nuvardthecat/SmolCourse

1{
2  "add_prefix_space": false,
3  "added_tokens_decoder": {
4    "0": {
5      "content": "<|endoftext|>",
6      "lstrip": false,
7      "normalized": false,
8      "rstrip": false,
9      "single_word": false,
10      "special": true
11    },
12    "1": {
13      "content": "<|im_start|>",
14      "lstrip": false,
15      "normalized": false,
16      "rstrip": false,
17      "single_word": false,
18      "special": true
19    },
20    "2": {
21      "content": "<|im_end|>",
22      "lstrip": false,
23      "normalized": false,
24      "rstrip": false,
25      "single_word": false,
26      "special": true
27    },
28    "3": {
29      "content": "<repo_name>",
30      "lstrip": false,
31      "normalized": false,
32      "rstrip": false,
33      "single_word": false,
34      "special": true
35    },
36    "4": {
37      "content": "<reponame>",
38      "lstrip": false,
39      "normalized": false,
40      "rstrip": false,
41      "single_word": false,
42      "special": true
43    },
44    "5": {
45      "content": "<file_sep>",
46      "lstrip": false,
47      "normalized": false,
48      "rstrip": false,
49      "single_word": false,
50      "special": true
51    },
52    "6": {
53      "content": "<filename>",
54      "lstrip": false,
55      "normalized": false,
56      "rstrip": false,
57      "single_word": false,
58      "special": true
59    },
60    "7": {
61      "content": "<gh_stars>",
62      "lstrip": false,
63      "normalized": false,
64      "rstrip": false,
65      "single_word": false,
66      "special": true
67    },
68    "8": {
69      "content": "<issue_start>",
70      "lstrip": false,
71      "normalized": false,
72      "rstrip": false,
73      "single_word": false,
74      "special": true
75    },
76    "9": {
77      "content": "<issue_comment>",
78      "lstrip": false,
79      "normalized": false,
80      "rstrip": false,
81      "single_word": false,
82      "special": true
83    },
84    "10": {
85      "content": "<issue_closed>",
86      "lstrip": false,
87      "normalized": false,
88      "rstrip": false,
89      "single_word": false,
90      "special": true
91    },
92    "11": {
93      "content": "<jupyter_start>",
94      "lstrip": false,
95      "normalized": false,
96      "rstrip": false,
97      "single_word": false,
98      "special": true
99    },
100    "12": {
101      "content": "<jupyter_text>",
102      "lstrip": false,
103      "normalized": false,
104      "rstrip": false,
105      "single_word": false,
106      "special": true
107    },
108    "13": {
109      "content": "<jupyter_code>",
110      "lstrip": false,
111      "normalized": false,
112      "rstrip": false,
113      "single_word": false,
114      "special": true
115    },
116    "14": {
117      "content": "<jupyter_output>",
118      "lstrip": false,
119      "normalized": false,
120      "rstrip": false,
121      "single_word": false,
122      "special": true
123    },
124    "15": {
125      "content": "<jupyter_script>",
126      "lstrip": false,
127      "normalized": false,
128      "rstrip": false,
129      "single_word": false,
130      "special": true
131    },
132    "16": {
133      "content": "<empty_output>",
134      "lstrip": false,
135      "normalized": false,
136      "rstrip": false,
137      "single_word": false,
138      "special": true
139    }
140  },
141  "additional_special_tokens": [
142    "<|im_start|>",
143    "<|im_end|>"
144  ],
145  "bos_token": "<|im_start|>",
146  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147  "clean_up_tokenization_spaces": false,
148  "eos_token": "<|im_end|>",
149  "model_max_length": 8192,
150  "pad_token": "<|im_end|>",
151  "tokenizer_class": "GPT2Tokenizer",
152  "unk_token": "<|endoftext|>",
153  "vocab_size": 49152
154}
155