Hugging Face's logo

Ataur77
/
restaurants-chatbot-t5

Safetensors
t5
Model card Files
xet
Community
Ataur77 commited on
Commit
2a550df
·
verified ·
1 Parent(s): 7eed56c

Upload 8 files

Browse files
Files changed (8) hide show
  1. added_tokens.json +102 -0
  2. config.json +60 -0
  3. generation_config.json +7 -0
  4. model.safetensors +3 -0
  5. mt5_bangla_chatbot.ipynb +1831 -0
  6. special_tokens_map.json +125 -0
  7. spiece.model +3 -0
  8. tokenizer_config.json +941 -0
added_tokens.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<extra_id_0>": 32099,
3
+ "<extra_id_10>": 32089,
4
+ "<extra_id_11>": 32088,
5
+ "<extra_id_12>": 32087,
6
+ "<extra_id_13>": 32086,
7
+ "<extra_id_14>": 32085,
8
+ "<extra_id_15>": 32084,
9
+ "<extra_id_16>": 32083,
10
+ "<extra_id_17>": 32082,
11
+ "<extra_id_18>": 32081,
12
+ "<extra_id_19>": 32080,
13
+ "<extra_id_1>": 32098,
14
+ "<extra_id_20>": 32079,
15
+ "<extra_id_21>": 32078,
16
+ "<extra_id_22>": 32077,
17
+ "<extra_id_23>": 32076,
18
+ "<extra_id_24>": 32075,
19
+ "<extra_id_25>": 32074,
20
+ "<extra_id_26>": 32073,
21
+ "<extra_id_27>": 32072,
22
+ "<extra_id_28>": 32071,
23
+ "<extra_id_29>": 32070,
24
+ "<extra_id_2>": 32097,
25
+ "<extra_id_30>": 32069,
26
+ "<extra_id_31>": 32068,
27
+ "<extra_id_32>": 32067,
28
+ "<extra_id_33>": 32066,
29
+ "<extra_id_34>": 32065,
30
+ "<extra_id_35>": 32064,
31
+ "<extra_id_36>": 32063,
32
+ "<extra_id_37>": 32062,
33
+ "<extra_id_38>": 32061,
34
+ "<extra_id_39>": 32060,
35
+ "<extra_id_3>": 32096,
36
+ "<extra_id_40>": 32059,
37
+ "<extra_id_41>": 32058,
38
+ "<extra_id_42>": 32057,
39
+ "<extra_id_43>": 32056,
40
+ "<extra_id_44>": 32055,
41
+ "<extra_id_45>": 32054,
42
+ "<extra_id_46>": 32053,
43
+ "<extra_id_47>": 32052,
44
+ "<extra_id_48>": 32051,
45
+ "<extra_id_49>": 32050,
46
+ "<extra_id_4>": 32095,
47
+ "<extra_id_50>": 32049,
48
+ "<extra_id_51>": 32048,
49
+ "<extra_id_52>": 32047,
50
+ "<extra_id_53>": 32046,
51
+ "<extra_id_54>": 32045,
52
+ "<extra_id_55>": 32044,
53
+ "<extra_id_56>": 32043,
54
+ "<extra_id_57>": 32042,
55
+ "<extra_id_58>": 32041,
56
+ "<extra_id_59>": 32040,
57
+ "<extra_id_5>": 32094,
58
+ "<extra_id_60>": 32039,
59
+ "<extra_id_61>": 32038,
60
+ "<extra_id_62>": 32037,
61
+ "<extra_id_63>": 32036,
62
+ "<extra_id_64>": 32035,
63
+ "<extra_id_65>": 32034,
64
+ "<extra_id_66>": 32033,
65
+ "<extra_id_67>": 32032,
66
+ "<extra_id_68>": 32031,
67
+ "<extra_id_69>": 32030,
68
+ "<extra_id_6>": 32093,
69
+ "<extra_id_70>": 32029,
70
+ "<extra_id_71>": 32028,
71
+ "<extra_id_72>": 32027,
72
+ "<extra_id_73>": 32026,
73
+ "<extra_id_74>": 32025,
74
+ "<extra_id_75>": 32024,
75
+ "<extra_id_76>": 32023,
76
+ "<extra_id_77>": 32022,
77
+ "<extra_id_78>": 32021,
78
+ "<extra_id_79>": 32020,
79
+ "<extra_id_7>": 32092,
80
+ "<extra_id_80>": 32019,
81
+ "<extra_id_81>": 32018,
82
+ "<extra_id_82>": 32017,
83
+ "<extra_id_83>": 32016,
84
+ "<extra_id_84>": 32015,
85
+ "<extra_id_85>": 32014,
86
+ "<extra_id_86>": 32013,
87
+ "<extra_id_87>": 32012,
88
+ "<extra_id_88>": 32011,
89
+ "<extra_id_89>": 32010,
90
+ "<extra_id_8>": 32091,
91
+ "<extra_id_90>": 32009,
92
+ "<extra_id_91>": 32008,
93
+ "<extra_id_92>": 32007,
94
+ "<extra_id_93>": 32006,
95
+ "<extra_id_94>": 32005,
96
+ "<extra_id_95>": 32004,
97
+ "<extra_id_96>": 32003,
98
+ "<extra_id_97>": 32002,
99
+ "<extra_id_98>": 32001,
100
+ "<extra_id_99>": 32000,
101
+ "<extra_id_9>": 32090
102
+ }
config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "T5ForConditionalGeneration"
4
+ ],
5
+ "classifier_dropout": 0.0,
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dense_act_fn": "relu",
11
+ "dropout_rate": 0.1,
12
+ "eos_token_id": 1,
13
+ "feed_forward_proj": "relu",
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "is_gated_act": false,
17
+ "layer_norm_epsilon": 1e-06,
18
+ "model_type": "t5",
19
+ "n_positions": 512,
20
+ "num_decoder_layers": 6,
21
+ "num_heads": 8,
22
+ "num_layers": 6,
23
+ "output_past": true,
24
+ "pad_token_id": 0,
25
+ "relative_attention_max_distance": 128,
26
+ "relative_attention_num_buckets": 32,
27
+ "task_specific_params": {
28
+ "summarization": {
29
+ "early_stopping": true,
30
+ "length_penalty": 2.0,
31
+ "max_length": 200,
32
+ "min_length": 30,
33
+ "no_repeat_ngram_size": 3,
34
+ "num_beams": 4,
35
+ "prefix": "summarize: "
36
+ },
37
+ "translation_en_to_de": {
38
+ "early_stopping": true,
39
+ "max_length": 300,
40
+ "num_beams": 4,
41
+ "prefix": "translate English to German: "
42
+ },
43
+ "translation_en_to_fr": {
44
+ "early_stopping": true,
45
+ "max_length": 300,
46
+ "num_beams": 4,
47
+ "prefix": "translate English to French: "
48
+ },
49
+ "translation_en_to_ro": {
50
+ "early_stopping": true,
51
+ "max_length": 300,
52
+ "num_beams": 4,
53
+ "prefix": "translate English to Romanian: "
54
+ }
55
+ },
56
+ "torch_dtype": "float32",
57
+ "transformers_version": "4.52.4",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "decoder_start_token_id": 0,
4
+ "eos_token_id": 1,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.52.4"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f4e10db9fc3ba9e190532dd0a9d06291b86043cbab12e281ad07a521689896c
3
+ size 242041896
mt5_bangla_chatbot.ipynb ADDED
@@ -0,0 +1,1831 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "nbformat": 4,
3
+ "nbformat_minor": 0,
4
+ "metadata": {
5
+ "colab": {
6
+ "provenance": [],
7
+ "gpuType": "T4"
8
+ },
9
+ "kernelspec": {
10
+ "name": "python3",
11
+ "display_name": "Python 3"
12
+ },
13
+ "language_info": {
14
+ "name": "python"
15
+ },
16
+ "accelerator": "GPU",
17
+ "widgets": {
18
+ "application/vnd.jupyter.widget-state+json": {
19
+ "6731bf4c44b04418a3e92162bf339b4d": {
20
+ "model_module": "@jupyter-widgets/controls",
21
+ "model_name": "HBoxModel",
22
+ "model_module_version": "1.5.0",
23
+ "state": {
24
+ "_dom_classes": [],
25
+ "_model_module": "@jupyter-widgets/controls",
26
+ "_model_module_version": "1.5.0",
27
+ "_model_name": "HBoxModel",
28
+ "_view_count": null,
29
+ "_view_module": "@jupyter-widgets/controls",
30
+ "_view_module_version": "1.5.0",
31
+ "_view_name": "HBoxView",
32
+ "box_style": "",
33
+ "children": [
34
+ "IPY_MODEL_7f292c9fb40a43cea617cb2af8cf6d16",
35
+ "IPY_MODEL_5cbd9bb2715d46e7ba22e559d5b75c96",
36
+ "IPY_MODEL_2ab10bd157ee4e568c10374e4720e676"
37
+ ],
38
+ "layout": "IPY_MODEL_e7f1d0472dbc41ababc2d4153f13d2b4"
39
+ }
40
+ },
41
+ "7f292c9fb40a43cea617cb2af8cf6d16": {
42
+ "model_module": "@jupyter-widgets/controls",
43
+ "model_name": "HTMLModel",
44
+ "model_module_version": "1.5.0",
45
+ "state": {
46
+ "_dom_classes": [],
47
+ "_model_module": "@jupyter-widgets/controls",
48
+ "_model_module_version": "1.5.0",
49
+ "_model_name": "HTMLModel",
50
+ "_view_count": null,
51
+ "_view_module": "@jupyter-widgets/controls",
52
+ "_view_module_version": "1.5.0",
53
+ "_view_name": "HTMLView",
54
+ "description": "",
55
+ "description_tooltip": null,
56
+ "layout": "IPY_MODEL_abb5f0f1c1694961957f32824d14ccf5",
57
+ "placeholder": "​",
58
+ "style": "IPY_MODEL_acad57f3134c46e7b08af70d9d72ece9",
59
+ "value": "Map: 100%"
60
+ }
61
+ },
62
+ "5cbd9bb2715d46e7ba22e559d5b75c96": {
63
+ "model_module": "@jupyter-widgets/controls",
64
+ "model_name": "FloatProgressModel",
65
+ "model_module_version": "1.5.0",
66
+ "state": {
67
+ "_dom_classes": [],
68
+ "_model_module": "@jupyter-widgets/controls",
69
+ "_model_module_version": "1.5.0",
70
+ "_model_name": "FloatProgressModel",
71
+ "_view_count": null,
72
+ "_view_module": "@jupyter-widgets/controls",
73
+ "_view_module_version": "1.5.0",
74
+ "_view_name": "ProgressView",
75
+ "bar_style": "success",
76
+ "description": "",
77
+ "description_tooltip": null,
78
+ "layout": "IPY_MODEL_0fd2902a45474e09832d43da534e5540",
79
+ "max": 202,
80
+ "min": 0,
81
+ "orientation": "horizontal",
82
+ "style": "IPY_MODEL_74f3cd48c2504464a2ef14f9c6f7730b",
83
+ "value": 202
84
+ }
85
+ },
86
+ "2ab10bd157ee4e568c10374e4720e676": {
87
+ "model_module": "@jupyter-widgets/controls",
88
+ "model_name": "HTMLModel",
89
+ "model_module_version": "1.5.0",
90
+ "state": {
91
+ "_dom_classes": [],
92
+ "_model_module": "@jupyter-widgets/controls",
93
+ "_model_module_version": "1.5.0",
94
+ "_model_name": "HTMLModel",
95
+ "_view_count": null,
96
+ "_view_module": "@jupyter-widgets/controls",
97
+ "_view_module_version": "1.5.0",
98
+ "_view_name": "HTMLView",
99
+ "description": "",
100
+ "description_tooltip": null,
101
+ "layout": "IPY_MODEL_0031511abb9b459a9b9e1cded6186287",
102
+ "placeholder": "​",
103
+ "style": "IPY_MODEL_b30964047ced437aa46dd0b654270bbd",
104
+ "value": " 202/202 [00:00&lt;00:00, 439.85 examples/s]"
105
+ }
106
+ },
107
+ "e7f1d0472dbc41ababc2d4153f13d2b4": {
108
+ "model_module": "@jupyter-widgets/base",
109
+ "model_name": "LayoutModel",
110
+ "model_module_version": "1.2.0",
111
+ "state": {
112
+ "_model_module": "@jupyter-widgets/base",
113
+ "_model_module_version": "1.2.0",
114
+ "_model_name": "LayoutModel",
115
+ "_view_count": null,
116
+ "_view_module": "@jupyter-widgets/base",
117
+ "_view_module_version": "1.2.0",
118
+ "_view_name": "LayoutView",
119
+ "align_content": null,
120
+ "align_items": null,
121
+ "align_self": null,
122
+ "border": null,
123
+ "bottom": null,
124
+ "display": null,
125
+ "flex": null,
126
+ "flex_flow": null,
127
+ "grid_area": null,
128
+ "grid_auto_columns": null,
129
+ "grid_auto_flow": null,
130
+ "grid_auto_rows": null,
131
+ "grid_column": null,
132
+ "grid_gap": null,
133
+ "grid_row": null,
134
+ "grid_template_areas": null,
135
+ "grid_template_columns": null,
136
+ "grid_template_rows": null,
137
+ "height": null,
138
+ "justify_content": null,
139
+ "justify_items": null,
140
+ "left": null,
141
+ "margin": null,
142
+ "max_height": null,
143
+ "max_width": null,
144
+ "min_height": null,
145
+ "min_width": null,
146
+ "object_fit": null,
147
+ "object_position": null,
148
+ "order": null,
149
+ "overflow": null,
150
+ "overflow_x": null,
151
+ "overflow_y": null,
152
+ "padding": null,
153
+ "right": null,
154
+ "top": null,
155
+ "visibility": null,
156
+ "width": null
157
+ }
158
+ },
159
+ "abb5f0f1c1694961957f32824d14ccf5": {
160
+ "model_module": "@jupyter-widgets/base",
161
+ "model_name": "LayoutModel",
162
+ "model_module_version": "1.2.0",
163
+ "state": {
164
+ "_model_module": "@jupyter-widgets/base",
165
+ "_model_module_version": "1.2.0",
166
+ "_model_name": "LayoutModel",
167
+ "_view_count": null,
168
+ "_view_module": "@jupyter-widgets/base",
169
