LABEL_2",
16
+ "3": "LABEL_3",
17
+ "4": "LABEL_4",
18
+ "5": "LABEL_5",
19
+ "6": "LABEL_6",
20
+ "7": "LABEL_7",
21
+ "8": "LABEL_8"
22
+ },
23
+ "initializer_range": 0.02,
24
+ "intermediate_size": 3072,
25
+ "label2id": {
26
+ "LABEL_0": 0,
27
+ "LABEL_1": 1,
28
+ "LABEL_2": 2,
29
+ "LABEL_3": 3,
30
+ "LABEL_4": 4,
31
+ "LABEL_5": 5,
32
+ "LABEL_6": 6,
33
+ "LABEL_7": 7,
34
+ "LABEL_8": 8
35
+ },
36
+ "layer_norm_eps": 1e-12,
37
+ "max_position_embeddings": 512,
38
+ "model_type": "bert",
39
+ "num_attention_heads": 12,
40
+ "num_hidden_layers": 12,
41
+ "pad_token_id": 0,
42
+ "position_embedding_type": "absolute",
43
+ "problem_type": "single_label_classification",
44
+ "transformers_version": "4.57.2",
45
+ "type_vocab_size": 2,
46
+ "use_cache": true,
47
+ "vocab_size": 30522
48
+ }
label_encoder.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37029214a62955c410f4ee9a515ee40f3f2bff5b536e94e5a7876bc540b57140
3
+ size 804
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40ee2a9fb762a390561fa7d8f674b4d6562481dcb0c26758660b0cdce0e67c74
3
+ size 437980180
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff