lintang commited on
Commit
d46b546
1 Parent(s): e4ec632

fix tokenizer settings for step 2000000

Browse files
Files changed (4) hide show
  1. config.json +1 -1
  2. special_tokens_map.json +0 -1
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +133 -109
config.json CHANGED
@@ -24,7 +24,7 @@
24
  "relative_attention_num_buckets": 32,
25
  "scalable_attention": true,
26
  "tie_word_embeddings": false,
27
- "tokenizer_class": "T5Tokenizer",
28
  "torch_dtype": "bfloat16",
29
  "transformers_version": "4.31.0",
30
  "use_cache": true,
 
24
  "relative_attention_num_buckets": 32,
25
  "scalable_attention": true,
26
  "tie_word_embeddings": false,
27
+ "tokenizer_class": "LlamaTokenizerFast",
28
  "torch_dtype": "bfloat16",
29
  "transformers_version": "4.31.0",
30
  "use_cache": true,
special_tokens_map.json CHANGED
@@ -103,6 +103,5 @@
103
  ],
104
  "bos_token": "<s>",
105
  "eos_token": "</s>",
106
- "pad_token": "<pad>",
107
  "unk_token": "<unk>"
108
  }
 
103
  ],
104
  "bos_token": "<s>",
105
  "eos_token": "</s>",
 
106
  "unk_token": "<unk>"
107
  }
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -1,113 +1,137 @@
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
- "bos_token": "<s>",
105
- "eos_token": "</s>",
106
- "pad_token": "<unk>",
107
- "unk_token": "<unk>",
108
- "extra_ids": 100,
109
  "model_max_length": 512,
 
 
110
  "sp_model_kwargs": {},
111
- "spaces_between_special_tokens": false,
112
- "tokenizer_class": "T5Tokenizer"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
113
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_eos_token": true,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": false,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "legacy": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "model_max_length": 512,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
  "sp_model_kwargs": {},
26
+ "tokenizer_class": "LlamaTokenizerFast",
27
+ "unk_token": {
28
+ "__type": "AddedToken",
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "additional_special_tokens": [
36
+ "<extra_id_99>",
37
+ "<extra_id_98>",
38
+ "<extra_id_97>",
39
+ "<extra_id_96>",
40
+ "<extra_id_95>",
41
+ "<extra_id_94>",
42
+ "<extra_id_93>",
43
+ "<extra_id_92>",
44
+ "<extra_id_91>",
45
+ "<extra_id_90>",
46
+ "<extra_id_89>",
47
+ "<extra_id_88>",
48
+ "<extra_id_87>",
49
+ "<extra_id_86>",
50
+ "<extra_id_85>",
51
+ "<extra_id_84>",
52
+ "<extra_id_83>",
53
+ "<extra_id_82>",
54
+ "<extra_id_81>",
55
+ "<extra_id_80>",
56
+ "<extra_id_79>",
57
+ "<extra_id_78>",
58
+ "<extra_id_77>",
59
+ "<extra_id_76>",
60
+ "<extra_id_75>",
61
+ "<extra_id_74>",
62
+ "<extra_id_73>",
63
+ "<extra_id_72>",
64
+ "<extra_id_71>",
65
+ "<extra_id_70>",
66
+ "<extra_id_69>",
67
+ "<extra_id_68>",
68
+ "<extra_id_67>",
69
+ "<extra_id_66>",
70
+ "<extra_id_65>",
71
+ "<extra_id_64>",
72
+ "<extra_id_63>",
73
+ "<extra_id_62>",
74
+ "<extra_id_61>",
75
+ "<extra_id_60>",
76
+ "<extra_id_59>",
77
+ "<extra_id_58>",
78
+ "<extra_id_57>",
79
+ "<extra_id_56>",
80
+ "<extra_id_55>",
81
+ "<extra_id_54>",
82
+ "<extra_id_53>",
83
+ "<extra_id_52>",
84
+ "<extra_id_51>",
85
+ "<extra_id_50>",
86
+ "<extra_id_49>",
87
+ "<extra_id_48>",
88
+ "<extra_id_47>",
89
+ "<extra_id_46>",
90
+ "<extra_id_45>",
91
+ "<extra_id_44>",
92
+ "<extra_id_43>",
93
+ "<extra_id_42>",
94
+ "<extra_id_41>",
95
+ "<extra_id_40>",
96
+ "<extra_id_39>",
97
+ "<extra_id_38>",
98
+ "<extra_id_37>",
99
+ "<extra_id_36>",
100
+ "<extra_id_35>",
101
+ "<extra_id_34>",
102
+ "<extra_id_33>",
103
+ "<extra_id_32>",
104
+ "<extra_id_31>",
105
+ "<extra_id_30>",
106
+ "<extra_id_29>",
107
+ "<extra_id_28>",
108
+ "<extra_id_27>",
109
+ "<extra_id_26>",
110
+ "<extra_id_25>",
111
+ "<extra_id_24>",
112
+ "<extra_id_23>",
113
+ "<extra_id_22>",
114
+ "<extra_id_21>",
115
+ "<extra_id_20>",
116
+ "<extra_id_19>",
117
+ "<extra_id_18>",
118
+ "<extra_id_17>",
119
+ "<extra_id_16>",
120
+ "<extra_id_15>",
121
+ "<extra_id_14>",
122
+ "<extra_id_13>",
123
+ "<extra_id_12>",
124
+ "<extra_id_11>",
125
+ "<extra_id_10>",
126
+ "<extra_id_9>",
127
+ "<extra_id_8>",
128
+ "<extra_id_7>",
129
+ "<extra_id_6>",
130
+ "<extra_id_5>",
131
+ "<extra_id_4>",
132
+ "<extra_id_3>",
133
+ "<extra_id_2>",
134
+ "<extra_id_1>",
135
+ "<extra_id_0>"
136
+ ]
137
  }