+ "_view_module_version": "1.2.0",
170
+ "_view_name": "LayoutView",
171
+ "align_content": null,
172
+ "align_items": null,
173
+ "align_self": null,
174
+ "border": null,
175
+ "bottom": null,
176
+ "display": null,
177
+ "flex": null,
178
+ "flex_flow": null,
179
+ "grid_area": null,
180
+ "grid_auto_columns": null,
181
+ "grid_auto_flow": null,
182
+ "grid_auto_rows": null,
183
+ "grid_column": null,
184
+ "grid_gap": null,
185
+ "grid_row": null,
186
+ "grid_template_areas": null,
187
+ "grid_template_columns": null,
188
+ "grid_template_rows": null,
189
+ "height": null,
190
+ "justify_content": null,
191
+ "justify_items": null,
192
+ "left": null,
193
+ "margin": null,
194
+ "max_height": null,
195
+ "max_width": null,
196
+ "min_height": null,
197
+ "min_width": null,
198
+ "object_fit": null,
199
+ "object_position": null,
200
+ "order": null,
201
+ "overflow": null,
202
+ "overflow_x": null,
203
+ "overflow_y": null,
204
+ "padding": null,
205
+ "right": null,
206
+ "top": null,
207
+ "visibility": null,
208
+ "width": null
209
+ }
210
+ },
211
+ "acad57f3134c46e7b08af70d9d72ece9": {
212
+ "model_module": "@jupyter-widgets/controls",
213
+ "model_name": "DescriptionStyleModel",
214
+ "model_module_version": "1.5.0",
215
+ "state": {
216
+ "_model_module": "@jupyter-widgets/controls",
217
+ "_model_module_version": "1.5.0",
218
+ "_model_name": "DescriptionStyleModel",
219
+ "_view_count": null,
220
+ "_view_module": "@jupyter-widgets/base",
221
+ "_view_module_version": "1.2.0",
222
+ "_view_name": "StyleView",
223
+ "description_width": ""
224
+ }
225
+ },
226
+ "0fd2902a45474e09832d43da534e5540": {
227
+ "model_module": "@jupyter-widgets/base",
228
+ "model_name": "LayoutModel",
229
+ "model_module_version": "1.2.0",
230
+ "state": {
231
+ "_model_module": "@jupyter-widgets/base",
232
+ "_model_module_version": "1.2.0",
233
+ "_model_name": "LayoutModel",
234
+ "_view_count": null,
235
+ "_view_module": "@jupyter-widgets/base",
236
+ "_view_module_version": "1.2.0",
237
+ "_view_name": "LayoutView",
238
+ "align_content": null,
239
+ "align_items": null,
240
+ "align_self": null,
241
+ "border": null,
242
+ "bottom": null,
243
+ "display": null,
244
+ "flex": null,
245
+ "flex_flow": null,
246
+ "grid_area": null,
247
+ "grid_auto_columns": null,
248
+ "grid_auto_flow": null,
249
+ "grid_auto_rows": null,
250
+ "grid_column": null,
251
+ "grid_gap": null,
252
+ "grid_row": null,
253
+ "grid_template_areas": null,
254
+ "grid_template_columns": null,
255
+ "grid_template_rows": null,
256
+ "height": null,
257
+ "justify_content": null,
258
+ "justify_items": null,
259
+ "left": null,
260
+ "margin": null,
261
+ "max_height": null,
262
+ "max_width": null,
263
+ "min_height": null,
264
+ "min_width": null,
265
+ "object_fit": null,
266
+ "object_position": null,
267
+ "order": null,
268
+ "overflow": null,
269
+ "overflow_x": null,
270
+ "overflow_y": null,
271
+ "padding": null,
272
+ "right": null,
273
+ "top": null,
274
+ "visibility": null,
275
+ "width": null
276
+ }
277
+ },
278
+ "74f3cd48c2504464a2ef14f9c6f7730b": {
279
+ "model_module": "@jupyter-widgets/controls",
280
+ "model_name": "ProgressStyleModel",
281
+ "model_module_version": "1.5.0",
282
+ "state": {
283
+ "_model_module": "@jupyter-widgets/controls",
284
+ "_model_module_version": "1.5.0",
285
+ "_model_name": "ProgressStyleModel",
286
+ "_view_count": null,
287
+ "_view_module": "@jupyter-widgets/base",
288
+ "_view_module_version": "1.2.0",
289
+ "_view_name": "StyleView",
290
+ "bar_color": null,
291
+ "description_width": ""
292
+ }
293
+ },
294
+ "0031511abb9b459a9b9e1cded6186287": {
295
+ "model_module": "@jupyter-widgets/base",
296
+ "model_name": "LayoutModel",
297
+ "model_module_version": "1.2.0",
298
+ "state": {
299
+ "_model_module": "@jupyter-widgets/base",
300
+ "_model_module_version": "1.2.0",
301
+ "_model_name": "LayoutModel",
302
+ "_view_count": null,
303
+ "_view_module": "@jupyter-widgets/base",
304
+ "_view_module_version": "1.2.0",
305
+ "_view_name": "LayoutView",
306
+ "align_content": null,
307
+ "align_items": null,
308
+ "align_self": null,
309
+ "border": null,
310
+ "bottom": null,
311
+ "display": null,
312
+ "flex": null,
313
+ "flex_flow": null,
314
+ "grid_area": null,
315
+ "grid_auto_columns": null,
316
+ "grid_auto_flow": null,
317
+ "grid_auto_rows": null,
318
+ "grid_column": null,
319
+ "grid_gap": null,
320
+ "grid_row": null,
321
+ "grid_template_areas": null,
322
+ "grid_template_columns": null,
323
+ "grid_template_rows": null,
324
+ "height": null,
325
+ "justify_content": null,
326
+ "justify_items": null,
327
+ "left": null,
328
+ "margin": null,
329
+ "max_height": null,
330
+ "max_width": null,
331
+ "min_height": null,
332
+ "min_width": null,
333
+ "object_fit": null,
334
+ "object_position": null,
335
+ "order": null,
336
+ "overflow": null,
337
+ "overflow_x": null,
338
+ "overflow_y": null,
339
+ "padding": null,
340
+ "right": null,
341
+ "top": null,
342
+ "visibility": null,
343
+ "width": null
344
+ }
345
+ },
346
+ "b30964047ced437aa46dd0b654270bbd": {
347
+ "model_module": "@jupyter-widgets/controls",
348
+ "model_name": "DescriptionStyleModel",
349
+ "model_module_version": "1.5.0",
350
+ "state": {
351
+ "_model_module": "@jupyter-widgets/controls",
352
+ "_model_module_version": "1.5.0",
353
+ "_model_name": "DescriptionStyleModel",
354
+ "_view_count": null,
355
+ "_view_module": "@jupyter-widgets/base",
356
+ "_view_module_version": "1.2.0",
357
+ "_view_name": "StyleView",
358
+ "description_width": ""
359
+ }
360
+ },
361
+ "707c911f3f284ca694434c66a5d32164": {
362
+ "model_module": "@jupyter-widgets/controls",
363
+ "model_name": "HBoxModel",
364
+ "model_module_version": "1.5.0",
365
+ "state": {
366
+ "_dom_classes": [],
367
+ "_model_module": "@jupyter-widgets/controls",
368
+ "_model_module_version": "1.5.0",
369
+ "_model_name": "HBoxModel",
370
+ "_view_count": null,
371
+ "_view_module": "@jupyter-widgets/controls",
372
+ "_view_module_version": "1.5.0",
373
+ "_view_name": "HBoxView",
374
+ "box_style": "",
375
+ "children": [
376
+ "IPY_MODEL_5d09f1b981fe40408a510d10351beead",
377
+ "IPY_MODEL_ef27890e503a449f9583d960f244cfb8",
378
+ "IPY_MODEL_c626325b0dee40ee861315bb5fb176c7"
379
+ ],
380
+ "layout": "IPY_MODEL_643bd0b694994321b4c83ac36448a020"
381
+ }
382
+ },
383
+ "5d09f1b981fe40408a510d10351beead": {
384
+ "model_module": "@jupyter-widgets/controls",
385
+ "model_name": "HTMLModel",
386
+ "model_module_version": "1.5.0",
387
+ "state": {
388
+ "_dom_classes": [],
389
+ "_model_module": "@jupyter-widgets/controls",
390
+ "_model_module_version": "1.5.0",
391
+ "_model_name": "HTMLModel",
392
+ "_view_count": null,
393
+ "_view_module": "@jupyter-widgets/controls",
394
+ "_view_module_version": "1.5.0",
395
+ "_view_name": "HTMLView",
396
+ "description": "",
397
+ "description_tooltip": null,
398
+ "layout": "IPY_MODEL_4531e52322314195bb3ab8ae68d3a99e",
399
+ "placeholder": "​",
400
+ "style": "IPY_MODEL_81ecb5431f2b4d53811abc584b30de70",
401
+ "value": "Map: 100%"
402
+ }
403
+ },
404
+ "ef27890e503a449f9583d960f244cfb8": {
405
+ "model_module": "@jupyter-widgets/controls",
406
+ "model_name": "FloatProgressModel",
407
+ "model_module_version": "1.5.0",
408
+ "state": {
409
+ "_dom_classes": [],
410
+ "_model_module": "@jupyter-widgets/controls",
411
+ "_model_module_version": "1.5.0",
412
+ "_model_name": "FloatProgressModel",
413
+ "_view_count": null,
414
+ "_view_module": "@jupyter-widgets/controls",
415
+ "_view_module_version": "1.5.0",
416
+ "_view_name": "ProgressView",
417
+ "bar_style": "success",
418
+ "description": "",
419
+ "description_tooltip": null,
420
+ "layout": "IPY_MODEL_2a8bea160baf4fdb94d36ec7b2e48abc",
421
+ "max": 161,
422
+ "min": 0,
423
+ "orientation": "horizontal",
424
+ "style": "IPY_MODEL_ac0daaf6c7634a3ebe224a6ec0d53fed",
425
+ "value": 161
426
+ }
427
+ },
428
+ "c626325b0dee40ee861315bb5fb176c7": {
429
+ "model_module": "@jupyter-widgets/controls",
430
+ "model_name": "HTMLModel",
431
+ "model_module_version": "1.5.0",
432
+ "state": {
433
+ "_dom_classes": [],
434
+ "_model_module": "@jupyter-widgets/controls",
435
+ "_model_module_version": "1.5.0",
436
+ "_model_name": "HTMLModel",
437
+ "_view_count": null,
438
+ "_view_module": "@jupyter-widgets/controls",
439
+ "_view_module_version": "1.5.0",
440
+ "_view_name": "HTMLView",
441
+ "description": "",
442
+ "description_tooltip": null,
443
+ "layout": "IPY_MODEL_7a2e64f9ab664a0884e176ad6e126ce3",
444
+ "placeholder": "​",
445
+ "style": "IPY_MODEL_b1eabce5ada443bf803773ba90f03d74",
446
+ "value": " 161/161 [00:00&lt;00:00, 1716.09 examples/s]"
447
+ }
448
+ },
449
+ "643bd0b694994321b4c83ac36448a020": {
450
+ "model_module": "@jupyter-widgets/base",
451
+ "model_name": "LayoutModel",
452
+ "model_module_version": "1.2.0",
453
+ "state": {
454
+ "_model_module": "@jupyter-widgets/base",
455
+ "_model_module_version": "1.2.0",
456
+ "_model_name": "LayoutModel",
457
+ "_view_count": null,
458
+ "_view_module": "@jupyter-widgets/base",
459
+ "_view_module_version": "1.2.0",
460
+ "_view_name": "LayoutView",
461
+ "align_content": null,
462
+ "align_items": null,
463
+ "align_self": null,
464
+ "border": null,
465
+ "bottom": null,
466
+ "display": null,
467
+ "flex": null,
468
+ "flex_flow": null,
469
+ "grid_area": null,
470
+ "grid_auto_columns": null,
471
+ "grid_auto_flow": null,
472
+ "grid_auto_rows": null,
473
+ "grid_column": null,
474
+ "grid_gap": null,
475
+ "grid_row": null,
476
+ "grid_template_areas": null,
477
+ "grid_template_columns": null,
478
+ "grid_template_rows": null,
479
+ "height": null,
480
+ "justify_content": null,
481
+ "justify_items": null,
482
+ "left": null,
483
+ "margin": null,
484
+ "max_height": null,
485
+ "max_width": null,
486
+ "min_height": null,
487
+ "min_width": null,
488
+ "object_fit": null,
489
+ "object_position": null,
490
+ "order": null,
491
+ "overflow": null,
492
+ "overflow_x": null,
493
+ "overflow_y": null,
494
+ "padding": null,
495
+ "right": null,
496
+ "top": null,
497
+ "visibility": null,
498
+ "width": null
499
+ }
500
+ },
501
+ "4531e52322314195bb3ab8ae68d3a99e": {
502
+ "model_module": "@jupyter-widgets/base",
503
+ "model_name": "LayoutModel",
504
+ "model_module_version": "1.2.0",
505
+ "state": {
506
+ "_model_module": "@jupyter-widgets/base",
507
+ "_model_module_version": "1.2.0",
508
+ "_model_name": "LayoutModel",
509
+ "_view_count": null,
510
+ "_view_module": "@jupyter-widgets/base",
511
+ "_view_module_version": "1.2.0",
