Hugging Face's logo

benjamin
/
TinyLlama-1.1B-intermediate-step-1431k-3T-starcoder-from-focus

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
benjamin commited on
Commit
02ad8ef
·
verified ·
1 Parent(s): dc740f4

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +21 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +26 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +209 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<commit_after>": 49227,
3
+ "<commit_before>": 49225,
4
+ "<commit_msg>": 49226,
5
+ "<empty_output>": 49224,
6
+ "<filename>": 49215,
7
+ "<fim_middle>": 49212,
8
+ "<fim_pad>": 49214,
9
+ "<fim_prefix>": 49211,
10
+ "<fim_suffix>": 49213,
11
+ "<gh_stars>": 49216,
12
+ "<issue_closed>": 49219,
13
+ "<issue_comment>": 49218,
14
+ "<issue_start>": 49217,
15
+ "<jupyter_code>": 49222,
16
+ "<jupyter_output>": 49223,
17
+ "<jupyter_start>": 49220,
18
+ "<jupyter_text>": 49221,
19
+ "<reponame>": 49228,
20
+ "<|endoftext|>": 49210
21
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<fim_prefix>",
5
+ "<fim_middle>",
6
+ "<fim_suffix>",
7
+ "<fim_pad>",
8
+ "<filename>",
9
+ "<gh_stars>",
10
+ "<issue_start>",
11
+ "<issue_comment>",
12
+ "<issue_closed>",
13
+ "<jupyter_start>",
14
+ "<jupyter_text>",
15
+ "<jupyter_code>",
16
+ "<jupyter_output>",
17
+ "<empty_output>",
18
+ "<commit_before>",
19
+ "<commit_msg>",
20
+ "<commit_after>",
21
+ "<reponame>"
22
+ ],
23
+ "bos_token": "<s>",
24
+ "eos_token": "</s>",
25
+ "unk_token": "<unk>"
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,209 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "49210": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "49211": {
37
+ "content": "<fim_prefix>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "49212": {
45
+ "content": "<fim_middle>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "49213": {
53
+ "content": "<fim_suffix>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "49214": {
61
+ "content": "<fim_pad>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "49215": {
69
+ "content": "<filename>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "49216": {
77
+ "content": "<gh_stars>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "49217": {
85
+ "content": "<issue_start>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "49218": {
93
+ "content": "<issue_comment>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "49219": {
101
+ "content": "<issue_closed>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "49220": {
109
+ "content": "<jupyter_start>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "49221": {
117
+ "content": "<jupyter_text>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "49222": {
125
+ "content": "<jupyter_code>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "49223": {
133
+ "content": "<jupyter_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49224": {
141
+ "content": "<empty_output>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49225": {
149
+ "content": "<commit_before>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49226": {
157
+ "content": "<commit_msg>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49227": {
165
+ "content": "<commit_after>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49228": {
173
+ "content": "<reponame>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ }
180
+ },
181
+ "additional_special_tokens": [
182
+ "<|endoftext|>",
183
+ "<fim_prefix>",
184
+ "<fim_middle>",
185
+ "<fim_suffix>",
186
+ "<fim_pad>",
187
+ "<filename>",
188
+ "<gh_stars>",
189
+ "<issue_start>",
190
+ "<issue_comment>",
191
+ "<issue_closed>",
192
+ "<jupyter_start>",
193
+ "<jupyter_text>",
194
+ "<jupyter_code>",
195
+ "<jupyter_output>",
196
+ "<empty_output>",
197
+ "<commit_before>",
198
+ "<commit_msg>",
199
+ "<commit_after>",
200
+ "<reponame>"
201
+ ],
202
+ "bos_token": "<s>",
203
+ "clean_up_tokenization_spaces": true,
204
+ "eos_token": "</s>",
205
+ "model_max_length": 1000000000000000019884624838656,
206
+ "tokenizer_class": "GPT2Tokenizer",
207
+ "unk_token": "<unk>",
208
+ "vocab_size": 49210
209
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff