N8Programs commited on
Commit
083750a
·
verified ·
1 Parent(s): 451a228

Add NextTerm tokenizer files and MLX config compatibility

Browse files
Files changed (24) hide show
  1. checkpoints/best_val/config.json +2 -1
  2. checkpoints/best_val/special_tokens_map.json +6 -0
  3. checkpoints/best_val/tokenizer.json +149 -0
  4. checkpoints/best_val/tokenizer_config.json +36 -0
  5. checkpoints/checkpoint_tokens_012000258345/config.json +2 -1
  6. checkpoints/checkpoint_tokens_012000258345/special_tokens_map.json +6 -0
  7. checkpoints/checkpoint_tokens_012000258345/tokenizer.json +149 -0
  8. checkpoints/checkpoint_tokens_012000258345/tokenizer_config.json +36 -0
  9. checkpoints/checkpoint_tokens_012500265837/config.json +2 -1
  10. checkpoints/checkpoint_tokens_012500265837/special_tokens_map.json +6 -0
  11. checkpoints/checkpoint_tokens_012500265837/tokenizer.json +149 -0
  12. checkpoints/checkpoint_tokens_012500265837/tokenizer_config.json +36 -0
  13. checkpoints/checkpoint_tokens_013000266889/config.json +2 -1
  14. checkpoints/checkpoint_tokens_013000266889/special_tokens_map.json +6 -0
  15. checkpoints/checkpoint_tokens_013000266889/tokenizer.json +149 -0
  16. checkpoints/checkpoint_tokens_013000266889/tokenizer_config.json +36 -0
  17. checkpoints/checkpoint_tokens_013500289737/config.json +2 -1
  18. checkpoints/checkpoint_tokens_013500289737/special_tokens_map.json +6 -0
  19. checkpoints/checkpoint_tokens_013500289737/tokenizer.json +149 -0
  20. checkpoints/checkpoint_tokens_013500289737/tokenizer_config.json +36 -0
  21. checkpoints/final_latest/config.json +2 -1
  22. checkpoints/final_latest/special_tokens_map.json +6 -0
  23. checkpoints/final_latest/tokenizer.json +149 -0
  24. checkpoints/final_latest/tokenizer_config.json +36 -0
checkpoints/best_val/config.json CHANGED
@@ -59,5 +59,6 @@
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
- "vocab_size": 16
 
63
  }
 
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
+ "vocab_size": 16,
63
+ "rope_theta": 1000000.0
64
  }
checkpoints/best_val/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<pad>"
6
+ }
checkpoints/best_val/tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 12,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 13,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 14,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "Replace",
39
+ "pattern": {
40
+ "Regex": "[^0-9,-]+"
41
+ },
42
+ "content": ""
43
+ },
44
+ {
45
+ "type": "Replace",
46
+ "pattern": {
47
+ "Regex": ",+"
48
+ },
49
+ "content": ","
50
+ },
51
+ {
52
+ "type": "Strip",
53
+ "strip_left": true,
54
+ "strip_right": true
55
+ },
56
+ {
57
+ "type": "Replace",
58
+ "pattern": {
59
+ "Regex": "^,+"
60
+ },
61
+ "content": ""
62
+ },
63
+ { "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Split",
68
+ "pattern": {
69
+ "Regex": ""
70
+ },
71
+ "behavior": "Isolated",
72
+ "invert": false
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ }
89
+ ],
90
+ "pair": [
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "<bos>": {
106
+ "id": "<bos>",
107
+ "ids": [
108
+ 12
109
+ ],
110
+ "tokens": [
111
+ "<bos>"
112
+ ]
113
+ }
114
+ }
115
+ },
116
+ "decoder": {
117
+ "type": "Sequence",
118
+ "decoders": [
119
+ {
120
+ "type": "Replace",
121
+ "pattern": {
122
+ "String": " "
123
+ },
124
+ "content": ""
125
+ }
126
+ ]
127
+ },
128
+ "model": {
129
+ "type": "WordLevel",
130
+ "vocab": {
131
+ "0": 0,
132
+ "1": 1,
133
+ "2": 2,
134
+ "3": 3,
135
+ "4": 4,
136
+ "5": 5,
137
+ "6": 6,
138
+ "7": 7,
139
+ "8": 8,
140
+ "9": 9,
141
+ "-": 10,
142
+ ",": 11,
143
+ "<bos>": 12,
144
+ "<eos>": 13,
145
+ "<pad>": 14
146
+ },
147
+ "unk_token": "<pad>"
148
+ }
149
+ }
checkpoints/best_val/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "12": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "13": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "14": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<bos>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<eos>",
31
+ "extra_special_tokens": {},
32
+ "model_max_length": 40960,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<pad>"
36
+ }
checkpoints/checkpoint_tokens_012000258345/config.json CHANGED
@@ -59,5 +59,6 @@
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
- "vocab_size": 16
 
