alpertml commited on
Commit
a68f679
1 Parent(s): e2b1d98

Upload 28 files

Browse files
models/bart_model/config.json ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sshleifer/distilbart-xsum-6-6",
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": 6,
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": 6,
27
+ "eos_token_id": 2,
28
+ "eos_token_ids": [
29
+ 2
30
+ ],
31
+ "extra_pos_embeddings": 2,
32
+ "forced_eos_token_id": 2,
33
+ "gradient_checkpointing": false,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1",
37
+ "2": "LABEL_2"
38
+ },
39
+ "init_std": 0.02,
40
+ "is_encoder_decoder": true,
41
+ "label2id": {
42
+ "LABEL_0": 0,
43
+ "LABEL_1": 1,
44
+ "LABEL_2": 2
45
+ },
46
+ "length_penalty": 0.5,
47
+ "max_length": 62,
48
+ "max_position_embeddings": 1024,
49
+ "min_length": 11,
50
+ "model_type": "bart",
51
+ "no_repeat_ngram_size": 3,
52
+ "normalize_before": false,
53
+ "normalize_embedding": true,
54
+ "num_beams": 6,
55
+ "num_hidden_layers": 6,
56
+ "output_past": true,
57
+ "pad_token_id": 1,
58
+ "prefix": " ",
59
+ "replacing_rate": 0,
60
+ "save_step": 38,
61
+ "scale_embedding": false,
62
+ "static_position_embeddings": false,
63
+ "student_decoder_layers": null,
64
+ "student_encoder_layers": null,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.30.2",
67
+ "use_cache": true,
68
+ "vocab_size": 50264
69
+ }
models/bart_model/generation_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "early_stopping": true,
6
+ "eos_token_id": 2,
7
+ "forced_eos_token_id": 2,
8
+ "length_penalty": 0.5,
9
+ "max_length": 62,
10
+ "min_length": 11,
11
+ "no_repeat_ngram_size": 3,
12
+ "num_beams": 6,
13
+ "pad_token_id": 1,
14
+ "transformers_version": "4.30.2"
15
+ }
models/bart_model/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/bart_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45b52e2ae678b6b76c5d5c05bf6d7e3d8b682af6ea66316f5b425d555fe424fa
3
+ size 460024785
models/bart_model/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
models/bart_model/tokenizer_config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "model_max_length": 1024,
38
+ "pad_token": {
39
+ "__type": "AddedToken",
40
+ "content": "<pad>",
41
+ "lstrip": false,
42
+ "normalized": true,
43
+ "rstrip": false,
44
+ "single_word": false
45
+ },
46
+ "sep_token": {
47
+ "__type": "AddedToken",
48
+ "content": "</s>",
49
+ "lstrip": false,
50
+ "normalized": true,
51
+ "rstrip": false,
52
+ "single_word": false
53
+ },
54
+ "tokenizer_class": "BartTokenizer",
55
+ "unk_token": {
56
+ "__type": "AddedToken",
57
+ "content": "<unk>",
58
+ "lstrip": false,
59
+ "normalized": true,
60
+ "rstrip": false,
61
+ "single_word": false
62
+ }
63
+ }
models/bart_model/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
models/nltkUtilsObj.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36a80ef2637bd3e5c87c3275abf6bf6a48e385658d041da6d6e5b4c6a8bd8e15
3
+ size 56
models/pegasus_model/config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "google/pegasus-xsum",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "relu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "PegasusForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.0,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 1024,
15
+ "decoder_attention_heads": 16,
16
+ "decoder_ffn_dim": 4096,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 16,
