Matttttttt commited on
Commit
00119a0
1 Parent(s): 0ef6c23

Upload model/tokenizer and their configs.

Browse files
config.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./japanese_bart_large_2.0_torch/",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": true,
7
+ "architectures": [
8
+ "MBartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
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": 12,
19
+ "decoder_start_token_id": 2,
20
+ "do_blenderbot_90_layernorm": false,
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
+ "extra_pos_embeddings": 2,
29
+ "force_bos_token_to_be_generated": false,
30
+ "forced_eos_token_id": 2,
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
+ "max_position_embeddings": 1024,
44
+ "model_type": "mbart",
45
+ "no_repeat_ngram_size": 3,
46
+ "normalize_before": true,
47
+ "normalize_embedding": true,
48
+ "num_beams": 4,
49
+ "num_hidden_layers": 12,
50
+ "pad_token_id": 1,
51
+ "scale_embedding": false,
52
+ "static_position_embeddings": false,
53
+ "task_specific_params": {
54
+ "summarization": {
55
+ "length_penalty": 1.0,
56
+ "max_length": 128,
57
+ "min_length": 12,
58
+ "num_beams": 4
59
+ },
60
+ "summarization_cnn": {
61
+ "length_penalty": 2.0,
62
+ "max_length": 142,
63
+ "min_length": 56,
64
+ "num_beams": 4
65
+ },
66
+ "summarization_xsum": {
67
+ "length_penalty": 1.0,
68
+ "max_length": 62,
69
+ "min_length": 11,
70
+ "num_beams": 6
71
+ }
72
+ },
73
+ "torch_dtype": "float32",
74
+ "transformers_version": "4.24.0",
75
+ "use_cache": true,
76
+ "vocab_size": 32002
77
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e3b387144970a1a43cca967fa4001760a3908f92e2f807c0d0abb86be34e2a8
3
+ size 1550677177
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9226612d029bfade0621f401cb605740dc0a8ca88400e89ffdce26702ee266
3
+ size 588767
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": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<pad>",
14
+ "sep_token": "</s>",
15
+ "sp_model_kwargs": {},
16
+ "tokenizer_class": "XLMRobertaTokenizer",
17
+ "unk_token": "<unk>"
18
+ }