Upload 9 files
Browse files- added_tokens.json +125 -0
- config.json +75 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +39 -0
- tokenizer_config.json +65 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<S0>": 50268,
|
3 |
+
"<S100>": 50368,
|
4 |
+
"<S101>": 50369,
|
5 |
+
"<S102>": 50370,
|
6 |
+
"<S103>": 50371,
|
7 |
+
"<S104>": 50372,
|
8 |
+
"<S105>": 50373,
|
9 |
+
"<S106>": 50374,
|
10 |
+
"<S107>": 50375,
|
11 |
+
"<S108>": 50376,
|
12 |
+
"<S109>": 50377,
|
13 |
+
"<S10>": 50278,
|
14 |
+
"<S110>": 50378,
|
15 |
+
"<S111>": 50379,
|
16 |
+
"<S112>": 50380,
|
17 |
+
"<S113>": 50381,
|
18 |
+
"<S114>": 50382,
|
19 |
+
"<S115>": 50383,
|
20 |
+
"<S116>": 50384,
|
21 |
+
"<S117>": 50385,
|
22 |
+
"<S118>": 50386,
|
23 |
+
"<S119>": 50387,
|
24 |
+
"<S11>": 50279,
|
25 |
+
"<S12>": 50280,
|
26 |
+
"<S13>": 50281,
|
27 |
+
"<S14>": 50282,
|
28 |
+
"<S15>": 50283,
|
29 |
+
"<S16>": 50284,
|
30 |
+
"<S17>": 50285,
|
31 |
+
"<S18>": 50286,
|
32 |
+
"<S19>": 50287,
|
33 |
+
"<S1>": 50269,
|
34 |
+
"<S20>": 50288,
|
35 |
+
"<S21>": 50289,
|
36 |
+
"<S22>": 50290,
|
37 |
+
"<S23>": 50291,
|
38 |
+
"<S24>": 50292,
|
39 |
+
"<S25>": 50293,
|
40 |
+
"<S26>": 50294,
|
41 |
+
"<S27>": 50295,
|
42 |
+
"<S28>": 50296,
|
43 |
+
"<S29>": 50297,
|
44 |
+
"<S2>": 50270,
|
45 |
+
"<S30>": 50298,
|
46 |
+
"<S31>": 50299,
|
47 |
+
"<S32>": 50300,
|
48 |
+
"<S33>": 50301,
|
49 |
+
"<S34>": 50302,
|
50 |
+
"<S35>": 50303,
|
51 |
+
"<S36>": 50304,
|
52 |
+
"<S37>": 50305,
|
53 |
+
"<S38>": 50306,
|
54 |
+
"<S39>": 50307,
|
55 |
+
"<S3>": 50271,
|
56 |
+
"<S40>": 50308,
|
57 |
+
"<S41>": 50309,
|
58 |
+
"<S42>": 50310,
|
59 |
+
"<S43>": 50311,
|
60 |
+
"<S44>": 50312,
|
61 |
+
"<S45>": 50313,
|
62 |
+
"<S46>": 50314,
|
63 |
+
"<S47>": 50315,
|
64 |
+
"<S48>": 50316,
|
65 |
+
"<S49>": 50317,
|
66 |
+
"<S4>": 50272,
|
67 |
+
"<S50>": 50318,
|
68 |
+
"<S51>": 50319,
|
69 |
+
"<S52>": 50320,
|
70 |
+
"<S53>": 50321,
|
71 |
+
"<S54>": 50322,
|
72 |
+
"<S55>": 50323,
|
73 |
+
"<S56>": 50324,
|
74 |
+
"<S57>": 50325,
|
75 |
+
"<S58>": 50326,
|
76 |
+
"<S59>": 50327,
|
77 |
+
"<S5>": 50273,
|
78 |
+
"<S60>": 50328,
|
79 |
+
"<S61>": 50329,
|
80 |
+
"<S62>": 50330,
|
81 |
+
"<S63>": 50331,
|
82 |
+
"<S64>": 50332,
|
83 |
+
"<S65>": 50333,
|
84 |
+
"<S66>": 50334,
|
85 |
+
"<S67>": 50335,
|
86 |
+
"<S68>": 50336,
|
87 |
+
"<S69>": 50337,
|
88 |
+
"<S6>": 50274,
|
89 |
+
"<S70>": 50338,
|
90 |
+
"<S71>": 50339,
|
91 |
+
"<S72>": 50340,
|
92 |
+
"<S73>": 50341,
|
93 |
+
"<S74>": 50342,
|
94 |
+
"<S75>": 50343,
|
95 |
+
"<S76>": 50344,
|
96 |
+
"<S77>": 50345,
|
97 |
+
"<S78>": 50346,
|
98 |
+
"<S79>": 50347,
|
99 |
+
"<S7>": 50275,
|
100 |
+
"<S80>": 50348,
|
101 |
+
"<S81>": 50349,
|
102 |
+
"<S82>": 50350,
|
103 |
+
"<S83>": 50351,
|
104 |
+
"<S84>": 50352,
|
105 |
+
"<S85>": 50353,
|
106 |
+
"<S86>": 50354,
|
107 |
+
"<S87>": 50355,
|
108 |
+
"<S88>": 50356,
|
109 |
+
"<S89>": 50357,
|
110 |
+
"<S8>": 50276,
|
111 |
+
"<S90>": 50358,
|
112 |
+
"<S91>": 50359,
|
113 |
+
"<S92>": 50360,
|
114 |
+
"<S93>": 50361,
|
115 |
+
"<S94>": 50362,
|
116 |
+
"<S95>": 50363,
|
117 |
+
"<S96>": 50364,
|
118 |
+
"<S97>": 50365,
|
119 |
+
"<S98>": 50366,
|
120 |
+
"<S99>": 50367,
|
121 |
+
"<S9>": 50277,
|
122 |
+
"<eos>": 50267,
|
123 |
+
"[orig]": 50266,
|
124 |
+
"[shuffled]": 50265
|
125 |
+
}
|
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "facebook/bart-base",
|
3 |
+
"activation_dropout": 0.1,
|
4 |
+
"activation_function": "gelu",
|
5 |
+
"add_bias_logits": false,