512
+ "_view_name": "LayoutView",
513
+ "align_content": null,
514
+ "align_items": null,
515
+ "align_self": null,
516
+ "border": null,
517
+ "bottom": null,
518
+ "display": null,
519
+ "flex": null,
520
+ "flex_flow": null,
521
+ "grid_area": null,
522
+ "grid_auto_columns": null,
523
+ "grid_auto_flow": null,
524
+ "grid_auto_rows": null,
525
+ "grid_column": null,
526
+ "grid_gap": null,
527
+ "grid_row": null,
528
+ "grid_template_areas": null,
529
+ "grid_template_columns": null,
530
+ "grid_template_rows": null,
531
+ "height": null,
532
+ "justify_content": null,
533
+ "justify_items": null,
534
+ "left": null,
535
+ "margin": null,
536
+ "max_height": null,
537
+ "max_width": null,
538
+ "min_height": null,
539
+ "min_width": null,
540
+ "object_fit": null,
541
+ "object_position": null,
542
+ "order": null,
543
+ "overflow": null,
544
+ "overflow_x": null,
545
+ "overflow_y": null,
546
+ "padding": null,
547
+ "right": null,
548
+ "top": null,
549
+ "visibility": null,
550
+ "width": null
551
+ }
552
+ },
553
+ "81ecb5431f2b4d53811abc584b30de70": {
554
+ "model_module": "@jupyter-widgets/controls",
555
+ "model_name": "DescriptionStyleModel",
556
+ "model_module_version": "1.5.0",
557
+ "state": {
558
+ "_model_module": "@jupyter-widgets/controls",
559
+ "_model_module_version": "1.5.0",
560
+ "_model_name": "DescriptionStyleModel",
561
+ "_view_count": null,
562
+ "_view_module": "@jupyter-widgets/base",
563
+ "_view_module_version": "1.2.0",
564
+ "_view_name": "StyleView",
565
+ "description_width": ""
566
+ }
567
+ },
568
+ "2a8bea160baf4fdb94d36ec7b2e48abc": {
569
+ "model_module": "@jupyter-widgets/base",
570
+ "model_name": "LayoutModel",
571
+ "model_module_version": "1.2.0",
572
+ "state": {
573
+ "_model_module": "@jupyter-widgets/base",
574
+ "_model_module_version": "1.2.0",
575
+ "_model_name": "LayoutModel",
576
+ "_view_count": null,
577
+ "_view_module": "@jupyter-widgets/base",
578
+ "_view_module_version": "1.2.0",
579
+ "_view_name": "LayoutView",
580
+ "align_content": null,
581
+ "align_items": null,
582
+ "align_self": null,
583
+ "border": null,
584
+ "bottom": null,
585
+ "display": null,
586
+ "flex": null,
587
+ "flex_flow": null,
588
+ "grid_area": null,
589
+ "grid_auto_columns": null,
590
+ "grid_auto_flow": null,
591
+ "grid_auto_rows": null,
592
+ "grid_column": null,
593
+ "grid_gap": null,
594
+ "grid_row": null,
595
+ "grid_template_areas": null,
596
+ "grid_template_columns": null,
597
+ "grid_template_rows": null,
598
+ "height": null,
599
+ "justify_content": null,
600
+ "justify_items": null,
601
+ "left": null,
602
+ "margin": null,
603
+ "max_height": null,
604
+ "max_width": null,
605
+ "min_height": null,
606
+ "min_width": null,
607
+ "object_fit": null,
608
+ "object_position": null,
609
+ "order": null,
610
+ "overflow": null,
611
+ "overflow_x": null,
612
+ "overflow_y": null,
613
+ "padding": null,
614
+ "right": null,
615
+ "top": null,
616
+ "visibility": null,
617
+ "width": null
618
+ }
619
+ },
620
+ "ac0daaf6c7634a3ebe224a6ec0d53fed": {
621
+ "model_module": "@jupyter-widgets/controls",
622
+ "model_name": "ProgressStyleModel",
623
+ "model_module_version": "1.5.0",
624
+ "state": {
625
+ "_model_module": "@jupyter-widgets/controls",
626
+ "_model_module_version": "1.5.0",
627
+ "_model_name": "ProgressStyleModel",
628
+ "_view_count": null,
629
+ "_view_module": "@jupyter-widgets/base",
630
+ "_view_module_version": "1.2.0",
631
+ "_view_name": "StyleView",
632
+ "bar_color": null,
633
+ "description_width": ""
634
+ }
635
+ },
636
+ "7a2e64f9ab664a0884e176ad6e126ce3": {
637
+ "model_module": "@jupyter-widgets/base",
638
+ "model_name": "LayoutModel",
639
+ "model_module_version": "1.2.0",
640
+ "state": {
641
+ "_model_module": "@jupyter-widgets/base",
642
+ "_model_module_version": "1.2.0",
643
+ "_model_name": "LayoutModel",
644
+ "_view_count": null,
645
+ "_view_module": "@jupyter-widgets/base",
646
+ "_view_module_version": "1.2.0",
647
+ "_view_name": "LayoutView",
648
+ "align_content": null,
649
+ "align_items": null,
650
+ "align_self": null,
651
+ "border": null,
652
+ "bottom": null,
653
+ "display": null,
654
+ "flex": null,
655
+ "flex_flow": null,
656
+ "grid_area": null,
657
+ "grid_auto_columns": null,
658
+ "grid_auto_flow": null,
659
+ "grid_auto_rows": null,
660
+ "grid_column": null,
661
+ "grid_gap": null,
662
+ "grid_row": null,
663
+ "grid_template_areas": null,
664
+ "grid_template_columns": null,
665
+ "grid_template_rows": null,
666
+ "height": null,
667
+ "justify_content": null,
668
+ "justify_items": null,
669
+ "left": null,
670
+ "margin": null,
671
+ "max_height": null,
672
+ "max_width": null,
673
+ "min_height": null,
674
+ "min_width": null,
675
+ "object_fit": null,
676
+ "object_position": null,
677
+ "order": null,
678
+ "overflow": null,
679
+ "overflow_x": null,
680
+ "overflow_y": null,
681
+ "padding": null,
682
+ "right": null,
683
+ "top": null,
684
+ "visibility": null,
685
+ "width": null
686
+ }
687
+ },
688
+ "b1eabce5ada443bf803773ba90f03d74": {
689
+ "model_module": "@jupyter-widgets/controls",
690
+ "model_name": "DescriptionStyleModel",
691
+ "model_module_version": "1.5.0",
692
+ "state": {
693
+ "_model_module": "@jupyter-widgets/controls",
694
+ "_model_module_version": "1.5.0",
695
+ "_model_name": "DescriptionStyleModel",
696
+ "_view_count": null,
697
+ "_view_module": "@jupyter-widgets/base",
698
+ "_view_module_version": "1.2.0",
699
+ "_view_name": "StyleView",
700
+ "description_width": ""
701
+ }
702
+ },
703
+ "24f4f3f3e2c54bc789d30d363a93095e": {
704
+ "model_module": "@jupyter-widgets/controls",
705
+ "model_name": "HBoxModel",
706
+ "model_module_version": "1.5.0",
707
+ "state": {
708
+ "_dom_classes": [],
709
+ "_model_module": "@jupyter-widgets/controls",
710
+ "_model_module_version": "1.5.0",
711
+ "_model_name": "HBoxModel",
712
+ "_view_count": null,
713
+ "_view_module": "@jupyter-widgets/controls",
714
+ "_view_module_version": "1.5.0",
715
+ "_view_name": "HBoxView",
716
+ "box_style": "",
717
+ "children": [
718
+ "IPY_MODEL_b220dd31400349b1a09e1244574b8fd2",
719
+ "IPY_MODEL_cdce2e98b8584f12a533144e07387eaa",
720
+ "IPY_MODEL_db62ab11b6464508baa4799e7c1c1e16"
721
+ ],
722
+ "layout": "IPY_MODEL_174904c1cbb3475193a99498f870ec21"
723
+ }
724
+ },
725
+ "b220dd31400349b1a09e1244574b8fd2": {
726
+ "model_module": "@jupyter-widgets/controls",
727
+ "model_name": "HTMLModel",
728
+ "model_module_version": "1.5.0",
729
+ "state": {
730
+ "_dom_classes": [],
731
+ "_model_module": "@jupyter-widgets/controls",
732
+ "_model_module_version": "1.5.0",
733
+ "_model_name": "HTMLModel",
734
+ "_view_count": null,
735
+ "_view_module": "@jupyter-widgets/controls",
736
+ "_view_module_version": "1.5.0",
737
+ "_view_name": "HTMLView",
738
+ "description": "",
739
+ "description_tooltip": null,
740
+ "layout": "IPY_MODEL_9fe9296adae642d380e09e71dc9bfce0",
741
+ "placeholder": "​",
742
+ "style": "IPY_MODEL_3a9b29c6754b4929bc2849addf5470ab",
743
+ "value": "Map: 100%"
744
+ }
745
+ },
746
+ "cdce2e98b8584f12a533144e07387eaa": {
747
+ "model_module": "@jupyter-widgets/controls",
748
+ "model_name": "FloatProgressModel",
749
+ "model_module_version": "1.5.0",
750
+ "state": {
751
+ "_dom_classes": [],
752
+ "_model_module": "@jupyter-widgets/controls",
753
+ "_model_module_version": "1.5.0",
754
+ "_model_name": "FloatProgressModel",
755
+ "_view_count": null,
756
+ "_view_module": "@jupyter-widgets/controls",
757
+ "_view_module_version": "1.5.0",
758
+ "_view_name": "ProgressView",
759
+ "bar_style": "success",
760
+ "description": "",
761
+ "description_tooltip": null,
762
+ "layout": "IPY_MODEL_f44a5f3e7f8b4d2c947a5596e4915124",
763
+ "max": 41,
764
+ "min": 0,
765
+ "orientation": "horizontal",
766
+ "style": "IPY_MODEL_56d13847df33476da1d463470ba84722",
767
+ "value": 41
768
+ }
769
+ },
770
+ "db62ab11b6464508baa4799e7c1c1e16": {
771
+ "model_module": "@jupyter-widgets/controls",
772
+ "model_name": "HTMLModel",
773
+ "model_module_version": "1.5.0",
774
+ "state": {
775
+ "_dom_classes": [],
776
+ "_model_module": "@jupyter-widgets/controls",
777
+ "_model_module_version": "1.5.0",
778
+ "_model_name": "HTMLModel",
779
+ "_view_count": null,
780
+ "_view_module": "@jupyter-widgets/controls",
781
+ "_view_module_version": "1.5.0",
782
+ "_view_name": "HTMLView",
783
+ "description": "",
784
+ "description_tooltip": null,
785
+ "layout": "IPY_MODEL_4532aae1ae1842a19695c55bf13458c2",
786
+ "placeholder": "​",
787
+ "style": "IPY_MODEL_66596e16abbf4561997ec9689b08fe01",
788
+ "value": " 41/41 [00:00&lt;00:00, 493.62 examples/s]"
789
+ }
790
+ },
791
+ "174904c1cbb3475193a99498f870ec21": {
792
+ "model_module": "@jupyter-widgets/base",
793
+ "model_name": "LayoutModel",
794
+ "model_module_version": "1.2.0",
795
+ "state": {
796
+ "_model_module": "@jupyter-widgets/base",
797
+ "_model_module_version": "1.2.0",
798
+ "_model_name": "LayoutModel",
799
+ "_view_count": null,
800
+ "_view_module": "@jupyter-widgets/base",
801
+ "_view_module_version": "1.2.0",
802
+ "_view_name": "LayoutView",
803
+ "align_content": null,
804
+ "align_items": null,
805
+ "align_self": null,
806
+ "border": null,
807
+ "bottom": null,
808
+ "display": null,
809
+ "flex": null,
810
+ "flex_flow": null,
811
+ "grid_area": null,
812
+ "grid_auto_columns": null,
813
+ "grid_auto_flow": null,
814
+ "grid_auto_rows": null,
815
+ "grid_column": null,
816
+ "grid_gap": null,
817
+ "grid_row": null,
818
+ "grid_template_areas": null,
819
+ "grid_template_columns": null,
820
+ "grid_template_rows": null,
821
+ "height": null,
822
+ "justify_content": null,
823
+ "justify_items": null,
824
+ "left": null,
825
+ "margin": null,
826
+ "max_height": null,
827
+ "max_width": null,
828
+ "min_height": null,
829
+ "min_width": null,
830
+ "object_fit": null,
831
+ "object_position": null,
832
+ "order": null,
833
+ "overflow": null,
834
+ "overflow_x": null,
835
+ "overflow_y": null,
836
+ "padding": null,
837
+ "right": null,
838
+ "top": null,
839
+ "visibility": null,
840
+ "width": null
841
+ }
842
+ },
843
+ "9fe9296adae642d380e09e71dc9bfce0": {
844
+ "model_module": "@jupyter-widgets/base",
845
+ "model_name": "LayoutModel",
846
+ "model_module_version": "1.2.0",
847
+ "state": {
848
+ "_model_module": "@jupyter-widgets/base",
849
+ "_model_module_version": "1.2.0",
850
+ "_model_name": "LayoutModel",
851
+ "_view_count": null,
852
+ "_view_module": "@jupyter-widgets/base",
853
+ "_view_module_version": "1.2.0",
854