19
+ "decoder_start_token_id": 0,
20
+ "do_blenderbot_90_layernorm": false,
21
+ "dropout": 0.1,
22
+ "encoder_attention_heads": 16,
23
+ "encoder_ffn_dim": 4096,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 16,
26
+ "eos_token_id": 1,
27
+ "extra_pos_embeddings": 0,
28
+ "force_bos_token_to_be_generated": false,
29
+ "forced_eos_token_id": 1,
30
+ "gradient_checkpointing": false,
31
+ "id2label": {
32
+ "0": "LABEL_0",
33
+ "1": "LABEL_1",
34
+ "2": "LABEL_2"
35
+ },
36
+ "init_std": 0.02,
37
+ "is_encoder_decoder": true,
38
+ "label2id": {
39
+ "LABEL_0": 0,
40
+ "LABEL_1": 1,
41
+ "LABEL_2": 2
42
+ },
43
+ "length_penalty": 0.6,
44
+ "max_length": 64,
45
+ "max_position_embeddings": 512,
46
+ "model_type": "pegasus",
47
+ "normalize_before": true,
48
+ "normalize_embedding": false,
49
+ "num_beams": 8,
50
+ "num_hidden_layers": 16,
51
+ "pad_token_id": 0,
52
+ "scale_embedding": true,
53
+ "static_position_embeddings": true,
54
+ "torch_dtype": "float32",
55
+ "transformers_version": "4.30.2",
56
+ "use_cache": true,
57
+ "vocab_size": 96103
58
+ }
models/pegasus_model/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 0,
5
+ "eos_token_id": 1,
6
+ "forced_eos_token_id": 1,
7
+ "length_penalty": 0.6,
8
+ "max_length": 64,
9
+ "num_beams": 8,
10
+ "pad_token_id": 0,
11
+ "transformers_version": "4.30.2"
12
+ }
models/pegasus_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b923a377cc494428de9015e8089a319bfcbfb35e0ad3b5edd34fa3b2d3d894a0
3
+ size 2279600813
models/pegasus_model/special_tokens_map.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<mask_1>",
4
+ "<unk_2>",
5
+ "<unk_3>",
6
+ "<unk_4>",
7
+ "<unk_5>",
8
+ "<unk_6>",
9
+ "<unk_7>",
10
+ "<unk_8>",
11
+ "<unk_9>",
12
+ "<unk_10>",
13
+ "<unk_11>",
14
+ "<unk_12>",
15
+ "<unk_13>",
16
+ "<unk_14>",
17
+ "<unk_15>",
18
+ "<unk_16>",
19
+ "<unk_17>",
20
+ "<unk_18>",
21
+ "<unk_19>",
22
+ "<unk_20>",
23
+ "<unk_21>",
24
+ "<unk_22>",
25
+ "<unk_23>",
26
+ "<unk_24>",
27
+ "<unk_25>",
28
+ "<unk_26>",
29
+ "<unk_27>",
30
+ "<unk_28>",
31
+ "<unk_29>",
32
+ "<unk_30>",
33
+ "<unk_31>",
34
+ "<unk_32>",
35
+ "<unk_33>",
36
+ "<unk_34>",
37
+ "<unk_35>",
38
+ "<unk_36>",
39
+ "<unk_37>",
40
+ "<unk_38>",
41
+ "<unk_39>",
42
+ "<unk_40>",
43
+ "<unk_41>",
44
+ "<unk_42>",
45
+ "<unk_43>",
46
+ "<unk_44>",
47
+ "<unk_45>",
48
+ "<unk_46>",
49
+ "<unk_47>",
50
+ "<unk_48>",
51
+ "<unk_49>",
52
+ "<unk_50>",
53
+ "<unk_51>",
54
+ "<unk_52>",
55
+ "<unk_53>",
56
+ "<unk_54>",
57
+ "<unk_55>",
58
+ "<unk_56>",
59
+ "<unk_57>",
60
+ "<unk_58>",
61
+ "<unk_59>",
62
+ "<unk_60>",
63
+ "<unk_61>",
64
+ "<unk_62>",
65
+ "<unk_63>",
66
+ "<unk_64>",
67
+ "<unk_65>",
68
+ "<unk_66>",
69
+ "<unk_67>",
70
+ "<unk_68>",
71
+ "<unk_69>",
72
+ "<unk_70>",
73
+ "<unk_71>",
74
+ "<unk_72>",
75
+ "<unk_73>",
76
+ "<unk_74>",
77
+ "<unk_75>",
78
+ "<unk_76>",
79
+ "<unk_77>",
80
+ "<unk_78>",
81
+ "<unk_79>",
82
+ "<unk_80>",
83
+ "<unk_81>",
84
+ "<unk_82>",
85
+ "<unk_83>",
86
+ "<unk_84>",
87
+ "<unk_85>",
88
+ "<unk_86>",
89
+ "<unk_87>",
90
+ "<unk_88>",
91
+ "<unk_89>",
92
+ "<unk_90>",
93
+ "<unk_91>",
94
+ "<unk_92>",
95
+ "<unk_93>",
96
+ "<unk_94>",
97
+ "<unk_95>",
98
+ "<unk_96>",
99
+ "<unk_97>",
100
+ "<unk_98>",
101
+ "<unk_99>",
102
+ "<unk_100>",
103
+ "<unk_101>",
104
+ "<unk_102>"
105
+ ],
106
+ "eos_token": "</s>",
107
+ "mask_token": "<mask_2>",
