Hugging Face's logo

boneb
/
t5-sl-large-TS-para

Transformers
PyTorch
t5
text2text-generation
text-generation-inference
Model card Files
xet
 Community
boneb commited on
Commit
f0ff154
·
1 Parent(s): 9536e88

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. config.json +21 -46
  2. generation_config.json +3 -8
  3. pytorch_model.bin +2 -2
  4. special_tokens_map.json +100 -56
  5. tokenizer.json +2 -2
  6. tokenizer_config.json +103 -67
  7. training_args.bin +1 -1
config.json CHANGED
@@ -1,58 +1,33 @@
1
  {
2
- "_name_or_path": "facebook/mbart-large-50",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "gelu",
6
- "add_bias_logits": false,
7
- "add_final_layer_norm": true,
8
  "architectures": [
9
- "MBartForConditionalGeneration"
10
  ],
11
- "attention_dropout": 0.0,
12
- "bos_token_id": 0,
13
- "classif_dropout": 0.0,
14
  "classifier_dropout": 0.0,
 
 
15
  "d_model": 1024,
16
- "decoder_attention_heads": 16,
17
- "decoder_ffn_dim": 4096,
18
- "decoder_layerdrop": 0.0,
19
- "decoder_layers": 12,
20
- "decoder_start_token_id": 2,
21
- "dropout": 0.1,
22
- "early_stopping": true,
23
- "encoder_attention_heads": 16,
24
- "encoder_ffn_dim": 4096,
25
- "encoder_layerdrop": 0.0,
26
- "encoder_layers": 12,
27
- "eos_token_id": 2,
28
- "forced_eos_token_id": 2,
29
  "gradient_checkpointing": false,
30
- "id2label": {
31
- "0": "LABEL_0",
32
- "1": "LABEL_1",
33
- "2": "LABEL_2"
34
- },
35
- "init_std": 0.02,
36
  "is_encoder_decoder": true,
37
- "label2id": {
38
- "LABEL_0": 0,
39
- "LABEL_1": 1,
40
- "LABEL_2": 2
41
- },
42
- "max_length": 200,
43
- "max_position_embeddings": 1024,
44
- "model_type": "mbart",
45
- "normalize_before": true,
46
- "normalize_embedding": true,
47
- "num_beams": 5,
48
- "num_hidden_layers": 12,
49
  "output_past": true,
50
- "pad_token_id": 1,
51
- "scale_embedding": true,
52
- "static_position_embeddings": false,
53
- "tokenizer_class": "MBart50Tokenizer",
54
  "torch_dtype": "float32",
55
  "transformers_version": "4.32.0.dev0",
56
  "use_cache": true,
57
- "vocab_size": 250054
58
  }
 
1
  {
2
+ "_name_or_path": "cjvt/t5-sl-large",
 
 
 
 
 
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
 
 
 
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 2816,
8
+ "d_kv": 64,
9
  "d_model": 1024,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "gelu_new",
12
+ "dropout_rate": 0.0,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "gated-gelu",
 
 
 
 
 
 
 
 
15
  "gradient_checkpointing": false,
16
+ "initializer_factor": 1.0,
 
 
 
 
 
17
  "is_encoder_decoder": true,
18
+ "is_gated_act": true,
19
+ "layer_norm_epsilon": 1e-06,
20
+ "model_type": "t5",
21
+ "num_decoder_layers": 24,
22
+ "num_heads": 16,
23
+ "num_layers": 24,
 
 
 
 
 
 
24
  "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "tie_word_embeddings": false,
29
  "torch_dtype": "float32",
30
  "transformers_version": "4.32.0.dev0",
31
  "use_cache": true,
32
+ "vocab_size": 32000
33
  }
generation_config.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
- "bos_token_id": 0,
3
- "decoder_start_token_id": 2,
4
- "early_stopping": true,
5
- "eos_token_id": 2,
6
- "forced_eos_token_id": 2,
7
- "max_length": 200,
8
- "num_beams": 5,
9
- "pad_token_id": 1,
10
  "transformers_version": "4.32.0.dev0"
11
  }
 
1
  {
2
+ "decoder_start_token_id": 0,
3
+ "eos_token_id": 1,
4
+ "pad_token_id": 0,
 
 
 
 
 
5
  "transformers_version": "4.32.0.dev0"
6
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b0b5fc5bd2cadde45d438f9c7160d73b35da7cf6abef17fb70f151a983bb8f0
3
- size 2444694045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a41c1bff98cfdde5ec2547a1aca7ec4795c870ac446c831a647eebb8e261a4e
3
+ size 3131745093
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
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53d5f2733f6b360d28c2576f5ee7f59d0fe1bc9e8e28a63e5f0227282700b294
3
- size 17109850
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5244d03e1e8c686de915f12c4cbd2baf4d2f367f50b52729332be19fd5f1b07
3
+ size 2335740
tokenizer_config.json CHANGED
@@ -1,76 +1,112 @@
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": 1000000000000000019884624838656,
 
 
 
 
 
 
 
108
  "pad_token": "<pad>",
 
109
  "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
 
 
111
  "unk_token": "<unk>"
112
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ea9ac6c3371e3d7d1f47a1cd8b432326cb576ec918b3239ecfb0b381cacaaf8
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194c0ac45ef63f17f9400f22aa374a6abfb0edbf14d97dec85f20c7177f4000f
3
  size 4219