+ "_view_name": "LayoutView",
855
+ "align_content": null,
856
+ "align_items": null,
857
+ "align_self": null,
858
+ "border": null,
859
+ "bottom": null,
860
+ "display": null,
861
+ "flex": null,
862
+ "flex_flow": null,
863
+ "grid_area": null,
864
+ "grid_auto_columns": null,
865
+ "grid_auto_flow": null,
866
+ "grid_auto_rows": null,
867
+ "grid_column": null,
868
+ "grid_gap": null,
869
+ "grid_row": null,
870
+ "grid_template_areas": null,
871
+ "grid_template_columns": null,
872
+ "grid_template_rows": null,
873
+ "height": null,
874
+ "justify_content": null,
875
+ "justify_items": null,
876
+ "left": null,
877
+ "margin": null,
878
+ "max_height": null,
879
+ "max_width": null,
880
+ "min_height": null,
881
+ "min_width": null,
882
+ "object_fit": null,
883
+ "object_position": null,
884
+ "order": null,
885
+ "overflow": null,
886
+ "overflow_x": null,
887
+ "overflow_y": null,
888
+ "padding": null,
889
+ "right": null,
890
+ "top": null,
891
+ "visibility": null,
892
+ "width": null
893
+ }
894
+ },
895
+ "3a9b29c6754b4929bc2849addf5470ab": {
896
+ "model_module": "@jupyter-widgets/controls",
897
+ "model_name": "DescriptionStyleModel",
898
+ "model_module_version": "1.5.0",
899
+ "state": {
900
+ "_model_module": "@jupyter-widgets/controls",
901
+ "_model_module_version": "1.5.0",
902
+ "_model_name": "DescriptionStyleModel",
903
+ "_view_count": null,
904
+ "_view_module": "@jupyter-widgets/base",
905
+ "_view_module_version": "1.2.0",
906
+ "_view_name": "StyleView",
907
+ "description_width": ""
908
+ }
909
+ },
910
+ "f44a5f3e7f8b4d2c947a5596e4915124": {
911
+ "model_module": "@jupyter-widgets/base",
912
+ "model_name": "LayoutModel",
913
+ "model_module_version": "1.2.0",
914
+ "state": {
915
+ "_model_module": "@jupyter-widgets/base",
916
+ "_model_module_version": "1.2.0",
917
+ "_model_name": "LayoutModel",
918
+ "_view_count": null,
919
+ "_view_module": "@jupyter-widgets/base",
920
+ "_view_module_version": "1.2.0",
921
+ "_view_name": "LayoutView",
922
+ "align_content": null,
923
+ "align_items": null,
924
+ "align_self": null,
925
+ "border": null,
926
+ "bottom": null,
927
+ "display": null,
928
+ "flex": null,
929
+ "flex_flow": null,
930
+ "grid_area": null,
931
+ "grid_auto_columns": null,
932
+ "grid_auto_flow": null,
933
+ "grid_auto_rows": null,
934
+ "grid_column": null,
935
+ "grid_gap": null,
936
+ "grid_row": null,
937
+ "grid_template_areas": null,
938
+ "grid_template_columns": null,
939
+ "grid_template_rows": null,
940
+ "height": null,
941
+ "justify_content": null,
942
+ "justify_items": null,
943
+ "left": null,
944
+ "margin": null,
945
+ "max_height": null,
946
+ "max_width": null,
947
+ "min_height": null,
948
+ "min_width": null,
949
+ "object_fit": null,
950
+ "object_position": null,
951
+ "order": null,
952
+ "overflow": null,
953
+ "overflow_x": null,
954
+ "overflow_y": null,
955
+ "padding": null,
956
+ "right": null,
957
+ "top": null,
958
+ "visibility": null,
959
+ "width": null
960
+ }
961
+ },
962
+ "56d13847df33476da1d463470ba84722": {
963
+ "model_module": "@jupyter-widgets/controls",
964
+ "model_name": "ProgressStyleModel",
965
+ "model_module_version": "1.5.0",
966
+ "state": {
967
+ "_model_module": "@jupyter-widgets/controls",
968
+ "_model_module_version": "1.5.0",
969
+ "_model_name": "ProgressStyleModel",
970
+ "_view_count": null,
971
+ "_view_module": "@jupyter-widgets/base",
972
+ "_view_module_version": "1.2.0",
973
+ "_view_name": "StyleView",
974
+ "bar_color": null,
975
+ "description_width": ""
976
+ }
977
+ },
978
+ "4532aae1ae1842a19695c55bf13458c2": {
979
+ "model_module": "@jupyter-widgets/base",
980
+ "model_name": "LayoutModel",
981
+ "model_module_version": "1.2.0",
982
+ "state": {
983
+ "_model_module": "@jupyter-widgets/base",
984
+ "_model_module_version": "1.2.0",
985
+ "_model_name": "LayoutModel",
986
+ "_view_count": null,
987
+ "_view_module": "@jupyter-widgets/base",
988
+ "_view_module_version": "1.2.0",
989
+ "_view_name": "LayoutView",
990
+ "align_content": null,
991
+ "align_items": null,
992
+ "align_self": null,
993
+ "border": null,
994
+ "bottom": null,
995
+ "display": null,
996
+ "flex": null,
997
+ "flex_flow": null,
998
+ "grid_area": null,
999
+ "grid_auto_columns": null,
1000
+ "grid_auto_flow": null,
1001
+ "grid_auto_rows": null,
1002
+ "grid_column": null,
1003
+ "grid_gap": null,
1004
+ "grid_row": null,
1005
+ "grid_template_areas": null,
1006
+ "grid_template_columns": null,
1007
+ "grid_template_rows": null,
1008
+ "height": null,
1009
+ "justify_content": null,
1010
+ "justify_items": null,
1011
+ "left": null,
1012
+ "margin": null,
1013
+ "max_height": null,
1014
+ "max_width": null,
1015
+ "min_height": null,
1016
+ "min_width": null,
1017
+ "object_fit": null,
1018
+ "object_position": null,
1019
+ "order": null,
1020
+ "overflow": null,
1021
+ "overflow_x": null,
1022
+ "overflow_y": null,
1023
+ "padding": null,
1024
+ "right": null,
1025
+ "top": null,
1026
+ "visibility": null,
1027
+ "width": null
1028
+ }
1029
+ },
1030
+ "66596e16abbf4561997ec9689b08fe01": {
1031
+ "model_module": "@jupyter-widgets/controls",
1032
+ "model_name": "DescriptionStyleModel",
1033
+ "model_module_version": "1.5.0",
1034
+ "state": {
1035
+ "_model_module": "@jupyter-widgets/controls",
1036
+ "_model_module_version": "1.5.0",
1037
+ "_model_name": "DescriptionStyleModel",
1038
+ "_view_count": null,
1039
+ "_view_module": "@jupyter-widgets/base",
1040
+ "_view_module_version": "1.2.0",
1041
+ "_view_name": "StyleView",
1042
+ "description_width": ""
1043
+ }
1044
+ }
1045
+ }
1046
+ }
1047
+ },
1048
+ "cells": [
1049
+ {
1050
+ "cell_type": "code",
1051
+ "execution_count": 1,
1052
+ "metadata": {
1053
+ "id": "SQmVx0tV0YAq"
1054
+ },
1055
+ "outputs": [],
1056
+ "source": [
1057
+ "!pip install -q transformers datasets pandas scikit-learn"
1058
+ ]
1059
+ },
1060
+ {
1061
+ "cell_type": "code",
1062
+ "source": [
1063
+ "import pandas as pd\n",
1064
+ "df = pd.read_csv(\"bengali_restaurant_qa.csv\", quotechar='\"', encoding=\"utf-8\")\n",
1065
+ "df = df[[\"input\", \"target\"]]\n",
1066
+ "df.head()\n"
1067
+ ],
1068
+ "metadata": {
1069
+ "colab": {
1070
+ "base_uri": "https://localhost:8080/",
1071
+ "height": 206
1072
+ },
1073
+ "id": "4E0YWme90jua",
1074
+ "outputId": "00813efe-a5eb-4c27-8912-7a4dba08fd04"
1075
+ },
1076
+ "execution_count": 6,
1077
+ "outputs": [
1078
+ {
1079
+ "output_type": "execute_result",
1080
+ "data": {
1081
+ "text/plain": [
1082
+ " input \\\n",
1083
+ "0 প্রশ্ন: ফোনে রিজার্ভ করা যায়? \n",
1084
+ "1 প্রশ্ন: রেস্টুরেন্টে মাস্ক বাধ্যতামূলক? \n",
1085
+ "2 প্রশ্ন: মাছ ভুনা কি পাওয়া যায়? \n",
1086
+ "3 প্রশ্ন: ছুটির দিনে কি খোলা থাকে? \n",
1087
+ "4 প্রশ্ন: খাবারের দাম কেমন? \n",
1088
+ "\n",
1089
+ " target \n",
1090
+ "0 হ্যাঁ, আমাদের হটলাইন নম্বরে ফোন করলেই রিজার্ভ ... \n",
1091
+ "1 হ্যাঁ, মাস্ক বাধ্যতামূলক। \n",
1092
+ "2 হ্যাঁ, আমাদের মেনুতে মাছ ভুনা রয়েছে। \n",
1093
+ "3 হ্যাঁ, আমরা ছুটির দিনেও খোলা থাকি। \n",
1094
+ "4 খাবারের দাম ১০০ টাকা থেকে শুরু। "
1095
+ ],
1096
+ "text/html": [
1097
+ "\n",
1098
+ " <div id=\"df-725b8b89-a10b-4045-8026-84dda36f435e\" class=\"colab-df-container\">\n",
1099
+ " <div>\n",
1100
+ "<style scoped>\n",
1101
+ " .dataframe tbody tr th:only-of-type {\n",
1102
+ " vertical-align: middle;\n",
1103
+ " }\n",
1104
+ "\n",
1105
+ " .dataframe tbody tr th {\n",
1106
+ " vertical-align: top;\n",
1107
+ " }\n",
1108
+ "\n",
1109
+ " .dataframe thead th {\n",
1110
+ " text-align: right;\n",
1111
+ " }\n",
1112
+ "</style>\n",
1113
+ "<table border=\"1\" class=\"dataframe\">\n",
1114
+ " <thead>\n",
1115
+ " <tr style=\"text-align: right;\">\n",
1116
+ " <th></th>\n",
1117
+ " <th>input</th>\n",
1118
+ " <th>target</th>\n",
1119
+ " </tr>\n",
1120
+ " </thead>\n",
1121
+ " <tbody>\n",
1122
+ " <tr>\n",
1123
+ " <th>0</th>\n",
1124
+ " <td>প্রশ্ন: ফোনে রিজার্ভ করা যায়?</td>\n",
1125
+ " <td>হ্যাঁ, আমাদের হটলাইন নম্বরে ফোন করলেই রিজার্ভ ...</td>\n",
1126
+ " </tr>\n",
1127
+ " <tr>\n",
1128
+ " <th>1</th>\n",
1129
+ " <td>প্রশ্ন: রেস্টুরেন্টে মাস্ক বাধ্যতামূলক?</td>\n",
1130
+ " <td>হ্যাঁ, মাস্ক বাধ্যতামূলক।</td>\n",
1131
+ " </tr>\n",
1132
+ " <tr>\n",
1133
+ " <th>2</th>\n",
1134
+ " <td>প্রশ্ন: মাছ ভুনা কি পাওয়া যায়?</td>\n",
1135
+ " <td>হ্যাঁ, আমাদের মেনুতে মাছ ভুনা রয়েছে।</td>\n",
1136
+ " </tr>\n",
1137
+ " <tr>\n",
1138
+ " <th>3</th>\n",
1139
+ " <td>প্রশ্ন: ছুটির দিনে কি খোলা থাকে?</td>\n",
1140
+ " <td>হ্যাঁ, আমরা ছুটির দিনেও খোলা থাকি।</td>\n",
1141
+ " </tr>\n",
1142
+ " <tr>\n",
1143
+ " <th>4</th>\n",
1144
+ " <td>প্রশ্ন: খাবারের দাম কেমন?</td>\n",
1145
+ " <td>খাবারের দাম ১০০ টাকা থেকে শুরু।</td>\n",
1146
+ " </tr>\n",
1147
+ " </tbody>\n",
1148
+ "</table>\n",
1149
+ "</div>\n",
1150
+ " <div class=\"colab-df-buttons\">\n",
1151
+ "\n",
1152
+ " <div class=\"colab-df-container\">\n",
1153
+ " <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-725b8b89-a10b-4045-8026-84dda36f435e')\"\n",
1154
+ " title=\"Convert this dataframe to an interactive table.\"\n",
1155
+ " style=\"display:none;\">\n",
1156
+ "\n",
1157
+ " <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
1158
+ " <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
1159
+ " </svg>\n",
1160
+ " </button>\n",
1161
+ "\n",
1162
+ " <style>\n",
1163
+ " .colab-df-container {\n",
1164
+ " display:flex;\n",
1165
+ " gap: 12px;\n",
1166
+ " }\n",
1167
+ "\n",
1168
+ " .colab-df-convert {\n",
1169
+ " background-color: #E8F0FE;\n",
1170
+ " border: none;\n",
1171
+ " border-radius: 50%;\n",
1172
+ " cursor: pointer;\n",
1173
+ " display: none;\n",
1174
+ " fill: #1967D2;\n",
1175
+ " height: 32px;\n",
1176
+ " padding: 0 0 0 0;\n",
1177
+ " width: 32px;\n",
1178
+ " }\n",
1179
+ "\n",
1180
+ " .colab-df-convert:hover {\n",
1181
+ " background-color: #E2EBFA;\n",
1182
+ " box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
1183
+ " fill: #174EA6;\n",
1184
+ " }\n",
1185
+ "\n",
1186
+ " .colab-df-buttons div {\n",
1187
+ " margin-bottom: 4px;\n",
1188
+ " }\n",
1189
+ "\n",
1190
+ " [theme=dark] .colab-df-convert {\n",
1191
+ " background-color: #3B4455;\n",
1192
+ " fill: #D2E3FC;\n",
1193
+ " }\n",
1194
+ "\n",
1195
+ " [theme=dark] .colab-df-convert:hover {\n",
1196
+ " background-color: #434B5C;\n",
1197
+ " box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
1198
+ " filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
1199
+ " fill: #FFFFFF;\n",
1200
+ " }\n",
1201
+ " </style>\n",
1202
+ "\n",
1203
+ " <script>\n",
1204
+ " const buttonEl =\n",
1205