63
  }
 
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
+ "vocab_size": 16,
63
+ "rope_theta": 1000000.0
64
  }
checkpoints/checkpoint_tokens_012000258345/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<pad>"
6
+ }
checkpoints/checkpoint_tokens_012000258345/tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 12,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 13,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 14,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "Replace",
39
+ "pattern": {
40
+ "Regex": "[^0-9,-]+"
41
+ },
42
+ "content": ""
43
+ },
44
+ {
45
+ "type": "Replace",
46
+ "pattern": {
47
+ "Regex": ",+"
48
+ },
49
+ "content": ","
50
+ },
51
+ {
52
+ "type": "Strip",
53
+ "strip_left": true,
54
+ "strip_right": true
55
+ },
56
+ {
57
+ "type": "Replace",
58
+ "pattern": {
59
+ "Regex": "^,+"
60
+ },
61
+ "content": ""
62
+ },
63
+ { "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Split",
68
+ "pattern": {
69
+ "Regex": ""
70
+ },
71
+ "behavior": "Isolated",
72
+ "invert": false
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ }
89
+ ],
90
+ "pair": [
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "<bos>": {
106
+ "id": "<bos>",
107
+ "ids": [
108
+ 12
109
+ ],
110
+ "tokens": [
111
+ "<bos>"
112
+ ]
113
+ }
114
+ }
115
+ },
116
+ "decoder": {
117
+ "type": "Sequence",
118
+ "decoders": [
119
+ {
120
+ "type": "Replace",
121
+ "pattern": {
122
+ "String": " "
123
+ },
124
+ "content": ""
125
+ }
126
+ ]
127
+ },
128
+ "model": {
129
+ "type": "WordLevel",
130
+ "vocab": {
131
+ "0": 0,
132
+ "1": 1,
133
+ "2": 2,
134
+ "3": 3,
135
+ "4": 4,
136
+ "5": 5,
137
+ "6": 6,
138
+ "7": 7,
139
+ "8": 8,
140
+ "9": 9,
141
+ "-": 10,
142
+ ",": 11,
143
+ "<bos>": 12,
144
+ "<eos>": 13,
145
+ "<pad>": 14
146
+ },
147
+ "unk_token": "<pad>"
148
+ }
149
+ }
checkpoints/checkpoint_tokens_012000258345/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "12": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "13": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "14": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<bos>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<eos>",
31
+ "extra_special_tokens": {},
32
+ "model_max_length": 40960,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<pad>"
36
+ }
checkpoints/checkpoint_tokens_012500265837/config.json CHANGED
@@ -59,5 +59,6 @@
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
- "vocab_size": 16
 
63
  }
 
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
+ "vocab_size": 16,
63
+ "rope_theta": 1000000.0
64
  }
checkpoints/checkpoint_tokens_012500265837/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<pad>"
6
+ }
checkpoints/checkpoint_tokens_012500265837/tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 12,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 13,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 14,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "Replace",
39
+ "pattern": {
40
+ "Regex": "[^0-9,-]+"
41
+ },
42
+ "content": ""
43
+ },
44
+ {
45
+ "type": "Replace",
46
+ "pattern": {
47
+ "Regex": ",+"
48
+ },
49
+ "content": ","
50
+ },
51
+ {
52
+ "type": "Strip",
53
+ "strip_left": true,
54
+ "strip_right": true
55
+ },
56
+ {
57
+ "type": "Replace",
58
+ "pattern": {
59
+ "Regex": "^,+"
60
+ },
61
+ "content": ""
62
+ },
63
+ { "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Split",
68
+ "pattern": {
69
+ "Regex": ""
70
+ },
71
+ "behavior": "Isolated",
72
+ "invert": false
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ }
89
+ ],
90
+ "pair": [
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "<bos>": {
106
+ "id": "<bos>",
107
+ "ids": [
108
+ 12
109
+ ],
110
+ "tokens": [
111
+ "<bos>"
112
+ ]
113
+ }
114
+ }
115
+ },
116
+ "decoder": {
117
+ "type": "Sequence",
118
+ "decoders": [
119
+ {
120
+ "type": "Replace",
121
+ "pattern": {
122
+ "String": " "
123
+ },
124
+ "content": ""
125
+ }
126
+ ]
127
+ },
128
+ "model": {
129
+ "type": "WordLevel",
130
+ "vocab": {
131
+ "0": 0,
132
+ "1": 1,
133
+ "2": 2,
134
+ "3": 3,
135
+ "4": 4,
136
+ "5": 5,
137
+ "6": 6,
138
+ "7": 7,
139
+ "8": 8,
140
+ "9": 9,
141
+ "-": 10,
142
+ ",": 11,
143
+ "<bos>": 12,
144
+ "<eos>": 13,
145
+ "<pad>": 14
146
+ },
147
+ "unk_token": "<pad>"
148
+ }
149
+ }
checkpoints/checkpoint_tokens_012500265837/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "12": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "13": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "14": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<bos>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<eos>",
31
+ "extra_special_tokens": {},
32
+ "model_max_length": 40960,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<pad>"
36
+ }
checkpoints/checkpoint_tokens_013000266889/config.json CHANGED
@@ -59,5 +59,6 @@
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
- "vocab_size": 16
 
