Hugging Face's logo

ldos
/
text_shortening_model_v72

Text2Text Generation
Transformers
PyTorch
t5
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
ldos commited on
Commit
319f6b4
•
1 Parent(s): 8d8d425

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +51 -57
  2. pytorch_model.bin +2 -2
  3. special_tokens_map.json +102 -10
  4. spiece.model +3 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +105 -9
  7. training_args.bin +1 -1
config.json CHANGED
@@ -1,67 +1,61 @@
1
  {
2
- "_name_or_path": "facebook/bart-large-xsum",
3
- "_num_labels": 3,
4
- "activation_dropout": 0.0,
5
- "activation_function": "gelu",
6
- "add_bias_logits": false,
7
- "add_final_layer_norm": false,
8
  "architectures": [
9
- "BartForConditionalGeneration"
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
- "eos_token_ids": [
29
- 2
30
- ],
31
- "forced_eos_token_id": 2,
32
- "gradient_checkpointing": false,
33
- "id2label": {
34
- "0": "LABEL_0",
35
- "1": "LABEL_1",
36
- "2": "LABEL_2"
37
- },
38
- "init_std": 0.02,
39
  "is_encoder_decoder": true,
40
- "label2id": {
41
- "LABEL_0": 0,
42
- "LABEL_1": 1,
43
- "LABEL_2": 2
44
- },
45
- "max_length": 62,
46
- "max_position_embeddings": 1024,
47
- "min_length": 11,
48
- "model_type": "bart",
49
- "no_repeat_ngram_size": 3,
50
- "normalize_before": false,
51
- "normalize_embedding": true,
52
- "num_beams": 6,
53
- "num_hidden_layers": 12,
54
  "output_past": true,
55
- "pad_token_id": 1,
56
- "prefix": " ",
57
- "replacing_rate": 0,
58
- "scale_embedding": false,
59
- "static_position_embeddings": false,
60
- "student_decoder_layers": null,
61
- "student_encoder_layers": null,
62
- "task_specific_params": {},
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  "torch_dtype": "float32",
64
  "transformers_version": "4.33.1",
65
  "use_cache": true,
66
- "vocab_size": 50264
67
  }
 
1
  {
2
+ "_name_or_path": "t5-small",
 
 
 
 
 
3
  "architectures": [
4
+ "T5ForConditionalGeneration"
5
  ],
 
 
 
6
  "classifier_dropout": 0.0,
7
+ "d_ff": 2048,
8
+ "d_kv": 64,
9
+ "d_model": 512,
10
+ "decoder_start_token_id": 0,
11
+ "dense_act_fn": "relu",
12
+ "dropout_rate": 0.1,
13
+ "eos_token_id": 1,
14
+ "feed_forward_proj": "relu",
15
+ "initializer_factor": 1.0,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16
  "is_encoder_decoder": true,
17
+ "is_gated_act": false,
18
+ "layer_norm_epsilon": 1e-06,
19
+ "model_type": "t5",
20
+ "n_positions": 512,
21
+ "num_decoder_layers": 6,
22
+ "num_heads": 8,
23
+ "num_layers": 6,
 
 
 
 
 
 
 
24
  "output_past": true,
25
+ "pad_token_id": 0,
26
+ "relative_attention_max_distance": 128,
27
+ "relative_attention_num_buckets": 32,
28
+ "task_specific_params": {
29
+ "summarization": {
30
+ "early_stopping": true,
31
+ "length_penalty": 2.0,
32
+ "max_length": 200,
33
+ "min_length": 30,
34
+ "no_repeat_ngram_size": 3,
35
+ "num_beams": 4,
36
+ "prefix": "summarize: "
37
+ },
38
+ "translation_en_to_de": {
39
+ "early_stopping": true,
40
+ "max_length": 300,
41
+ "num_beams": 4,
42
+ "prefix": "translate English to German: "
43
+ },
44
+ "translation_en_to_fr": {
45
+ "early_stopping": true,
46
+ "max_length": 300,
47
+ "num_beams": 4,
48
+ "prefix": "translate English to French: "
49
+ },
50
+ "translation_en_to_ro": {
51
+ "early_stopping": true,
52
+ "max_length": 300,
53
+ "num_beams": 4,
54
+ "prefix": "translate English to Romanian: "
55
+ }
56
+ },
57
  "torch_dtype": "float32",
58
  "transformers_version": "4.33.1",
59
  "use_cache": true,
60
+ "vocab_size": 32128
61
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19228973dff26af203b85869673fc52ec24e551df9afa4d51009e9eca91f14b1
3
- size 1625537293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adf195f51ed18bb1bc5abe4f1f8d92c6a6636d534f8d918af76872175c058941
3
+ size 242071641
special_tokens_map.json CHANGED
@@ -1,15 +1,107 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "eos_token": "</s>",
5
- "mask_token": {
6
- "content": "<mask>",
7
- "lstrip": true,
8
- "normalized": false,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
  "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
  "unk_token": "<unk>"
15
  }
 
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
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,15 +1,111 @@
1
  {
2
- "add_prefix_space": false,
3
- "bos_token": "<s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  "clean_up_tokenization_spaces": true,
5
- "cls_token": "<s>",
6
  "eos_token": "</s>",
7
- "errors": "replace",
8
- "mask_token": "<mask>",
9
- "model_max_length": 1024,
10
  "pad_token": "<pad>",
11
- "sep_token": "</s>",
12
- "tokenizer_class": "BartTokenizer",
13
- "trim_offsets": true,
14
  "unk_token": "<unk>"
15
  }
 
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 sha256:8f2f939743744f21fdef4e0f703ef4b137fb6831f76914409c9644bb553997a9
3
  size 4155
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef40983bc1255e664a812318cbc9c551fd76694822c9dbf3dea2dddac904b2d2
3
  size 4155