+ " document.querySelector('#df-725b8b89-a10b-4045-8026-84dda36f435e button.colab-df-convert');\n",
1206
+ " buttonEl.style.display =\n",
1207
+ " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
1208
+ "\n",
1209
+ " async function convertToInteractive(key) {\n",
1210
+ " const element = document.querySelector('#df-725b8b89-a10b-4045-8026-84dda36f435e');\n",
1211
+ " const dataTable =\n",
1212
+ " await google.colab.kernel.invokeFunction('convertToInteractive',\n",
1213
+ " [key], {});\n",
1214
+ " if (!dataTable) return;\n",
1215
+ "\n",
1216
+ " const docLinkHtml = 'Like what you see? Visit the ' +\n",
1217
+ " '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
1218
+ " + ' to learn more about interactive tables.';\n",
1219
+ " element.innerHTML = '';\n",
1220
+ " dataTable['output_type'] = 'display_data';\n",
1221
+ " await google.colab.output.renderOutput(dataTable, element);\n",
1222
+ " const docLink = document.createElement('div');\n",
1223
+ " docLink.innerHTML = docLinkHtml;\n",
1224
+ " element.appendChild(docLink);\n",
1225
+ " }\n",
1226
+ " </script>\n",
1227
+ " </div>\n",
1228
+ "\n",
1229
+ "\n",
1230
+ " <div id=\"df-137925ad-495d-405f-947c-b00844c0cbb0\">\n",
1231
+ " <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-137925ad-495d-405f-947c-b00844c0cbb0')\"\n",
1232
+ " title=\"Suggest charts\"\n",
1233
+ " style=\"display:none;\">\n",
1234
+ "\n",
1235
+ "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
1236
+ " width=\"24px\">\n",
1237
+ " <g>\n",
1238
+ " <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
1239
+ " </g>\n",
1240
+ "</svg>\n",
1241
+ " </button>\n",
1242
+ "\n",
1243
+ "<style>\n",
1244
+ " .colab-df-quickchart {\n",
1245
+ " --bg-color: #E8F0FE;\n",
1246
+ " --fill-color: #1967D2;\n",
1247
+ " --hover-bg-color: #E2EBFA;\n",
1248
+ " --hover-fill-color: #174EA6;\n",
1249
+ " --disabled-fill-color: #AAA;\n",
1250
+ " --disabled-bg-color: #DDD;\n",
1251
+ " }\n",
1252
+ "\n",
1253
+ " [theme=dark] .colab-df-quickchart {\n",
1254
+ " --bg-color: #3B4455;\n",
1255
+ " --fill-color: #D2E3FC;\n",
1256
+ " --hover-bg-color: #434B5C;\n",
1257
+ " --hover-fill-color: #FFFFFF;\n",
1258
+ " --disabled-bg-color: #3B4455;\n",
1259
+ " --disabled-fill-color: #666;\n",
1260
+ " }\n",
1261
+ "\n",
1262
+ " .colab-df-quickchart {\n",
1263
+ " background-color: var(--bg-color);\n",
1264
+ " border: none;\n",
1265
+ " border-radius: 50%;\n",
1266
+ " cursor: pointer;\n",
1267
+ " display: none;\n",
1268
+ " fill: var(--fill-color);\n",
1269
+ " height: 32px;\n",
1270
+ " padding: 0;\n",
1271
+ " width: 32px;\n",
1272
+ " }\n",
1273
+ "\n",
1274
+ " .colab-df-quickchart:hover {\n",
1275
+ " background-color: var(--hover-bg-color);\n",
1276
+ " box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
1277
+ " fill: var(--button-hover-fill-color);\n",
1278
+ " }\n",
1279
+ "\n",
1280
+ " .colab-df-quickchart-complete:disabled,\n",
1281
+ " .colab-df-quickchart-complete:disabled:hover {\n",
1282
+ " background-color: var(--disabled-bg-color);\n",
1283
+ " fill: var(--disabled-fill-color);\n",
1284
+ " box-shadow: none;\n",
1285
+ " }\n",
1286
+ "\n",
1287
+ " .colab-df-spinner {\n",
1288
+ " border: 2px solid var(--fill-color);\n",
1289
+ " border-color: transparent;\n",
1290
+ " border-bottom-color: var(--fill-color);\n",
1291
+ " animation:\n",
1292
+ " spin 1s steps(1) infinite;\n",
1293
+ " }\n",
1294
+ "\n",
1295
+ " @keyframes spin {\n",
1296
+ " 0% {\n",
1297
+ " border-color: transparent;\n",
1298
+ " border-bottom-color: var(--fill-color);\n",
1299
+ " border-left-color: var(--fill-color);\n",
1300
+ " }\n",
1301
+ " 20% {\n",
1302
+ " border-color: transparent;\n",
1303
+ " border-left-color: var(--fill-color);\n",
1304
+ " border-top-color: var(--fill-color);\n",
1305
+ " }\n",
1306
+ " 30% {\n",
1307
+ " border-color: transparent;\n",
1308
+ " border-left-color: var(--fill-color);\n",
1309
+ " border-top-color: var(--fill-color);\n",
1310
+ " border-right-color: var(--fill-color);\n",
1311
+ " }\n",
1312
+ " 40% {\n",
1313
+ " border-color: transparent;\n",
1314
+ " border-right-color: var(--fill-color);\n",
1315
+ " border-top-color: var(--fill-color);\n",
1316
+ " }\n",
1317
+ " 60% {\n",
1318
+ " border-color: transparent;\n",
1319
+ " border-right-color: var(--fill-color);\n",
1320
+ " }\n",
1321
+ " 80% {\n",
1322
+ " border-color: transparent;\n",
1323
+ " border-right-color: var(--fill-color);\n",
1324
+ " border-bottom-color: var(--fill-color);\n",
1325
+ " }\n",
1326
+ " 90% {\n",
1327
+ " border-color: transparent;\n",
1328
+ " border-bottom-color: var(--fill-color);\n",
1329
+ " }\n",
1330
+ " }\n",
1331
+ "</style>\n",
1332
+ "\n",
1333
+ " <script>\n",
1334
+ " async function quickchart(key) {\n",
1335
+ " const quickchartButtonEl =\n",
1336
+ " document.querySelector('#' + key + ' button');\n",
1337
+ " quickchartButtonEl.disabled = true; // To prevent multiple clicks.\n",
1338
+ " quickchartButtonEl.classList.add('colab-df-spinner');\n",
1339
+ " try {\n",
1340
+ " const charts = await google.colab.kernel.invokeFunction(\n",
1341
+ " 'suggestCharts', [key], {});\n",
1342
+ " } catch (error) {\n",
1343
+ " console.error('Error during call to suggestCharts:', error);\n",
1344
+ " }\n",
1345
+ " quickchartButtonEl.classList.remove('colab-df-spinner');\n",
1346
+ " quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
1347
+ " }\n",
1348
+ " (() => {\n",
1349
+ " let quickchartButtonEl =\n",
1350
+ " document.querySelector('#df-137925ad-495d-405f-947c-b00844c0cbb0 button');\n",
1351
+ " quickchartButtonEl.style.display =\n",
1352
+ " google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
1353
+ " })();\n",
1354
+ " </script>\n",
1355
+ " </div>\n",
1356
+ "\n",
1357
+ " </div>\n",
1358
+ " </div>\n"
1359
+ ],
1360
+ "application/vnd.google.colaboratory.intrinsic+json": {
1361
+ "type": "dataframe",
1362
+ "variable_name": "df",
1363
+ "summary": "{\n \"name\": \"df\",\n \"rows\": 202,\n \"fields\": [\n {\n \"column\": \"input\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 202,\n \"samples\": [\n \"\\u09aa\\u09cd\\u09b0\\u09b6\\u09cd\\u09a8: \\u0995\\u09ab\\u09bf \\u09a1\\u09bf\\u0995\\u09cd\\u09af\\u09be\\u09ab?\",\n \"\\u09aa\\u09cd\\u09b0\\u09b6\\u09cd\\u09a8: \\u09aa\\u09b0\\u09bf\\u09b7\\u09cd\\u0995\\u09be\\u09b0 \\u09aa\\u09b0\\u09bf\\u099a\\u09cd\\u099b\\u09a8\\u09cd\\u09a8\\u09a4\\u09be \\u0995\\u09c7\\u09ae\\u09a8?\",\n \"\\u09aa\\u09cd\\u09b0\\u09b6\\u09cd\\u09a8: \\u0997\\u09cd\\u09b0\\u09c1\\u09aa \\u09ac\\u09c1\\u0995\\u09bf\\u0982 \\u098f\\u09b0 \\u09b8\\u09c1\\u09ac\\u09bf\\u09a7\\u09be \\u0986\\u099b\\u09c7?\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"target\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 202,\n \"samples\": [\n \"\\u09b9\\u09cd\\u09af\\u09be\\u0981, \\u09a1\\u09bf\\u0995\\u09cd\\u09af\\u09be\\u09ab \\u0995\\u09ab\\u09bf\\u09b0 \\u09ac\\u09cd\\u09af\\u09ac\\u09b8\\u09cd\\u09a5\\u09be \\u0986\\u099b\\u09c7\\u0964\",\n \"\\u0986\\u09ae\\u09b0\\u09be \\u09b8\\u09b0\\u09cd\\u09ac\\u09cb\\u099a\\u09cd\\u099a \\u09ae\\u09be\\u09a8\\u09c7\\u09b0 \\u09aa\\u09b0\\u09bf\\u09b7\\u09cd\\u0995\\u09be\\u09b0 \\u09aa\\u09b0\\u09bf\\u099a\\u09cd\\u099b\\u09a8\\u09cd\\u09a8\\u09a4\\u09be \\u09a8\\u09bf\\u09b6\\u09cd\\u099a\\u09bf\\u09a4 \\u0995\\u09b0\\u09bf\\u0964\",\n \"\\u09b9\\u09cd\\u09af\\u09be\\u0981, \\u09e7\\u09e6 \\u099c\\u09a8\\u09c7\\u09b0 \\u09ac\\u09c7\\u09b6\\u09bf \\u0997\\u09cd\\u09b0\\u09c1\\u09aa\\u09c7\\u09b0 \\u099c\\u09a8\\u09cd\\u09af \\u09aa\\u09cd\\u09b0\\u09bf-\\u09ac\\u09c1\\u0995\\u09bf\\u0982 \\u0995\\u09b0\\u09a4\\u09c7 \\u09b9\\u09ac\\u09c7\\u0964\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}"
1364
+ }
1365
+ },
1366
+ "metadata": {},
1367
+ "execution_count": 6
1368
+ }
1369
+ ]
1370
+ },
1371
+ {
1372
+ "cell_type": "code",
1373
+ "source": [
1374
+ "\n",
1375
+ "# 🔤 Tokenization\n",
1376
+ "from transformers import AutoTokenizer\n",
1377
+ "from datasets import Dataset\n",
1378
+ "\n",
1379
+ "model_name = \"google/mt5-small\"\n",
1380
+ "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
1381
+ "\n",
1382
+ "max_input_length = 128\n",
1383
+ "max_target_length = 128\n",
1384
+ "\n",
1385
+ "df['input'] = df['input'].apply(lambda x: \"<bn> \" + x)\n",
1386
+ "df['target'] = df['target'].apply(lambda x: \"<bn> \" + x)\n",
1387
+ "\n",
1388
+ "dataset = Dataset.from_pandas(df)\n",
1389
+ "\n",
1390
+ "def tokenize(batch):\n",
1391
+ " input_enc = tokenizer(batch[\"input\"], padding=\"max_length\", truncation=True, max_length=max_input_length)\n",
1392
+ " target_enc = tokenizer(batch[\"target\"], padding=\"max_length\", truncation=True, max_length=max_target_length)\n",
1393
+ "\n",
1394
+ " labels = target_enc[\"input_ids\"]\n",
1395
+ " labels = [[(token if token != tokenizer.pad_token_id else -100) for token in label] for label in labels]\n",
1396
+ "\n",
1397
+ " print(\"Sample labels:\", labels[0]) # Debug print\n",
1398
+ " input_enc[\"labels\"] = labels\n",
1399
+ " return input_enc\n",
1400
+ "\n",
1401
+ "\n",
1402
+ "tokenized_dataset = dataset.map(tokenize, batched=True)\n",
1403
+ "\n"
1404
+ ],
1405
+ "metadata": {
1406
+ "colab": {
1407
+ "base_uri": "https://localhost:8080/",
1408
+ "height": 121,
1409
+ "referenced_widgets": [
1410
+ "6731bf4c44b04418a3e92162bf339b4d",
1411
+ "7f292c9fb40a43cea617cb2af8cf6d16",
1412
+ "5cbd9bb2715d46e7ba22e559d5b75c96",
1413
+ "2ab10bd157ee4e568c10374e4720e676",
1414
+ "e7f1d0472dbc41ababc2d4153f13d2b4",
1415
+ "abb5f0f1c1694961957f32824d14ccf5",
1416
+ "acad57f3134c46e7b08af70d9d72ece9",
1417
+ "0fd2902a45474e09832d43da534e5540",
1418
+ "74f3cd48c2504464a2ef14f9c6f7730b",
1419
+ "0031511abb9b459a9b9e1cded6186287",
1420
+ "b30964047ced437aa46dd0b654270bbd"
1421
+ ]
1422
+ },
1423
+ "id": "otLZo4OK0sxK",
1424
+ "outputId": "f92c8307-055b-47ff-b9c3-77f6d5867e37"
1425
+ },
1426
+ "execution_count": 32,
1427
+ "outputs": [
1428
+ {
1429
+ "output_type": "stream",
1430
+ "name": "stderr",
1431
+ "text": [
1432
+ "/usr/local/lib/python3.11/dist-packages/transformers/convert_slow_tokenizer.py:564: UserWarning: The sentencepiece tokenizer that you are converting to a fast tokenizer uses the byte fallback option which is not implemented in the fast tokenizers. In practice this means that the fast version of the tokenizer can produce unknown tokens whereas the sentencepiece version would have converted these unknown tokens into a sequence of byte tokens matching the original piece of text.\n",
1433
+ " warnings.warn(\n"
1434
+ ]
1435
+ },
1436
+ {
1437