63
  }
 
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
+ "vocab_size": 16,
63
+ "rope_theta": 1000000.0
64
  }
checkpoints/checkpoint_tokens_013000266889/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<pad>"
6
+ }
checkpoints/checkpoint_tokens_013000266889/tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 12,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 13,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 14,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "Replace",
39
+ "pattern": {
40
+ "Regex": "[^0-9,-]+"
41
+ },
42
+ "content": ""
43
+ },
44
+ {
45
+ "type": "Replace",
46
+ "pattern": {
47
+ "Regex": ",+"
48
+ },
49
+ "content": ","
50
+ },
51
+ {
52
+ "type": "Strip",
53
+ "strip_left": true,
54
+ "strip_right": true
55
+ },
56
+ {
57
+ "type": "Replace",
58
+ "pattern": {
59
+ "Regex": "^,+"
60
+ },
61
+ "content": ""
62
+ },
63
+ { "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Split",
68
+ "pattern": {
69
+ "Regex": ""
70
+ },
71
+ "behavior": "Isolated",
72
+ "invert": false
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ }
89
+ ],
90
+ "pair": [
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "<bos>": {
106
+ "id": "<bos>",
107
+ "ids": [
108
+ 12
109
+ ],
110
+ "tokens": [
111
+ "<bos>"
112
+ ]
113
+ }
114
+ }
115
+ },
116
+ "decoder": {
117
+ "type": "Sequence",
118
+ "decoders": [
119
+ {
120
+ "type": "Replace",
121
+ "pattern": {
122
+ "String": " "
123
+ },
124
+ "content": ""
125
+ }
126
+ ]
127
+ },
128
+ "model": {
129
+ "type": "WordLevel",
130
+ "vocab": {
131
+ "0": 0,
132
+ "1": 1,
133
+ "2": 2,
134
+ "3": 3,
135
+ "4": 4,
136
+ "5": 5,
137
+ "6": 6,
138
+ "7": 7,
139
+ "8": 8,
140
+ "9": 9,
141
+ "-": 10,
142
+ ",": 11,
143
+ "<bos>": 12,
144
+ "<eos>": 13,
145
+ "<pad>": 14
146
+ },
147
+ "unk_token": "<pad>"
148
+ }
149
+ }
checkpoints/checkpoint_tokens_013000266889/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "12": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "13": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "14": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<bos>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<eos>",
31
+ "extra_special_tokens": {},
32
+ "model_max_length": 40960,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<pad>"
36
+ }
checkpoints/checkpoint_tokens_013500289737/config.json CHANGED
@@ -59,5 +59,6 @@
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
- "vocab_size": 16
 
63
  }
 
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
+ "vocab_size": 16,
63
+ "rope_theta": 1000000.0
64
  }
checkpoints/checkpoint_tokens_013500289737/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<pad>"
6
+ }
checkpoints/checkpoint_tokens_013500289737/tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 12,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 13,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 14,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "Replace",
39
+ "pattern": {
40
+ "Regex": "[^0-9,-]+"
41
+ },
42
+ "content": ""
43
+ },
44
+ {
45
+ "type": "Replace",
46
+ "pattern": {
47
+ "Regex": ",+"
48
+ },
49
+ "content": ","
50
+ },
51
+ {
52
+ "type": "Strip",
53
+ "strip_left": true,
54
+ "strip_right": true
55
+ },
56
+ {
57
+ "type": "Replace",
58
+ "pattern": {
59
+ "Regex": "^,+"
60
+ },
61
+ "content": ""
62
+ },
63
+ { "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Split",
68
+ "pattern": {
69
+ "Regex": ""
70
+ },
71
+ "behavior": "Isolated",
72
+ "invert": false
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ }
89
+ ],
90
+ "pair": [
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "<bos>": {
106
+ "id": "<bos>",
107
+ "ids": [
108
+ 12
109
+ ],
110
+ "tokens": [
111
+ "<bos>"
112
+ ]
113
+ }
114
+ }
115
+ },
116
+ "decoder": {
117
+ "type": "Sequence",
118
+ "decoders": [
119
+ {
120
+ "type": "Replace",
121
+ "pattern": {
122
+ "String": " "
123
+ },
124
+ "content": ""
125
+ }
126
+ ]
127
+ },
128
+ "model": {
129
+ "type": "WordLevel",
130
+ "vocab": {
131
+ "0": 0,
132
+ "1": 1,
133
+ "2": 2,
134
+ "3": 3,
135
+ "4": 4,
136
+ "5": 5,
137
+ "6": 6,
138
+ "7": 7,
139
+ "8": 8,
140
+ "9": 9,
141
+ "-": 10,
142
+ ",": 11,
143
+ "<bos>": 12,
144
+ "<eos>": 13,
145
+ "<pad>": 14
146
+ },
147
+ "unk_token": "<pad>"
148
+ }
149
+ }
checkpoints/checkpoint_tokens_013500289737/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "12": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "13": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "14": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<bos>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<eos>",
31
+ "extra_special_tokens": {},
32
+ "model_max_length": 40960,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<pad>"
36
+ }
checkpoints/final_latest/config.json CHANGED
@@ -59,5 +59,6 @@
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
- "vocab_size": 16
 
