Zihao Li
commited on
Upload 8 files
Browse files- added_tokens.json +100 -0
- config.json +75 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.25>": 50266,
|
3 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.2>": 50265,
|
4 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.35>": 50268,
|
5 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.3>": 50267,
|
6 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.45>": 50270,
|
7 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.4>": 50269,
|
8 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.55>": 50272,
|
9 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.5>": 50271,
|
10 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.65>": 50274,
|
11 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.6>": 50273,
|
12 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.75>": 50276,
|
13 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.7>": 50275,
|
14 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.85>": 50278,
|
15 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.8>": 50277,
|
16 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.95>": 50280,
|
17 |
+
"<DEPENDENCYTREEDEPTHRATIO_0.9>": 50279,
|
18 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.05>": 50282,
|
19 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.0>": 50281,
|
20 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.15>": 50284,
|
21 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.1>": 50283,
|
22 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.25>": 50286,
|
23 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.2>": 50285,
|
24 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.35>": 50288,
|
25 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.3>": 50287,
|
26 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.45>": 50290,
|
27 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.4>": 50289,
|
28 |
+
"<DEPENDENCYTREEDEPTHRATIO_1.5>": 50291,
|
29 |
+
"<LENGTHRATIO_0.25>": 50320,
|
30 |
+
"<LENGTHRATIO_0.2>": 50319,
|
31 |
+
"<LENGTHRATIO_0.35>": 50322,
|
32 |
+
"<LENGTHRATIO_0.3>": 50321,
|
33 |
+
"<LENGTHRATIO_0.45>": 50324,
|
34 |
+
"<LENGTHRATIO_0.4>": 50323,
|
35 |
+
"<LENGTHRATIO_0.55>": 50326,
|
36 |
+
"<LENGTHRATIO_0.5>": 50325,
|
37 |
+
"<LENGTHRATIO_0.65>": 50328,
|
38 |
+
"<LENGTHRATIO_0.6>": 50327,
|
39 |
+
"<LENGTHRATIO_0.75>": 50330,
|
40 |
+
"<LENGTHRATIO_0.7>": 50329,
|
41 |
+
"<LENGTHRATIO_0.85>": 50332,
|
42 |
+
"<LENGTHRATIO_0.8>": 50331,
|
43 |
+
"<LENGTHRATIO_0.95>": 50334,
|
44 |
+
"<LENGTHRATIO_0.9>": 50333,
|
45 |
+
"<LENGTHRATIO_1.05>": 50336,
|
46 |
+
"<LENGTHRATIO_1.0>": 50335,
|
47 |
+
"<LENGTHRATIO_1.15>": 50338,
|
48 |
+
"<LENGTHRATIO_1.1>": 50337,
|
49 |
+
"<LENGTHRATIO_1.25>": 50340,
|
50 |
+
"<LENGTHRATIO_1.2>": 50339,
|
51 |
+
"<LENGTHRATIO_1.35>": 50342,
|
52 |
+
"<LENGTHRATIO_1.3>": 50341,
|
53 |
+
"<LENGTHRATIO_1.45>": 50344,
|
54 |
+
"<LENGTHRATIO_1.4>": 50343,
|
55 |
+
"<LENGTHRATIO_1.5>": 50345,
|
56 |
+
"<REPLACEONLYLEVENSHTEIN_0.25>": 50347,
|
57 |
+
"<REPLACEONLYLEVENSHTEIN_0.2>": 50346,
|
58 |
+
"<REPLACEONLYLEVENSHTEIN_0.35>": 50349,
|
59 |
+
"<REPLACEONLYLEVENSHTEIN_0.3>": 50348,
|
60 |
+
"<REPLACEONLYLEVENSHTEIN_0.45>": 50351,
|
61 |
+
"<REPLACEONLYLEVENSHTEIN_0.4>": 50350,
|
62 |
+
"<REPLACEONLYLEVENSHTEIN_0.55>": 50353,
|
63 |
+
"<REPLACEONLYLEVENSHTEIN_0.5>": 50352,
|
64 |
+
"<REPLACEONLYLEVENSHTEIN_0.65>": 50355,
|
65 |
+
"<REPLACEONLYLEVENSHTEIN_0.6>": 50354,
|
66 |
+
"<REPLACEONLYLEVENSHTEIN_0.75>": 50357,
|
67 |
+
"<REPLACEONLYLEVENSHTEIN_0.7>": 50356,
|
68 |
+
"<REPLACEONLYLEVENSHTEIN_0.85>": 50359,
|
69 |
+
"<REPLACEONLYLEVENSHTEIN_0.8>": 50358,
|
70 |
+
"<REPLACEONLYLEVENSHTEIN_0.95>": 50361,
|
71 |
+
"<REPLACEONLYLEVENSHTEIN_0.9>": 50360,
|
72 |
+
"<REPLACEONLYLEVENSHTEIN_1.0>": 50362,
|
73 |
+
"<WORDRANKRATIO_0.25>": 50293,
|
74 |
+
"<WORDRANKRATIO_0.2>": 50292,
|
75 |
+
"<WORDRANKRATIO_0.35>": 50295,
|
76 |
+
"<WORDRANKRATIO_0.3>": 50294,
|
77 |
+
"<WORDRANKRATIO_0.45>": 50297,
|
78 |
+
"<WORDRANKRATIO_0.4>": 50296,
|
79 |
+
"<WORDRANKRATIO_0.55>": 50299,
|
80 |
+
"<WORDRANKRATIO_0.5>": 50298,
|
81 |
+
"<WORDRANKRATIO_0.65>": 50301,
|
82 |
+
"<WORDRANKRATIO_0.6>": 50300,
|
83 |
+
"<WORDRANKRATIO_0.75>": 50303,
|
84 |
+
"<WORDRANKRATIO_0.7>": 50302,
|
85 |
+
"<WORDRANKRATIO_0.85>": 50305,
|
86 |
+
"<WORDRANKRATIO_0.8>": 50304,
|
87 |
+
"<WORDRANKRATIO_0.95>": 50307,
|
88 |
+
"<WORDRANKRATIO_0.9>": 50306,
|
89 |
+
"<WORDRANKRATIO_1.05>": 50309,
|
90 |
+
"<WORDRANKRATIO_1.0>": 50308,
|
91 |
+
"<WORDRANKRATIO_1.15>": 50311,
|
92 |
+
"<WORDRANKRATIO_1.1>": 50310,
|
93 |
+
"<WORDRANKRATIO_1.25>": 50313,
|
94 |
+
"<WORDRANKRATIO_1.2>": 50312,
|
95 |
+
"<WORDRANKRATIO_1.35>": 50315,
|
96 |
+
"<WORDRANKRATIO_1.3>": 50314,
|
97 |
+
"<WORDRANKRATIO_1.45>": 50317,
|
98 |
+
"<WORDRANKRATIO_1.4>": 50316,
|
99 |
+
"<WORDRANKRATIO_1.5>": 50318
|
100 |
+
}
|
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": "4.20.1",
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 50363
|
75 |
+
}
|
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 sha256:854e48e4ad357f8bee9111b8be084d22e8562abd417937981ef8598a626c4a0e
|
3 |
+
size 558270585
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"eos_token": "</s>",
|
6 |
+
"errors": "replace",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"model_max_length": 1024,
|
9 |
+
"name_or_path": "facebook/bart-base",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"special_tokens_map_file": null,
|
13 |
+
"tokenizer_class": "BartTokenizer",
|
14 |
+
"trim_offsets": true,
|
15 |
+
"unk_token": "<unk>"
|
16 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|