hhou435 commited on
Commit
ddc38a7
1 Parent(s): c5f4945
Files changed (4) hide show
  1. config.json +5 -7
  2. pytorch_model.bin +2 -2
  3. tokenizer_config.json +1 -1
  4. vocab.txt +0 -2
config.json CHANGED
@@ -8,7 +8,7 @@
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": 768,
@@ -16,13 +16,13 @@
16
  "decoder_ffn_dim": 3072,
17
  "decoder_layerdrop": 0.0,
18
  "decoder_layers": 12,
19
- "decoder_start_token_id": 0,
20
  "dropout": 0.1,
21
  "encoder_attention_heads": 12,
22
  "encoder_ffn_dim": 3072,
23
  "encoder_layerdrop": 0.0,
24
  "encoder_layers": 12,
25
- "eos_token_id": 102,
26
  "extra_pos_embeddings": 1,
27
  "force_bos_token_to_be_generated": false,
28
  "forced_eos_token_id": 1,
@@ -39,9 +39,8 @@
39
  "LABEL_1": 1,
40
  "LABEL_2": 2
41
  },
42
- "length_penalty": 0.8,
43
  "max_length": 256,
44
- "max_position_embeddings": 512,
45
  "model_type": "pegasus",
46
  "normalize_before": true,
47
  "normalize_embedding": false,
@@ -50,7 +49,6 @@
50
  "scale_embedding": true,
51
  "static_position_embeddings": true,
52
  "transformers_version": "4.6.0",
53
- "tokenizer_class": "BertTokenizer",
54
  "use_cache": true,
55
- "vocab_size": 21130
56
  }
 
8
  "PegasusForConditionalGeneration"
9
  ],
10
  "attention_dropout": 0.1,
11
+ "bos_token_id": 101,
12
  "classif_dropout": 0.0,
13
  "classifier_dropout": 0.0,
14
  "d_model": 768,
 
16
  "decoder_ffn_dim": 3072,
17
  "decoder_layerdrop": 0.0,
18
  "decoder_layers": 12,
19
+ "decoder_start_token_id": 101,
20
  "dropout": 0.1,
21
  "encoder_attention_heads": 12,
22
  "encoder_ffn_dim": 3072,
23
  "encoder_layerdrop": 0.0,
24
  "encoder_layers": 12,
25
+ "eos_token_id": 1,
26
  "extra_pos_embeddings": 1,
27
  "force_bos_token_to_be_generated": false,
28
  "forced_eos_token_id": 1,
 
39
  "LABEL_1": 1,
40
  "LABEL_2": 2
41
  },
 
42
  "max_length": 256,
43
+ "max_position_embeddings": 1024,
44
  "model_type": "pegasus",
45
  "normalize_before": true,
46
  "normalize_embedding": false,
 
49
  "scale_embedding": true,
50
  "static_position_embeddings": true,
51
  "transformers_version": "4.6.0",
 
52
  "use_cache": true,
53
+ "vocab_size": 21128
54
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d899d06f51522a107365079361235f619b1784015e7f6e5af24e1d1b1c4b241
3
- size 862251247
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ac0b2cbcb21b7dc45fae80866753b0326d6e38deee26e8e84a01833f0f7ef4
3
+ size 865390831
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK1]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "pegasus"}
 
1
+ {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "pegasus"}
vocab.txt CHANGED
@@ -102,8 +102,6 @@
102
  [CLS]
103
  [SEP]
104
  [MASK]
105
- [MASK1]
106
- [MASK2]
107
  <S>
108
  <T>
109
  !
 
102
  [CLS]
103
  [SEP]
104
  [MASK]
 
 
105
  <S>
106
  <T>
107
  !