+ "output_type": "display_data",
1438
+ "data": {
1439
+ "text/plain": [
1440
+ "Map: 0%| | 0/202 [00:00<?, ? examples/s]"
1441
+ ],
1442
+ "application/vnd.jupyter.widget-view+json": {
1443
+ "version_major": 2,
1444
+ "version_minor": 0,
1445
+ "model_id": "6731bf4c44b04418a3e92162bf339b4d"
1446
+ }
1447
+ },
1448
+ "metadata": {}
1449
+ },
1450
+ {
1451
+ "output_type": "stream",
1452
+ "name": "stdout",
1453
+ "text": [
1454
+ "Sample labels: [1042, 316, 272, 669, 1042, 316, 272, 669, 1042, 316, 272, 669, 140227, 8460, 261, 5998, 9977, 2326, 4402, 67283, 259, 1152, 22250, 994, 259, 40780, 1152, 2212, 2496, 1413, 68488, 16506, 96544, 259, 5399, 17275, 378, 1, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100]\n"
1455
+ ]
1456
+ }
1457
+ ]
1458
+ },
1459
+ {
1460
+ "cell_type": "code",
1461
+ "source": [
1462
+ "print(tokenized_dataset[0][\"labels\"])\n",
1463
+ "print(\"Number of valid tokens:\", sum(t != -100 for t in tokenized_dataset[0][\"labels\"]))\n"
1464
+ ],
1465
+ "metadata": {
1466
+ "colab": {
1467
+ "base_uri": "https://localhost:8080/"
1468
+ },
1469
+ "id": "PvVlr7u37yGu",
1470
+ "outputId": "b8b1dcb4-a613-4865-ee4f-c359fd021d41"
1471
+ },
1472
+ "execution_count": 33,
1473
+ "outputs": [
1474
+ {
1475
+ "output_type": "stream",
1476
+ "name": "stdout",
1477
+ "text": [
1478
+ "[1042, 316, 272, 669, 1042, 316, 272, 669, 1042, 316, 272, 669, 140227, 8460, 261, 5998, 9977, 2326, 4402, 67283, 259, 1152, 22250, 994, 259, 40780, 1152, 2212, 2496, 1413, 68488, 16506, 96544, 259, 5399, 17275, 378, 1, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100, -100]\n",
1479
+ "Number of valid tokens: 38\n"
1480
+ ]
1481
+ }
1482
+ ]
1483
+ },
1484
+ {
1485
+ "cell_type": "code",
1486
+ "source": [
1487
+ "\n",
1488
+ "from datasets import Dataset\n",
1489
+ "from datasets import load_metric\n",
1490
+ "\n",
1491
+ "# Load dataset from pandas df\n",
1492
+ "dataset = Dataset.from_pandas(df)\n",
1493
+ "\n",
1494
+ "# Split\n",
1495
+ "split_dataset = dataset.train_test_split(test_size=0.2, seed=42)\n",
1496
+ "train_dataset = split_dataset['train']\n",
1497
+ "eval_dataset = split_dataset['test']\n",
1498
+ "\n",
1499
+ "# Tokenize function as before\n",
1500
+ "def tokenize(batch):\n",
1501
+ " input_enc = tokenizer(batch['input'], padding=\"max_length\", truncation=True, max_length=64)\n",
1502
+ " target_enc = tokenizer(batch['target'], padding=\"max_length\", truncation=True, max_length=64)\n",
1503
+ " input_enc['labels'] = target_enc['input_ids']\n",
1504
+ " return input_enc\n",
1505
+ "\n",
1506
+ "train_dataset = train_dataset.map(tokenize, batched=True)\n",
1507
+ "eval_dataset = eval_dataset.map(tokenize, batched=True)\n",
1508
+ "\n",
1509
+ "\n",
1510
+ "\n"
1511
+ ],
1512
+ "metadata": {
1513
+ "colab": {
1514
+ "base_uri": "https://localhost:8080/",
1515
+ "height": 116,
1516
+ "referenced_widgets": [
1517
+ "707c911f3f284ca694434c66a5d32164",
1518
+ "5d09f1b981fe40408a510d10351beead",
1519
+ "ef27890e503a449f9583d960f244cfb8",
1520
+ "c626325b0dee40ee861315bb5fb176c7",
1521
+ "643bd0b694994321b4c83ac36448a020",
1522
+ "4531e52322314195bb3ab8ae68d3a99e",
1523
+ "81ecb5431f2b4d53811abc584b30de70",
1524
+ "2a8bea160baf4fdb94d36ec7b2e48abc",
1525
+ "ac0daaf6c7634a3ebe224a6ec0d53fed",
1526
+ "7a2e64f9ab664a0884e176ad6e126ce3",
1527
+ "b1eabce5ada443bf803773ba90f03d74",
1528
+ "24f4f3f3e2c54bc789d30d363a93095e",
1529
+ "b220dd31400349b1a09e1244574b8fd2",
1530
+ "cdce2e98b8584f12a533144e07387eaa",
1531
+ "db62ab11b6464508baa4799e7c1c1e16",
1532
+ "174904c1cbb3475193a99498f870ec21",
1533
+ "9fe9296adae642d380e09e71dc9bfce0",
1534
+ "3a9b29c6754b4929bc2849addf5470ab",
1535
+ "f44a5f3e7f8b4d2c947a5596e4915124",
1536
+ "56d13847df33476da1d463470ba84722",
1537
+ "4532aae1ae1842a19695c55bf13458c2",
1538
+ "66596e16abbf4561997ec9689b08fe01"
1539
+ ]
1540
+ },
1541
+ "id": "p80lltzD1-Rj",
1542
+ "outputId": "fcf0f192-e104-4ace-b963-533dcc6d453c"
1543
+ },
1544
+ "execution_count": 28,
1545
+ "outputs": [
1546
+ {
1547
+ "output_type": "display_data",
1548
+ "data": {
1549
+ "text/plain": [
1550
+ "Map: 0%| | 0/161 [00:00<?, ? examples/s]"
1551
+ ],
1552
+ "application/vnd.jupyter.widget-view+json": {
1553
+ "version_major": 2,
1554
+ "version_minor": 0,
1555
+ "model_id": "707c911f3f284ca694434c66a5d32164"
1556
+ }
1557
+ },
1558
+ "metadata": {}
1559
+ },
1560
+ {
1561
+ "output_type": "display_data",
1562
+ "data": {
1563
+ "text/plain": [
1564
+ "Map: 0%| | 0/41 [00:00<?, ? examples/s]"
1565
+ ],
1566
+ "application/vnd.jupyter.widget-view+json": {
1567
+ "version_major": 2,
1568
+ "version_minor": 0,
1569
+ "model_id": "24f4f3f3e2c54bc789d30d363a93095e"
1570
+ }
1571
+ },
1572
+ "metadata": {}
1573
+ },
1574
+ {
1575
+ "output_type": "stream",
1576
+ "name": "stderr",
1577
+ "text": [
1578
+ "/tmp/ipython-input-28-2680285985.py:22: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.\n",
1579
+ " trainer = Trainer(\n"
1580
+ ]
1581
+ }
1582
+ ]
1583
+ },
1584
+ {
1585
+ "cell_type": "code",
1586
+ "source": [
1587
+ "\n",
1588
+ "# 🧠 Load Pretrained Model\n",
1589
+ "from transformers import AutoModelForSeq2SeqLM\n",
1590
+ "\n",
1591
+ "model = AutoModelForSeq2SeqLM.from_pretrained(model_name)\n"
1592
+ ],
1593
+ "metadata": {
1594
+ "id": "cOzdYogx2Lvr"
1595
+ },
1596
+ "execution_count": 21,
1597
+ "outputs": []
1598
+ },
1599
+ {
1600
+ "cell_type": "code",
1601
+ "source": [
1602
+ "\n",
1603
+ "# ⚙️ Training Setup\n",
1604
+ "from transformers import TrainingArguments, Trainer\n",
1605
+ "\n",
1606
+ "training_args = TrainingArguments(\n",
1607
+ " output_dir=\"./bengali-mt5-chatbot\",\n",
1608
+ " per_device_train_batch_size=4,\n",
1609
+ " num_train_epochs=10,\n",
1610
+ " learning_rate=5e-5,\n",
1611
+ " logging_steps=10,\n",
1612
+ " save_total_limit=2,\n",
1613
+ " save_steps=50,\n",
1614
+ " eval_strategy=\"steps\",\n",
1615
+ " eval_steps=50,\n",
1616
+ " fp16=True,\n",
1617
+ ")\n",
1618
+ "\n",
1619
+ "trainer = Trainer(\n",
1620
+ " model=model,\n",
1621
+ " args=training_args,\n",
1622
+ " train_dataset=train_dataset,\n",
1623
+ " eval_dataset=eval_dataset,\n",
1624
+ " tokenizer=tokenizer\n",
1625
+ ")\n",
1626
+ "\n",
1627
+ "trainer.train()\n"
1628
+ ],
1629
+ "metadata": {
1630
+ "colab": {
1631
+ "base_uri": "https://localhost:8080/",
1632
+ "height": 396
1633
+ },
1634
+ "id": "TJUlJySX2Opk",
1635
+ "outputId": "14486d25-25a3-4537-a2e2-2fde681e92f9"
1636
+ },
1637
+ "execution_count": 30,
1638
+ "outputs": [
1639
+ {
1640
+ "output_type": "stream",
1641
+ "name": "stderr",
1642
+ "text": [
1643
+ "/tmp/ipython-input-30-1247104863.py:17: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.\n",
1644
+ " trainer = Trainer(\n"
1645
+ ]
1646
+ },
1647
+ {
1648
+ "output_type": "display_data",
1649
+ "data": {
1650
+ "text/plain": [
1651
+ "<IPython.core.display.HTML object>"
1652
+ ],
1653
+ "text/html": [
1654
+ "\n",
1655
+ " <div>\n",
1656
+ " \n",
1657
+ " <progress value='410' max='410' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
1658
+ " [410/410 06:44, Epoch 10/10]\n",
1659
+ " </div>\n",
1660
+ " <table border=\"1\" class=\"dataframe\">\n",
1661
+ " <thead>\n",
1662
+ " <tr style=\"text-align: left;\">\n",
1663
+ " <th>Step</th>\n",
1664
+ " <th>Training Loss</th>\n",
1665
+ " <th>Validation Loss</th>\n",
1666
+ " </tr>\n",
1667
+ " </thead>\n",
1668
+ " <tbody>\n",
1669
+ " <tr>\n",
1670
+ " <td>50</td>\n",
1671
+ " <td>0.000000</td>\n",
1672
+ " <td>nan</td>\n",
1673
+ " </tr>\n",
1674
+ " <tr>\n",
1675
+ " <td>100</td>\n",
1676
+ " <td>0.000000</td>\n",
1677
+ " <td>nan</td>\n",
1678
+ " </tr>\n",
1679
+ " <tr>\n",
1680
+ " <td>150</td>\n",
1681
+ " <td>0.000000</td>\n",
1682
+ " <td>nan</td>\n",
1683
+ " </tr>\n",
1684
+ " <tr>\n",
1685
+ " <td>200</td>\n",
1686
+ " <td>0.000000</td>\n",
1687
+ " <td>nan</td>\n",
1688
+ " </tr>\n",
1689
+ " <tr>\n",
1690
+ " <td>250</td>\n",
1691
+ " <td>0.000000</td>\n",
1692
+ " <td>nan</td>\n",
1693
+ " </tr>\n",
1694
+ " <tr>\n",
1695
+ " <td>300</td>\n",
1696
+ " <td>0.000000</td>\n",
1697
+ " <td>nan</td>\n",
1698
+ " </tr>\n",
1699
+ " <tr>\n",
1700
+ " <td>350</td>\n",
1701
+ " <td>0.000000</td>\n",
1702
+ " <td>nan</td>\n",
1703
+ " </tr>\n",
1704
+ " <tr>\n",
1705
+ " <td>400</td>\n",
1706
+ " <td>0.000000</td>\n",
1707
+ " <td>nan</td>\n",
1708
+ " </tr>\n",
1709
+ " </tbody>\n",
1710
+ "</table><p>"
1711
+ ]
1712
+ },
1713
+ "metadata": {}
1714
+ },
1715
+ {
1716
+ "output_type": "execute_result",
1717
+ "data": {
1718
+ "text/plain": [
1719
+ "TrainOutput(global_step=410, training_loss=0.0, metrics={'train_runtime': 403.0612, 'train_samples_per_second': 3.994, 'train_steps_per_second': 1.017, 'total_flos': 106410875289600.0, 'train_loss': 0.0, 'epoch': 10.0})"
1720
+ ]
1721
+ },
1722
+ "metadata": {},
1723
+ "execution_count": 30
1724
+ }
1725
+ ]
1726
+ },
1727
+ {
1728
+ "cell_type": "code",
1729
+ "source": [
1730
+ "\n",
1731
+ "# 💾 Save the fine-tuned model\n",
1732
+ "model.save_pretrained(\"./bengali-mt5-chatbot\")\n",
1733
+ "tokenizer.save_pretrained(\"./bengali-mt5-chatbot\")\n"
1734
+ ],
1735
+ "metadata": {
1736
+ "colab": {
1737
+ "base_uri": "https://localhost:8080/"
1738
+ },
1739
+ "id": "2-_xpFaY2Wia",
1740
+ "outputId": "a65d8f23-a5b5-452d-a0de-15f96f274ca1"
1741
+ },
1742
+ "execution_count": 34,
1743
+ "outputs": [
1744
+ {
1745
+ "output_type": "execute_result",
1746
+ "data": {
1747
+ "text/plain": [
1748
+ "('./bengali-mt5-chatbot/tokenizer_config.json',\n",
1749
+ " './bengali-mt5-chatbot/special_tokens_map.json',\n",
1750
+ " './bengali-mt5-chatbot/spiece.model',\n",
1751
+ " './bengali-mt5-chatbot/added_tokens.json',\n",
1752
+ " './bengali-mt5-chatbot/tokenizer.json')"
1753
+ ]
1754
+ },
1755
+ "metadata": {},
1756
+ "execution_count": 34
1757
+ }
1758
+ ]
1759
+ },
1760
+ {
1761
+ "cell_type": "code",
1762
+ "source": [
1763
+ "import torch\n",
1764
+ "\n",
1765
+ "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
1766
+ "model.to(device)\n",
1767
+ "model.eval()\n",
1768
+ "\n",
1769
+ "def answer_question(question):\n",
1770
+ " input_text = f\"প্রশ্ন: {question}\"\n",
1771
+ " inputs = tokenizer(input_text, return_tensors=\"pt\", truncation=True, padding=True, max_length=64)\n",
1772
+ " inputs = {k: v.to(device) for k, v in inputs.items()}\n",
1773
+ "\n",
1774
+ " output_ids = model.generate(\n",
1775
+ " **inputs,\n",
1776
+ " max_length=128,\n",
1777
+ " num_beams=4,\n",
1778
+ " early_stopping=True\n",
1779
+ " )\n",
1780
+ "\n",
1781
+ " decoded = tokenizer.decode(output_ids[0], skip_special_tokens=True)\n",