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.1,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.1,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 768,
|
15 |
+
"decoder_attention_heads": 12,
|
16 |
+
"decoder_ffn_dim": 3072,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 6,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 12,
|
23 |
+
"encoder_ffn_dim": 3072,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 6,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"forced_bos_token_id": 0,
|
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_position_embeddings": 1024,
|
43 |
+
"model_type": "bart",
|
44 |
+
"no_repeat_ngram_size": 3,
|
45 |
+
"normalize_before": false,
|
46 |
+
"normalize_embedding": true,
|
47 |
+
"num_beams": 4,
|
48 |
+
"num_hidden_layers": 6,
|
49 |
+
"pad_token_id": 1,
|
50 |
+
"scale_embedding": false,
|
51 |
+
"task_specific_params": {
|
52 |
+
"summarization": {
|
53 |
+
"length_penalty": 1.0,
|
54 |
+
"max_length": 128,
|
55 |
+
"min_length": 12,
|
56 |
+
"num_beams": 4
|
57 |
+
},
|
58 |
+
"summarization_cnn": {
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"num_beams": 4
|
63 |
+
},
|
64 |
+
"summarization_xsum": {
|
65 |
+
"length_penalty": 1.0,
|
66 |
+
"max_length": 62,
|
67 |
+
"min_length": 11,
|
68 |
+
"num_beams": 6
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.26.1",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 50388
|
75 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_bos_token_id": 0,
|
8 |
+
"forced_eos_token_id": 2,
|
9 |
+
"no_repeat_ngram_size": 3,
|
10 |
+
"num_beams": 4,
|
11 |
+
"pad_token_id": 1,
|
12 |
+
"transformers_version": "4.26.1"
|
13 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0346a183e8a08c8699dc449e6be4d6c838bce10b76e20345521a7621d9b4379
|
3 |
+
size 558349597
|
special_tokens_map.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<eos>",
|
17 |
+
"mask_token": {
|
18 |
+
"content": "<mask>",
|
19 |
+
"lstrip": true,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
},
|
24 |
+
"pad_token": "<pad>",
|
25 |
+
"sep_token": {
|
26 |
+
"content": "</s>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
},
|
32 |
+
"unk_token": {
|
33 |
+
"content": "<unk>",
|
34 |
+
"lstrip": false,
|
35 |
+
"normalized": true,
|
36 |
+
"rstrip": false,
|
37 |
+
"single_word": false
|
38 |
+
}
|
39 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "<s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"do_lower_case": false,
|
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 |
+
"name_or_path": "facebook/bart-base",
|
39 |
+
"pad_token": {
|
40 |
+
"__type": "AddedToken",
|
41 |
+
"content": "<pad>",
|
42 |
+
"lstrip": false,
|
43 |
+
"normalized": true,
|
44 |
+
"rstrip": false,
|
45 |
+
"single_word": false
|
46 |
+
},
|
47 |
+
"sep_token": {
|
48 |
+
"__type": "AddedToken",
|
49 |
+
"content": "</s>",
|
50 |
+
"lstrip": false,
|
51 |
+
"normalized": true,
|
52 |
+
"rstrip": false,
|
53 |
+
"single_word": false
|
54 |
+
},
|
55 |
+
"special_tokens_map_file": null,
|
56 |
+
"tokenizer_class": "BartTokenizer",
|
57 |
+
"unk_token": {
|
58 |
+
"__type": "AddedToken",
|
59 |
+
"content": "<unk>",
|
60 |
+
"lstrip": false,
|
61 |
+
"normalized": true,
|
62 |
+
"rstrip": false,
|
63 |
+
"single_word": false
|
64 |
+
}
|
65 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4e0b8ecf9623a5a75ddb09474d05d339b938ccaba44763164310766117a4a78
|
3 |
+
size 1339
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|