108
+ "pad_token": "<pad>",
109
+ "unk_token": "<unk>"
110
+ }
models/pegasus_model/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0015189ef36359283fec8b93cf6d9ce51bca37eb1101defc68a53b394913b96c
3
+ size 1912529
models/pegasus_model/tokenizer_config.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<mask_1>",
4
+ "<unk_2>",
5
+ "<unk_3>",
6
+ "<unk_4>",
7
+ "<unk_5>",
8
+ "<unk_6>",
9
+ "<unk_7>",
10
+ "<unk_8>",
11
+ "<unk_9>",
12
+ "<unk_10>",
13
+ "<unk_11>",
14
+ "<unk_12>",
15
+ "<unk_13>",
16
+ "<unk_14>",
17
+ "<unk_15>",
18
+ "<unk_16>",
19
+ "<unk_17>",
20
+ "<unk_18>",
21
+ "<unk_19>",
22
+ "<unk_20>",
23
+ "<unk_21>",
24
+ "<unk_22>",
25
+ "<unk_23>",
26
+ "<unk_24>",
27
+ "<unk_25>",
28
+ "<unk_26>",
29
+ "<unk_27>",
30
+ "<unk_28>",
31
+ "<unk_29>",
32
+ "<unk_30>",
33
+ "<unk_31>",
34
+ "<unk_32>",
35
+ "<unk_33>",
36
+ "<unk_34>",
37
+ "<unk_35>",
38
+ "<unk_36>",
39
+ "<unk_37>",
40
+ "<unk_38>",
41
+ "<unk_39>",
42
+ "<unk_40>",
43
+ "<unk_41>",
44
+ "<unk_42>",
45
+ "<unk_43>",
46
+ "<unk_44>",
47
+ "<unk_45>",
48
+ "<unk_46>",
49
+ "<unk_47>",
50
+ "<unk_48>",
51
+ "<unk_49>",
52
+ "<unk_50>",
53
+ "<unk_51>",
54
+ "<unk_52>",
55
+ "<unk_53>",
56
+ "<unk_54>",
57
+ "<unk_55>",
58
+ "<unk_56>",
59
+ "<unk_57>",
60
+ "<unk_58>",
61
+ "<unk_59>",
62
+ "<unk_60>",
63
+ "<unk_61>",
64
+ "<unk_62>",
65
+ "<unk_63>",
66
+ "<unk_64>",
67
+ "<unk_65>",
68
+ "<unk_66>",
69
+ "<unk_67>",
70
+ "<unk_68>",
71
+ "<unk_69>",
72
+ "<unk_70>",
73
+ "<unk_71>",
74
+ "<unk_72>",
75
+ "<unk_73>",
76
+ "<unk_74>",
77
+ "<unk_75>",
78
+ "<unk_76>",
79
+ "<unk_77>",
80
+ "<unk_78>",
81
+ "<unk_79>",
82
+ "<unk_80>",
83
+ "<unk_81>",
84
+ "<unk_82>",
85
+ "<unk_83>",
86
+ "<unk_84>",
87
+ "<unk_85>",
88
+ "<unk_86>",
89
+ "<unk_87>",
90
+ "<unk_88>",
91
+ "<unk_89>",
92
+ "<unk_90>",
93
+ "<unk_91>",
94
+ "<unk_92>",
95
+ "<unk_93>",
96
+ "<unk_94>",
97
+ "<unk_95>",
98
+ "<unk_96>",
99
+ "<unk_97>",
100
+ "<unk_98>",
101
+ "<unk_99>",
102
+ "<unk_100>",
103
+ "<unk_101>",
104
+ "<unk_102>"
105
+ ],
106
+ "clean_up_tokenization_spaces": true,
107
+ "eos_token": "</s>",
108
+ "full_tokenizer_file": null,
109
+ "mask_token": "<mask_2>",
110
+ "mask_token_sent": "<mask_1>",
111
+ "model_max_length": 512,
112
+ "offset": 103,
113
+ "pad_token": "<pad>",
114
+ "sp_model_kwargs": {},
115
+ "tokenizer_class": "PegasusTokenizer",
116
+ "unk_token": "<unk>"
117
+ }
models/prophetnet_model/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/prophetnet-large-uncased",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_cross_attention": true,
6
+ "architectures": [
7
+ "ProphetNetForConditionalGeneration"
8
+ ],
9
+ "attention_dropout": 0.1,
10
+ "bos_token_id": 102,
11
+ "decoder_ffn_dim": 4096,
12
+ "decoder_layerdrop": 0.0,
13
+ "decoder_max_position_embeddings": 514,
14
+ "decoder_start_token_id": 102,
15
+ "disable_ngram_loss": false,
16
+ "dropout": 0.1,
17
+ "early_stopping": true,
18
+ "encoder_ffn_dim": 4096,
19
+ "encoder_layerdrop": 0.0,
20
+ "encoder_max_position_embeddings": 513,
21
+ "eos_token_id": 102,
22
+ "eps": 0.0,
23
+ "hidden_size": 1024,
24
+ "id2label": {
25
+ "0": "LABEL_0",
26
+ "1": "LABEL_1",
27
+ "2": "LABEL_2"
28
+ },
29
+ "init_std": 0.02,
30
+ "is_encoder_decoder": true,
31
+ "label2id": {
32
+ "LABEL_0": 0,
33
+ "LABEL_1": 1,
34
+ "LABEL_2": 2
35
+ },
36
+ "length_penalty": 2.0,
37
