Hugging Face's logo

webAI-Official
/
TwIL-LM

Text Generation
Transformers
Safetensors
GGUF
English
llama
formal-logic
reasoning
lora
model-merging
wise-ft
reinforcement-learning
grpo
smollm2
twil-lm
conversational
text-generation-inference
Model card Files
xet
 Community
5

TwIL-LM2: v5 MGPO weights, normalised tokenizer metadata

#4
by anurag051194 - opened
base: refs/heads/main
←
from: refs/pr/4
Discussion Files changed
+171
-4
Files changed (2) hide show
  1. special_tokens_map.json +30 -0
  2. tokenizer_config.json +141 -4
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|im_start|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|im_end|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer_config.json CHANGED
@@ -1,14 +1,151 @@
1
  {
2
  "add_prefix_space": false,
3
- "backend": "tokenizers",
4
  "bos_token": "<|im_start|>",
5
  "clean_up_tokenization_spaces": false,
6
  "eos_token": "<|im_end|>",
7
  "errors": "replace",
8
- "is_local": true,
9
  "model_max_length": 8192,
10
  "pad_token": "<|im_end|>",
11
- "tokenizer_class": "GPT2Tokenizer",
12
  "unk_token": "<|endoftext|>",
13
- "vocab_size": 49152
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
 
1
  {
2
  "add_prefix_space": false,
 
3
  "bos_token": "<|im_start|>",
4
  "clean_up_tokenization_spaces": false,
5
  "eos_token": "<|im_end|>",
6
  "errors": "replace",
 
7
  "model_max_length": 8192,
8
  "pad_token": "<|im_end|>",
9
+ "tokenizer_class": "PreTrainedTokenizerFast",
10
  "unk_token": "<|endoftext|>",
11
+ "vocab_size": 49152,
12
+ "added_tokens_decoder": {
13
+ "0": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "1": {
22
+ "content": "<|im_start|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "2": {
30
+ "content": "<|im_end|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "3": {
38
+ "content": "<repo_name>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "4": {
46
+ "content": "<reponame>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "5": {
54
+ "content": "<file_sep>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "6": {
62
+ "content": "<filename>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "7": {
70
+ "content": "<gh_stars>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "8": {
78
+ "content": "<issue_start>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "9": {
86
+ "content": "<issue_comment>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "10": {
94
+ "content": "<issue_closed>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "11": {
102
+ "content": "<jupyter_start>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "12": {
110
+ "content": "<jupyter_text>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "13": {
118
+ "content": "<jupyter_code>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "14": {
126
+ "content": "<jupyter_output>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "15": {
134
+ "content": "<jupyter_script>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "16": {
142
+ "content": "<empty_output>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ }
149
+ },
150
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
151
  }