63
  }
 
59
  "transformers_version": "5.9.0",
60
  "use_cache": true,
61
  "use_sliding_window": false,
62
+ "vocab_size": 16,
63
+ "rope_theta": 1000000.0
64
  }
checkpoints/final_latest/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<bos>",
3
+ "eos_token": "<eos>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<pad>"
6
+ }
checkpoints/final_latest/tokenizer.json ADDED
@@ -0,0 +1,149 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 12,
8
+ "content": "<bos>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 13,
17
+ "content": "<eos>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 14,
26
+ "content": "<pad>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ }
33
+ ],
34
+ "normalizer": {
35
+ "type": "Sequence",
36
+ "normalizers": [
37
+ {
38
+ "type": "Replace",
39
+ "pattern": {
40
+ "Regex": "[^0-9,-]+"
41
+ },
42
+ "content": ""
43
+ },
44
+ {
45
+ "type": "Replace",
46
+ "pattern": {
47
+ "Regex": ",+"
48
+ },
49
+ "content": ","
50
+ },
51
+ {
52
+ "type": "Strip",
53
+ "strip_left": true,
54
+ "strip_right": true
55
+ },
56
+ {
57
+ "type": "Replace",
58
+ "pattern": {
59
+ "Regex": "^,+"
60
+ },
61
+ "content": ""
62
+ },
63
+ { "type": "Replace", "pattern": { "Regex": ",{2,}$" }, "content": "," }
64
+ ]
65
+ },
66
+ "pre_tokenizer": {
67
+ "type": "Split",
68
+ "pattern": {
69
+ "Regex": ""
70
+ },
71
+ "behavior": "Isolated",
72
+ "invert": false
73
+ },
74
+ "post_processor": {
75
+ "type": "TemplateProcessing",
76
+ "single": [
77
+ {
78
+ "SpecialToken": {
79
+ "id": "<bos>",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "A",
86
+ "type_id": 0
87
+ }
88
+ }
89
+ ],
90
+ "pair": [
91
+ {
92
+ "Sequence": {
93
+ "id": "A",
94
+ "type_id": 0
95
+ }
96
+ },
97
+ {
98
+ "Sequence": {
99
+ "id": "B",
100
+ "type_id": 1
101
+ }
102
+ }
103
+ ],
104
+ "special_tokens": {
105
+ "<bos>": {
106
+ "id": "<bos>",
107
+ "ids": [
108
+ 12
109
+ ],
110
+ "tokens": [
111
+ "<bos>"
112
+ ]
113
+ }
114
+ }
115
+ },
116
+ "decoder": {
117
+ "type": "Sequence",
118
+ "decoders": [
119
+ {
120
+ "type": "Replace",
121
+ "pattern": {
122
+ "String": " "
123
+ },
124
+ "content": ""
125
+ }
126
+ ]
127
+ },
128
+ "model": {
129
+ "type": "WordLevel",
130
+ "vocab": {
131
+ "0": 0,
132
+ "1": 1,
133
+ "2": 2,
134
+ "3": 3,
135
+ "4": 4,
136
+ "5": 5,
137
+ "6": 6,
138
+ "7": 7,
139
+ "8": 8,
140
+ "9": 9,
141
+ "-": 10,
142
+ ",": 11,
143
+ "<bos>": 12,
144
+ "<eos>": 13,
145
+ "<pad>": 14
146
+ },
147
+ "unk_token": "<pad>"
148
+ }
149
+ }
checkpoints/final_latest/tokenizer_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "12": {
4
+ "content": "<bos>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "13": {
12
+ "content": "<eos>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "14": {
20
+ "content": "<pad>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<bos>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "<eos>",
31
+ "extra_special_tokens": {},
32
+ "model_max_length": 40960,
33
+ "pad_token": "<pad>",
34
+ "tokenizer_class": "PreTrainedTokenizerFast",
35
+ "unk_token": "<pad>"
36
+ }