+ "max_length": 142,
38
+ "max_position_embeddings": 512,
39
+ "model_type": "prophetnet",
40
+ "ngram": 2,
41
+ "no_repeat_ngram_size": 3,
42
+ "num_beams": 4,
43
+ "num_buckets": 32,
44
+ "num_decoder_attention_heads": 16,
45
+ "num_decoder_layers": 12,
46
+ "num_encoder_attention_heads": 16,
47
+ "num_encoder_layers": 12,
48
+ "output_past": false,
49
+ "pad_token_id": 0,
50
+ "prefix": " ",
51
+ "relative_max_distance": 128,
52
+ "task_specific_params": {
53
+ "summarization": {
54
+ "early_stopping": true,
55
+ "length_penalty": 2.0,
56
+ "no_repeat_ngram_size": 3,
57
+ "num_beams": 4
58
+ }
59
+ },
60
+ "torch_dtype": "float32",
61
+ "transformers_version": "4.30.2",
62
+ "use_cache": true,
63
+ "vocab_size": 30522
64
+ }
models/prophetnet_model/generation_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 102,
4
+ "decoder_start_token_id": 102,
5
+ "early_stopping": true,
6
+ "eos_token_id": 102,
7
+ "length_penalty": 2.0,
8
+ "max_length": 142,
9
+ "no_repeat_ngram_size": 3,
10
+ "num_beams": 4,
11
+ "pad_token_id": 0,
12
+ "transformers_version": "4.30.2"
13
+ }
models/prophetnet_model/prophetnet.tokenizer ADDED
The diff for this file is too large to render. See raw diff
 
models/prophetnet_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cedef47113e2d8b06409b81df84b67143f2cc9e4b2b334aee6ae1e74e1f1728a
3
+ size 1565504151
models/prophetnet_model/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "mask_token": "[MASK]",
3
+ "pad_token": "[PAD]",
4
+ "sep_token": "[SEP]",
5
+ "unk_token": "[UNK]"
6
+ }
models/prophetnet_model/tokenizer_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "clean_up_tokenization_spaces": true,
3
+ "do_basic_tokenize": true,
4
+ "do_lower_case": true,
5
+ "mask_token": "[MASK]",
6
+ "model_max_length": 512,
7
+ "never_split": null,
8
+ "pad_token": "[PAD]",
9
+ "sep_token": "[SEP]",
10
+ "strip_accents": null,
11
+ "tokenize_chinese_chars": true,
12
+ "tokenizer_class": "ProphetNetTokenizer",
13
+ "unk_token": "[UNK]",
14
+ "x_sep_token": "[X_SEP]"
15
+ }
models/sentTransfModelUtilsObj-old.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdbe04c21ae043f16817281b939a807f120a90686ddf1da5163d4f7a7739aacb
3
+ size 479806236
models/sentTransfModelUtilsObj.pkl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e532e73ad712cdd8b2c1e6361b81bd649fb62ab8b2e752ad392f0aa9a581af4
3
+ size 479806616
models/t5_model/config.json ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "t5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 3072,
7
+ "d_kv": 64,
8
+ "d_model": 768,
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": 12,
21
+ "num_heads": 12,
22
+ "num_layers": 12,
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": "4.30.2",
58
+ "use_cache": true,
59
+ "vocab_size": 32128
60
+ }
models/t5_model/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": "4.30.2"
7
+ }
models/t5_model/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab97165968edc4aacd30554d18d7beca7f18b3a83e1a47abbad29792d984651f
3
+ size 891691430
models/t5_model/special_tokens_map.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
models/t5_model/spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
+ size 791656
models/t5_model/tokenizer_config.json ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "sp_model_kwargs": {},
110
+ "tokenizer_class": "T5Tokenizer",
111
+ "unk_token": "<unk>"
112
+ }