1782
+ " print(\"Generated tokens:\", output_ids[0].tolist())\n",
1783
+ " print(\"Decoded answer:\", decoded)\n",
1784
+ " return decoded\n",
1785
+ "\n",
1786
+ "answer_question(\"রেস্টুরেন্ট কখন খোলে?\")\n"
1787
+ ],
1788
+ "metadata": {
1789
+ "colab": {
1790
+ "base_uri": "https://localhost:8080/",
1791
+ "height": 70
1792
+ },
1793
+ "id": "BJ9XUng23QAr",
1794
+ "outputId": "0fcef38a-3068-47e5-f8d2-f050bc28a498"
1795
+ },
1796
+ "execution_count": 35,
1797
+ "outputs": [
1798
+ {
1799
+ "output_type": "stream",
1800
+ "name": "stdout",
1801
+ "text": [
1802
+ "Generated tokens: [0, 6]\n",
1803
+ "Decoded answer: <0x03>\n"
1804
+ ]
1805
+ },
1806
+ {
1807
+ "output_type": "execute_result",
1808
+ "data": {
1809
+ "text/plain": [
1810
+ "'<0x03>'"
1811
+ ],
1812
+ "application/vnd.google.colaboratory.intrinsic+json": {
1813
+ "type": "string"
1814
+ }
1815
+ },
1816
+ "metadata": {},
1817
+ "execution_count": 35
1818
+ }
1819
+ ]
1820
+ },
1821
+ {
1822
+ "cell_type": "code",
1823
+ "source": [],
1824
+ "metadata": {
1825
+ "id": "VfonlOE83VzF"
1826
+ },
1827
+ "execution_count": null,
1828
+ "outputs": []
1829
+ }
1830
+ ]
1831
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<extra_id_0>",
4
+ "<extra_id_1>",
5
+ "<extra_id_2>",
6
+ "<extra_id_3>",
7
+ "<extra_id_4>",
8
+ "<extra_id_5>",
9
+ "<extra_id_6>",
10
+ "<extra_id_7>",
11
+ "<extra_id_8>",
12
+ "<extra_id_9>",
13
+ "<extra_id_10>",
14
+ "<extra_id_11>",
15
+ "<extra_id_12>",
16
+ "<extra_id_13>",
17
+ "<extra_id_14>",
18
+ "<extra_id_15>",
19
+ "<extra_id_16>",
20
+ "<extra_id_17>",
21
+ "<extra_id_18>",
22
+ "<extra_id_19>",
23
+ "<extra_id_20>",
24
+ "<extra_id_21>",
25
+ "<extra_id_22>",
26
+ "<extra_id_23>",
27
+ "<extra_id_24>",
28
+ "<extra_id_25>",
29
+ "<extra_id_26>",
30
+ "<extra_id_27>",
31
+ "<extra_id_28>",
32
+ "<extra_id_29>",
33
+ "<extra_id_30>",
34
+ "<extra_id_31>",
35
+ "<extra_id_32>",
36
+ "<extra_id_33>",
37
+ "<extra_id_34>",
38
+ "<extra_id_35>",
39
+ "<extra_id_36>",
40
+ "<extra_id_37>",
41
+ "<extra_id_38>",
42
+ "<extra_id_39>",
43
+ "<extra_id_40>",
44
+ "<extra_id_41>",
45
+ "<extra_id_42>",
46
+ "<extra_id_43>",
47
+ "<extra_id_44>",
48
+ "<extra_id_45>",
49
+ "<extra_id_46>",
50
+ "<extra_id_47>",
51
+ "<extra_id_48>",
52
+ "<extra_id_49>",
53
+ "<extra_id_50>",
54
+ "<extra_id_51>",
55
+ "<extra_id_52>",
56
+ "<extra_id_53>",
57
+ "<extra_id_54>",
58
+ "<extra_id_55>",
59
+ "<extra_id_56>",
60
+ "<extra_id_57>",
61
+ "<extra_id_58>",
62
+ "<extra_id_59>",
63
+ "<extra_id_60>",
64
+ "<extra_id_61>",
65
+ "<extra_id_62>",
66
+ "<extra_id_63>",
67
+ "<extra_id_64>",
68
+ "<extra_id_65>",
69
+ "<extra_id_66>",
70
+ "<extra_id_67>",
71
+ "<extra_id_68>",
72
+ "<extra_id_69>",
73
+ "<extra_id_70>",
74
+ "<extra_id_71>",
75
+ "<extra_id_72>",
76
+ "<extra_id_73>",
77
+ "<extra_id_74>",
78
+ "<extra_id_75>",
79
+ "<extra_id_76>",
80
+ "<extra_id_77>",
81
+ "<extra_id_78>",
82
+ "<extra_id_79>",
83
+ "<extra_id_80>",
84
+ "<extra_id_81>",
85
+ "<extra_id_82>",
86
+ "<extra_id_83>",
87
+ "<extra_id_84>",
88
+ "<extra_id_85>",
89
+ "<extra_id_86>",
90
+ "<extra_id_87>",
91
+ "<extra_id_88>",
92
+ "<extra_id_89>",
93
+ "<extra_id_90>",
94
+ "<extra_id_91>",
95
+ "<extra_id_92>",
96
+ "<extra_id_93>",
97
+ "<extra_id_94>",
98
+ "<extra_id_95>",
99
+ "<extra_id_96>",
100
+ "<extra_id_97>",
101
+ "<extra_id_98>",
102
+ "<extra_id_99>"
103
+ ],
104
+ "eos_token": {
105
+ "content": "</s>",
106
+ "lstrip": false,
107
+ "normalized": false,
108
+ "rstrip": false,
109
+ "single_word": false
110
+ },
111
+ "pad_token": {
112
+ "content": "<pad>",
113
+ "lstrip": false,
114
+ "normalized": false,
115
+ "rstrip": false,
116
+ "single_word": false
117
+ },
118
+ "unk_token": {
119
+ "content": "<unk>",
120
+ "lstrip": false,
121
+ "normalized": false,
122
+ "rstrip": false,
123
+ "single_word": false
124
+ }
125
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer_config.json ADDED
@@ -0,0 +1,941 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<pad>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "32000": {
29
+ "content": "<extra_id_99>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "32001": {
37
+ "content": "<extra_id_98>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "32002": {
45
+ "content": "<extra_id_97>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32003": {
53
+ "content": "<extra_id_96>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32004": {
61
+ "content": "<extra_id_95>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "32005": {
69
+ "content": "<extra_id_94>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "32006": {
77
+ "content": "<extra_id_93>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "32007": {
85
+ "content": "<extra_id_92>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "32008": {
93
+ "content": "<extra_id_91>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "32009": {
101
+ "content": "<extra_id_90>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "32010": {
109
+ "content": "<extra_id_89>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "32011": {
117
+ "content": "<extra_id_88>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "32012": {
125
+ "content": "<extra_id_87>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "32013": {
133
+ "content": "<extra_id_86>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "32014": {
141
+ "content": "<extra_id_85>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "32015": {
149
+ "content": "<extra_id_84>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "32016": {
157
+ "content": "<extra_id_83>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "32017": {
165
+ "content": "<extra_id_82>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "32018": {
173
+ "content": "<extra_id_81>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "32019": {
181
+ "content": "<extra_id_80>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "32020": {
189
+ "content": "<extra_id_79>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "32021": {
197
+ "content": "<extra_id_78>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "32022": {
205
+ "content": "<extra_id_77>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "32023": {
213
+ "content": "<extra_id_76>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "32024": {
221
+ "content": "<extra_id_75>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "32025": {
229
+ "content": "<extra_id_74>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "32026": {
237
+ "content": "<extra_id_73>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "32027": {
245
+ "content": "<extra_id_72>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "32028": {
253
+ "content": "<extra_id_71>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "32029": {
261
+ "content": "<extra_id_70>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "32030": {
269
+ "content": "<extra_id_69>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "32031": {
277
+ "content": "<extra_id_68>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "32032": {
285
+ "content": "<extra_id_67>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "32033": {
293
+ "content": "<extra_id_66>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "32034": {
301
+ "content": "<extra_id_65>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "32035": {
309
+ "content": "<extra_id_64>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "32036": {
317
+ "content": "<extra_id_63>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "32037": {
325
+ "content": "<extra_id_62>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "32038": {
333
+ "content": "<extra_id_61>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "32039": {
341
+ "content": "<extra_id_60>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "32040": {
349
+ "content": "<extra_id_59>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ },
356
+ "32041": {
357
+ "content": "<extra_id_58>",
358
+ "lstrip": false,
359
+ "normalized": false,
360
+ "rstrip": false,
361
+ "single_word": false,
362
+ "special": true
363
+ },
364
+ "32042": {
365
+ "content": "<extra_id_57>",
366
+ "lstrip": false,
367
+ "normalized": false,
368
+ "rstrip": false,
369
+ "single_word": false,
370
+ "special": true
371
+ },
372
+ "32043": {
373
+ "content": "<extra_id_56>",
374
+ "lstrip": false,
375
+ "normalized": false,
376
+ "rstrip": false,
377
+ "single_word": false,
378
+ "special": true
379
+ },
380
+ "32044": {
381
+ "content": "<extra_id_55>",
382
+ "lstrip": false,
383
+ "normalized": false,
384
+ "rstrip": false,
385
+ "single_word": false,
386
+ "special": true
387
+ },
388
+ "32045": {
389
+ "content": "<extra_id_54>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false,
394
+ "special": true
395
+ },
396
+ "32046": {
397
+ "content": "<extra_id_53>",
398
+ "lstrip": false,
399
+ "normalized": false,
400
+ "rstrip": false,
401
+ "single_word": false,
402
+ "special": true
403
+ },
404
+ "32047": {
405
+ "content": "<extra_id_52>",
406
+ "lstrip": false,
407
+ "normalized": false,
408
+ "rstrip": false,
409
+ "single_word": false,
410
+ "special": true
411
+ },
412
+ "32048": {
413
+ "content": "<extra_id_51>",
414
+ "lstrip": false,
415
+ "normalized": false,
416
+ "rstrip": false,
417
+ "single_word": false,
418
+ "special": true
419
+ },
420
+ "32049": {
421
+ "content": "<extra_id_50>",
422
+ "lstrip": false,
423
+ "normalized": false,
424
+ "rstrip": false,
425
+ "single_word": false,
426
+ "special": true
427
+ },
428
+ "32050": {
429
+ "content": "<extra_id_49>",
430
+ "lstrip": false,
431
+ "normalized": false,
432
+ "rstrip": false,
433
+ "single_word": false,
434
+ "special": true
435
+ },
436
+ "32051": {
437
+ "content": "<extra_id_48>",
438
+ "lstrip": false,
439
+ "normalized": false,
440
+ "rstrip": false,
441
+ "single_word": false,
442
+ "special": true
443
+ },
444
+ "32052": {
445
+ "content": "<extra_id_47>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false,
450
+ "special": true
451
+ },
452
+ "32053": {
453
+ "content": "<extra_id_46>",
454
+ "lstrip": false,
455
+ "normalized": false,
456
+ "rstrip": false,
457
+ "single_word": false,
458
+ "special": true
459
+ },
460
+ "32054": {
461
+ "content": "<extra_id_45>",
462
+ "lstrip": false,
463
+ "normalized": false,
464
+ "rstrip": false,
465
+ "single_word": false,
466
+ "special": true
467
+ },
468
+ "32055": {
469
+ "content": "<extra_id_44>",
470
+ "lstrip": false,
471
