Hugging Face's logo

reaperdoesntknow
/
CasualSwarms

Text Generation
Transformers
Safetensors
English
swarm_agi
swarm
ai
agent
llm
convergent
cpu
fp32
agi
convergentintel
Model card Files
xet
 Community
reaperdoesntknow commited on
Commit
a0f77ce
·
verified ·
1 Parent(s): c829626

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +36 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +52 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +318 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<thought>": 50290,
3
+ "<|action|>": 50262,
4
+ "<|agent:0|>": 50270,
5
+ "<|agent:10|>": 50280,
6
+ "<|agent:11|>": 50281,
7
+ "<|agent:12|>": 50282,
8
+ "<|agent:13|>": 50283,
9
+ "<|agent:14|>": 50284,
10
+ "<|agent:15|>": 50285,
11
+ "<|agent:16|>": 50286,
12
+ "<|agent:17|>": 50287,
13
+ "<|agent:18|>": 50288,
14
+ "<|agent:19|>": 50289,
15
+ "<|agent:1|>": 50271,
16
+ "<|agent:2|>": 50272,
17
+ "<|agent:3|>": 50273,
18
+ "<|agent:4|>": 50274,
19
+ "<|agent:5|>": 50275,
20
+ "<|agent:6|>": 50276,
21
+ "<|agent:7|>": 50277,
22
+ "<|agent:8|>": 50278,
23
+ "<|agent:9|>": 50279,
24
+ "<|assistant|>": 50268,
25
+ "<|bos|>": 50258,
26
+ "<|eos|>": 50259,
27
+ "<|meta|>": 50265,
28
+ "<|observe|>": 50263,
29
+ "<|pad|>": 50257,
30
+ "<|route|>": 50264,
31
+ "<|system|>": 50266,
32
+ "<|thought|>": 50261,
33
+ "<|tool|>": 50269,
34
+ "<|unk|>": 50260,
35
+ "<|user|>": 50267
36
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|agent:0|>",
4
+ "<|agent:1|>",
5
+ "<|agent:2|>",
6
+ "<|agent:3|>",
7
+ "<|agent:4|>",
8
+ "<|agent:5|>",
9
+ "<|agent:6|>",
10
+ "<|agent:7|>",
11
+ "<|agent:8|>",
12
+ "<|agent:9|>",
13
+ "<|agent:10|>",
14
+ "<|agent:11|>",
15
+ "<|agent:12|>",
16
+ "<|agent:13|>",
17
+ "<|agent:14|>",
18
+ "<|agent:15|>",
19
+ "<|agent:16|>",
20
+ "<|agent:17|>",
21
+ "<|agent:18|>",
22
+ "<|agent:19|>"
23
+ ],
24
+ "bos_token": {
25
+ "content": "<thought>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "eos_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "pad_token": {
39
+ "content": "<|pad|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "unk_token": {
46
+ "content": "<|endoftext|>",
47
+ "lstrip": false,
48
+ "normalized": true,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ }
52
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,318 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "50257": {
13
+ "content": "<|pad|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<|bos|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|eos|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<|unk|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "<|thought|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50262": {
53
+ "content": "<|action|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50263": {
61
+ "content": "<|observe|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50264": {
69
+ "content": "<|route|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50265": {
77
+ "content": "<|meta|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "50266": {
85
+ "content": "<|system|>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "50267": {
93
+ "content": "<|user|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "50268": {
101
+ "content": "<|assistant|>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "50269": {
109
+ "content": "<|tool|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "50270": {
117
+ "content": "<|agent:0|>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "50271": {
125
+ "content": "<|agent:1|>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "50272": {
133
+ "content": "<|agent:2|>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "50273": {
141
+ "content": "<|agent:3|>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "50274": {
149
+ "content": "<|agent:4|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "50275": {
157
+ "content": "<|agent:5|>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "50276": {
165
+ "content": "<|agent:6|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "50277": {
173
+ "content": "<|agent:7|>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "50278": {
181
+ "content": "<|agent:8|>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "50279": {
189
+ "content": "<|agent:9|>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "50280": {
197
+ "content": "<|agent:10|>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "50281": {
205
+ "content": "<|agent:11|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50282": {
213
+ "content": "<|agent:12|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "50283": {
221
+ "content": "<|agent:13|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "50284": {
229
+ "content": "<|agent:14|>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "50285": {
237
+ "content": "<|agent:15|>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "50286": {
245
+ "content": "<|agent:16|>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "50287": {
253
+ "content": "<|agent:17|>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "50288": {
261
+ "content": "<|agent:18|>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "50289": {
269
+ "content": "<|agent:19|>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "50290": {
277
+ "content": "<thought>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ }
284
+ },
285
+ "additional_special_tokens": [
286
+ "<|agent:0|>",
287
+ "<|agent:1|>",
288
+ "<|agent:2|>",
289
+ "<|agent:3|>",
290
+ "<|agent:4|>",
291
+ "<|agent:5|>",
292
+ "<|agent:6|>",
293
+ "<|agent:7|>",
294
+ "<|agent:8|>",
295
+ "<|agent:9|>",
296
+ "<|agent:10|>",
297
+ "<|agent:11|>",
298
+ "<|agent:12|>",
299
+ "<|agent:13|>",
300
+ "<|agent:14|>",
301
+ "<|agent:15|>",
302
+ "<|agent:16|>",
303
+ "<|agent:17|>",
304
+ "<|agent:18|>",
305
+ "<|agent:19|>"
306
+ ],
307
+ "bos_token": "<thought>",
308
+ "bos_token_id": 50290,
309
+ "clean_up_tokenization_spaces": false,
310
+ "eos_token": "<|endoftext|>",
311
+ "extra_special_tokens": {},
312
+ "model_max_length": 1024,
313
+ "pad_token": "<|pad|>",
314
+ "pad_token_id": 50257,
315
+ "padding_side": "right",
316
+ "tokenizer_class": "GPT2Tokenizer",
317
+ "unk_token": "<|endoftext|>"
318
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff