Hugging Face's logo

tatiana-merz
/
mbart-large-50-finetuned-sah-to-feat

Text2Text Generation
Transformers
PyTorch
mbart
Generated from Trainer
Inference Endpoints
Model card Files Community
tatiana-merz commited on
Commit
fdadff1
•
1 Parent(s): 6c9aa86

End of training

Browse files
Files changed (6) hide show
  1. pytorch_model.bin +1 -1
  2. special_tokens_map.json +100 -56
  3. spiece.model +3 -0
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +103 -68
  6. training_args.bin +1 -1
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3ad66c0f08ac963ca0e80d793a2d3480d8a25e9913902d2695e01b4fc3ff275
3
  size 2444694045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efb7b7b1523e24de062ca93152add4a0c02a0fab36a5993244888fad92e547b2
3
  size 2444694045
special_tokens_map.json CHANGED
@@ -1,63 +1,107 @@
1
  {
2
  "additional_special_tokens": [
3
- "ar_AR",
4
- "cs_CZ",
5
- "de_DE",
6
- "en_XX",
7
- "es_XX",
8
- "et_EE",
9
- "fi_FI",
10
- "fr_XX",
11
- "gu_IN",
12
- "hi_IN",
13
- "it_IT",
14
- "ja_XX",
15
- "kk_KZ",
16
- "ko_KR",
17
- "lt_LT",
18
- "lv_LV",
19
- "my_MM",
20
- "ne_NP",
21
- "nl_XX",
22
- "ro_RO",
23
- "ru_RU",
24
- "si_LK",
25
- "tr_TR",
26
- "vi_VN",
27
- "zh_CN",
28
- "af_ZA",
29
- "az_AZ",
30
- "bn_IN",
31
- "fa_IR",
32
- "he_IL",
33
- "hr_HR",
34
- "id_ID",
35
- "ka_GE",
36
- "km_KH",
37
- "mk_MK",
38
- "ml_IN",
39
- "mn_MN",
40
- "mr_IN",
41
- "pl_PL",
42
- "ps_AF",
43
- "pt_XX",
44
- "sv_SE",
45
- "sw_KE",
46
- "ta_IN",
47
- "te_IN",
48
- "th_TH",
49
- "tl_XX",
50
- "uk_UA",
51
- "ur_PK",
52
- "xh_ZA",
53
- "gl_ES",
54
- "sl_SI"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ],
56
- "bos_token": "<s>",
57
- "cls_token": "<s>",
58
  "eos_token": "</s>",
59
- "mask_token": "<mask>",
60
  "pad_token": "<pad>",
61
- "sep_token": "</s>",
62
  "unk_token": "<unk>"
63
  }
 
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": "</s>",
 
105
  "pad_token": "<pad>",
 
106
  "unk_token": "<unk>"
107
  }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b66c8e9c2064150d815691facbe2a9be128d2082373d6a1b22facf9fffc6bbcb
3
- size 17109741
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:325982f929fb03e41968f4c0cdee41fa6d0cff2f6e15393ff2c72aec979a09fb
3
+ size 2422193
tokenizer_config.json CHANGED
@@ -1,76 +1,111 @@
1
  {
2
  "additional_special_tokens": [
3
- "ar_AR",
4
- "cs_CZ",
5
- "de_DE",
6
- "en_XX",
7
- "es_XX",
8
- "et_EE",
9
- "fi_FI",
10
- "fr_XX",
11
- "gu_IN",
12
- "hi_IN",
13
- "it_IT",
14
- "ja_XX",
15
- "kk_KZ",
16
- "ko_KR",
17
- "lt_LT",
18
- "lv_LV",
19
- "my_MM",
20
- "ne_NP",
21
- "nl_XX",
22
- "ro_RO",
23
- "ru_RU",
24
- "si_LK",
25
- "tr_TR",
26
- "vi_VN",
27
- "zh_CN",
28
- "af_ZA",
29
- "az_AZ",
30
- "bn_IN",
31
- "fa_IR",
32
- "he_IL",
33
- "hr_HR",
34
- "id_ID",
35
- "ka_GE",
36
- "km_KH",
37
- "mk_MK",
38
- "ml_IN",
39
- "mn_MN",
40
- "mr_IN",
41
- "pl_PL",
42
- "ps_AF",
43
- "pt_XX",
44
- "sv_SE",
45
- "sw_KE",
46
- "ta_IN",
47
- "te_IN",
48
- "th_TH",
49
- "tl_XX",
50
- "uk_UA",
51
- "ur_PK",
52
- "xh_ZA",
53
- "gl_ES",
54
- "sl_SI"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  ],
56
- "bos_token": "<s>",
57
  "clean_up_tokenization_spaces": true,
58
- "cls_token": "<s>",
59
  "eos_token": "</s>",
60
- "mask_token": {
61
- "__type": "AddedToken",
62
- "content": "<mask>",
63
- "lstrip": true,
64
- "normalized": true,
65
- "rstrip": false,
66
- "single_word": false
67
- },
68
- "model_max_length": 1024,
69
  "pad_token": "<pad>",
70
- "sep_token": "</s>",
71
- "sp_model_kwargs": {},
72
- "src_lang": null,
73
- "tgt_lang": null,
74
- "tokenizer_class": "MBart50Tokenizer",
75
  "unk_token": "<unk>"
76
  }
 
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
  "clean_up_tokenization_spaces": true,
 
105
  "eos_token": "</s>",
106
+ "extra_ids": 100,
107
+ "model_max_length": 512,
 
 
 
 
 
 
 
108
  "pad_token": "<pad>",
109
+ "tokenizer_class": "T5Tokenizer",
 
 
 
 
110
  "unk_token": "<unk>"
111
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26c3b27e07990bad32736d2b2f2e055c3be9ddb86496e59c6b5f990310271016
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61b54e5615277aedf6795a4c6a7529b84f653880219804ff89ea620adfc7b903
3
  size 4155