+ "normalized": false,
472
+ "rstrip": false,
473
+ "single_word": false,
474
+ "special": true
475
+ },
476
+ "32056": {
477
+ "content": "<extra_id_43>",
478
+ "lstrip": false,
479
+ "normalized": false,
480
+ "rstrip": false,
481
+ "single_word": false,
482
+ "special": true
483
+ },
484
+ "32057": {
485
+ "content": "<extra_id_42>",
486
+ "lstrip": false,
487
+ "normalized": false,
488
+ "rstrip": false,
489
+ "single_word": false,
490
+ "special": true
491
+ },
492
+ "32058": {
493
+ "content": "<extra_id_41>",
494
+ "lstrip": false,
495
+ "normalized": false,
496
+ "rstrip": false,
497
+ "single_word": false,
498
+ "special": true
499
+ },
500
+ "32059": {
501
+ "content": "<extra_id_40>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false,
506
+ "special": true
507
+ },
508
+ "32060": {
509
+ "content": "<extra_id_39>",
510
+ "lstrip": false,
511
+ "normalized": false,
512
+ "rstrip": false,
513
+ "single_word": false,
514
+ "special": true
515
+ },
516
+ "32061": {
517
+ "content": "<extra_id_38>",
518
+ "lstrip": false,
519
+ "normalized": false,
520
+ "rstrip": false,
521
+ "single_word": false,
522
+ "special": true
523
+ },
524
+ "32062": {
525
+ "content": "<extra_id_37>",
526
+ "lstrip": false,
527
+ "normalized": false,
528
+ "rstrip": false,
529
+ "single_word": false,
530
+ "special": true
531
+ },
532
+ "32063": {
533
+ "content": "<extra_id_36>",
534
+ "lstrip": false,
535
+ "normalized": false,
536
+ "rstrip": false,
537
+ "single_word": false,
538
+ "special": true
539
+ },
540
+ "32064": {
541
+ "content": "<extra_id_35>",
542
+ "lstrip": false,
543
+ "normalized": false,
544
+ "rstrip": false,
545
+ "single_word": false,
546
+ "special": true
547
+ },
548
+ "32065": {
549
+ "content": "<extra_id_34>",
550
+ "lstrip": false,
551
+ "normalized": false,
552
+ "rstrip": false,
553
+ "single_word": false,
554
+ "special": true
555
+ },
556
+ "32066": {
557
+ "content": "<extra_id_33>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false,
562
+ "special": true
563
+ },
564
+ "32067": {
565
+ "content": "<extra_id_32>",
566
+ "lstrip": false,
567
+ "normalized": false,
568
+ "rstrip": false,
569
+ "single_word": false,
570
+ "special": true
571
+ },
572
+ "32068": {
573
+ "content": "<extra_id_31>",
574
+ "lstrip": false,
575
+ "normalized": false,
576
+ "rstrip": false,
577
+ "single_word": false,
578
+ "special": true
579
+ },
580
+ "32069": {
581
+ "content": "<extra_id_30>",
582
+ "lstrip": false,
583
+ "normalized": false,
584
+ "rstrip": false,
585
+ "single_word": false,
586
+ "special": true
587
+ },
588
+ "32070": {
589
+ "content": "<extra_id_29>",
590
+ "lstrip": false,
591
+ "normalized": false,
592
+ "rstrip": false,
593
+ "single_word": false,
594
+ "special": true
595
+ },
596
+ "32071": {
597
+ "content": "<extra_id_28>",
598
+ "lstrip": false,
599
+ "normalized": false,
600
+ "rstrip": false,
601
+ "single_word": false,
602
+ "special": true
603
+ },
604
+ "32072": {
605
+ "content": "<extra_id_27>",
606
+ "lstrip": false,
607
+ "normalized": false,
608
+ "rstrip": false,
609
+ "single_word": false,
610
+ "special": true
611
+ },
612
+ "32073": {
613
+ "content": "<extra_id_26>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false,
618
+ "special": true
619
+ },
620
+ "32074": {
621
+ "content": "<extra_id_25>",
622
+ "lstrip": false,
623
+ "normalized": false,
624
+ "rstrip": false,
625
+ "single_word": false,
626
+ "special": true
627
+ },
628
+ "32075": {
629
+ "content": "<extra_id_24>",
630
+ "lstrip": false,
631
+ "normalized": false,
632
+ "rstrip": false,
633
+ "single_word": false,
634
+ "special": true
635
+ },
636
+ "32076": {
637
+ "content": "<extra_id_23>",
638
+ "lstrip": false,
639
+ "normalized": false,
640
+ "rstrip": false,
641
+ "single_word": false,
642
+ "special": true
643
+ },
644
+ "32077": {
645
+ "content": "<extra_id_22>",
646
+ "lstrip": false,
647
+ "normalized": false,
648
+ "rstrip": false,
649
+ "single_word": false,
650
+ "special": true
651
+ },
652
+ "32078": {
653
+ "content": "<extra_id_21>",
654
+ "lstrip": false,
655
+ "normalized": false,
656
+ "rstrip": false,
657
+ "single_word": false,
658
+ "special": true
659
+ },
660
+ "32079": {
661
+ "content": "<extra_id_20>",
662
+ "lstrip": false,
663
+ "normalized": false,
664
+ "rstrip": false,
665
+ "single_word": false,
666
+ "special": true
667
+ },
668
+ "32080": {
669
+ "content": "<extra_id_19>",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false,
674
+ "special": true
675
+ },
676
+ "32081": {
677
+ "content": "<extra_id_18>",
678
+ "lstrip": false,
679
+ "normalized": false,
680
+ "rstrip": false,
681
+ "single_word": false,
682
+ "special": true
683
+ },
684
+ "32082": {
685
+ "content": "<extra_id_17>",
686
+ "lstrip": false,
687
+ "normalized": false,
688
+ "rstrip": false,
689
+ "single_word": false,
690
+ "special": true
691
+ },
692
+ "32083": {
693
+ "content": "<extra_id_16>",
694
+ "lstrip": false,
695
+ "normalized": false,
696
+ "rstrip": false,
697
+ "single_word": false,
698
+ "special": true
699
+ },
700
+ "32084": {
701
+ "content": "<extra_id_15>",
702
+ "lstrip": false,
703
+ "normalized": false,
704
+ "rstrip": false,
705
+ "single_word": false,
706
+ "special": true
707
+ },
708
+ "32085": {
709
+ "content": "<extra_id_14>",
710
+ "lstrip": false,
711
+ "normalized": false,
712
+ "rstrip": false,
713
+ "single_word": false,
714
+ "special": true
715
+ },
716
+ "32086": {
717
+ "content": "<extra_id_13>",
718
+ "lstrip": false,
719
+ "normalized": false,
720
+ "rstrip": false,
721
+ "single_word": false,
722
+ "special": true
723
+ },
724
+ "32087": {
725
+ "content": "<extra_id_12>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false,
730
+ "special": true
731
+ },
732
+ "32088": {
733
+ "content": "<extra_id_11>",
734
+ "lstrip": false,
735
+ "normalized": false,
736
+ "rstrip": false,
737
+ "single_word": false,
738
+ "special": true
739
+ },
740
+ "32089": {
741
+ "content": "<extra_id_10>",
742
+ "lstrip": false,
743
+ "normalized": false,
744
+ "rstrip": false,
745
+ "single_word": false,
746
+ "special": true
747
+ },
748
+ "32090": {
749
+ "content": "<extra_id_9>",
750
+ "lstrip": false,
751
+ "normalized": false,
752
+ "rstrip": false,
753
+ "single_word": false,
754
+ "special": true
755
+ },
756
+ "32091": {
757
+ "content": "<extra_id_8>",
758
+ "lstrip": false,
759
+ "normalized": false,
760
+ "rstrip": false,
761
+ "single_word": false,
762
+ "special": true
763
+ },
764
+ "32092": {
765
+ "content": "<extra_id_7>",
766
+ "lstrip": false,
767
+ "normalized": false,
768
+ "rstrip": false,
769
+ "single_word": false,
770
+ "special": true
771
+ },
772
+ "32093": {
773
+ "content": "<extra_id_6>",
774
+ "lstrip": false,
775
+ "normalized": false,
776
+ "rstrip": false,
777
+ "single_word": false,
778
+ "special": true
779
+ },
780
+ "32094": {
781
+ "content": "<extra_id_5>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false,
786
+ "special": true
787
+ },
788
+ "32095": {
789
+ "content": "<extra_id_4>",
790
+ "lstrip": false,
791
+ "normalized": false,
792
+ "rstrip": false,
793
+ "single_word": false,
794
+ "special": true
795
+ },
796
+ "32096": {
797
+ "content": "<extra_id_3>",
798
+ "lstrip": false,
799
+ "normalized": false,
800
+ "rstrip": false,
801
+ "single_word": false,
802
+ "special": true
803
+ },
804
+ "32097": {
805
+ "content": "<extra_id_2>",
806
+ "lstrip": false,
807
+ "normalized": false,
808
+ "rstrip": false,
809
+ "single_word": false,
810
+ "special": true
811
+ },
812
+ "32098": {
813
+ "content": "<extra_id_1>",
814
+ "lstrip": false,
815
+ "normalized": false,
816
+ "rstrip": false,
817
+ "single_word": false,
818
+ "special": true
819
+ },
820
+ "32099": {
821
+ "content": "<extra_id_0>",
822
+ "lstrip": false,
823
+ "normalized": false,
824
+ "rstrip": false,
825
+ "single_word": false,
826
+ "special": true
827
+ }
828
+ },
829
+ "additional_special_tokens": [
830
+ "<extra_id_0>",
831
+ "<extra_id_1>",
832
+ "<extra_id_2>",
833
+ "<extra_id_3>",
834
+ "<extra_id_4>",
835
+ "<extra_id_5>",
836
+ "<extra_id_6>",
837
+ "<extra_id_7>",
838
+ "<extra_id_8>",
839
+ "<extra_id_9>",
840
+ "<extra_id_10>",
841
+ "<extra_id_11>",
842
+ "<extra_id_12>",
843
+ "<extra_id_13>",
844
+ "<extra_id_14>",
845
+ "<extra_id_15>",
846
+ "<extra_id_16>",
847
+ "<extra_id_17>",
848
+ "<extra_id_18>",
849
+ "<extra_id_19>",
850
+ "<extra_id_20>",
851
+ "<extra_id_21>",
852
+ "<extra_id_22>",
853
+ "<extra_id_23>",
854
+ "<extra_id_24>",
855
+ "<extra_id_25>",
856
+ "<extra_id_26>",
857
+ "<extra_id_27>",
858
+ "<extra_id_28>",
859
+ "<extra_id_29>",
860
+ "<extra_id_30>",
861
+ "<extra_id_31>",
862
+ "<extra_id_32>",
863
+ "<extra_id_33>",
864
+ "<extra_id_34>",
865
+ "<extra_id_35>",
866
+ "<extra_id_36>",
867
+ "<extra_id_37>",
868
+ "<extra_id_38>",
869
+ "<extra_id_39>",
870
+ "<extra_id_40>",
871
+ "<extra_id_41>",
872
+ "<extra_id_42>",
873
+ "<extra_id_43>",
874
+ "<extra_id_44>",
875
+ "<extra_id_45>",
876
+ "<extra_id_46>",
877
+ "<extra_id_47>",
878
+ "<extra_id_48>",
879
+ "<extra_id_49>",
880
+ "<extra_id_50>",
881
+ "<extra_id_51>",
882
+ "<extra_id_52>",
883
+ "<extra_id_53>",
884
+ "<extra_id_54>",
885
+ "<extra_id_55>",
886
+ "<extra_id_56>",
887
+ "<extra_id_57>",
888
+ "<extra_id_58>",
889
+ "<extra_id_59>",
890
+ "<extra_id_60>",
891
+ "<extra_id_61>",
892
+ "<extra_id_62>",
893
+ "<extra_id_63>",
894
+ "<extra_id_64>",
895
+ "<extra_id_65>",
896
+ "<extra_id_66>",
897
+ "<extra_id_67>",
898
+ "<extra_id_68>",
899
+ "<extra_id_69>",
900
+ "<extra_id_70>",
901
+ "<extra_id_71>",
902
+ "<extra_id_72>",
903
+ "<extra_id_73>",
904
+ "<extra_id_74>",
905
+ "<extra_id_75>",
906
+ "<extra_id_76>",
907
+ "<extra_id_77>",
908
+ "<extra_id_78>",
909
+ "<extra_id_79>",
910
+ "<extra_id_80>",
911
+ "<extra_id_81>",
912
+ "<extra_id_82>",
913
+ "<extra_id_83>",
914
+ "<extra_id_84>",
915
+ "<extra_id_85>",
916
+ "<extra_id_86>",
917
+ "<extra_id_87>",
918
+ "<extra_id_88>",
919
+ "<extra_id_89>",
920
+ "<extra_id_90>",
921
+ "<extra_id_91>",
922
+ "<extra_id_92>",
923
+ "<extra_id_93>",
924
+ "<extra_id_94>",
925
+ "<extra_id_95>",
926
+ "<extra_id_96>",
927
+ "<extra_id_97>",
928
+ "<extra_id_98>",
929
+ "<extra_id_99>"
930
+ ],
931
+ "clean_up_tokenization_spaces": true,
932
+ "eos_token": "</s>",
933
+ "extra_ids": 100,
934
+ "extra_special_tokens": {},
935
+ "legacy": true,
936
+ "model_max_length": 512,
937
+ "pad_token": "<pad>",
938
+ "sp_model_kwargs": {},
939
+ "tokenizer_class": "T5Tokenizer",
940
+ "unk_token": "<unk>"
941
+ }