zhangir-azerbayev
commited on
Commit
β’
87c9edc
1
Parent(s):
5a4995c
fix tokenizer
Browse files- tokenizer.json +2 -29
- tokenizer.model +2 -2
- tokenizer_config.json +5 -4
tokenizer.json
CHANGED
@@ -32134,23 +32134,7 @@
|
|
32134 |
"μ": 31996,
|
32135 |
"ζΆ": 31997,
|
32136 |
"εΌ": 31998,
|
32137 |
-
"η»": 31999
|
32138 |
-
"β<SU": 32000,
|
32139 |
-
"β<SUF": 32001,
|
32140 |
-
"β<PRE": 32002,
|
32141 |
-
"β<M": 32003,
|
32142 |
-
"β<MID": 32004,
|
32143 |
-
"β<E": 32005,
|
32144 |
-
"β<EOT": 32006,
|
32145 |
-
"β<PRE>": 32007,
|
32146 |
-
"β<SUF>": 32008,
|
32147 |
-
"β<MID>": 32009,
|
32148 |
-
"β<EOT>": 32010,
|
32149 |
-
"β<EOT><EOT>": 32011,
|
32150 |
-
"β<EOT><EOT><EOT>": 32012,
|
32151 |
-
"β<EOT><EOT><EOT><EOT>": 32013,
|
32152 |
-
"β<EOT><EOT><EOT><EOT><EOT>": 32014,
|
32153 |
-
"β<EOT><EOT><EOT><EOT><EOT><EOT>": 32015
|
32154 |
},
|
32155 |
"merges": [
|
32156 |
"β t",
|
@@ -93401,18 +93385,7 @@
|
|
93401 |
"βββββββββ ββββββ",
|
93402 |
"βββββββ ββββββββ",
|
93403 |
"βββββββββββ ββββ",
|
93404 |
-
"β ββββββββββββββ"
|
93405 |
-
"β< SU",
|
93406 |
-
"β<SU F",
|
93407 |
-
"β< PRE",
|
93408 |
-
"β< M",
|
93409 |
-
"β<M ID",
|
93410 |
-
"β< E",
|
93411 |
-
"β<E OT",
|
93412 |
-
"β<PRE >",
|
93413 |
-
"β<SUF >",
|
93414 |
-
"β<MID >",
|
93415 |
-
"β<EOT >"
|
93416 |
]
|
93417 |
}
|
93418 |
}
|
|
|
32134 |
"μ": 31996,
|
32135 |
"ζΆ": 31997,
|
32136 |
"εΌ": 31998,
|
32137 |
+
"η»": 31999
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32138 |
},
|
32139 |
"merges": [
|
32140 |
"β t",
|
|
|
93385 |
"βββββββββ ββββββ",
|
93386 |
"βββββββ ββββββββ",
|
93387 |
"βββββββββββ ββββ",
|
93388 |
+
"β ββββββββββββββ"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93389 |
]
|
93390 |
}
|
93391 |
}
|
tokenizer.model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
CHANGED
@@ -5,7 +5,7 @@
|
|
5 |
"__type": "AddedToken",
|
6 |
"content": "<s>",
|
7 |
"lstrip": false,
|
8 |
-
"normalized":
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
@@ -14,20 +14,21 @@
|
|
14 |
"__type": "AddedToken",
|
15 |
"content": "</s>",
|
16 |
"lstrip": false,
|
17 |
-
"normalized":
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
-
"legacy":
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
|
|
24 |
"sp_model_kwargs": {},
|
25 |
"tokenizer_class": "LlamaTokenizer",
|
26 |
"unk_token": {
|
27 |
"__type": "AddedToken",
|
28 |
"content": "<unk>",
|
29 |
"lstrip": false,
|
30 |
-
"normalized":
|
31 |
"rstrip": false,
|
32 |
"single_word": false
|
33 |
}
|
|
|
5 |
"__type": "AddedToken",
|
6 |
"content": "<s>",
|
7 |
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
"rstrip": false,
|
10 |
"single_word": false
|
11 |
},
|
|
|
14 |
"__type": "AddedToken",
|
15 |
"content": "</s>",
|
16 |
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
"rstrip": false,
|
19 |
"single_word": false
|
20 |
},
|
21 |
+
"legacy": false,
|
22 |
"model_max_length": 1000000000000000019884624838656,
|
23 |
"pad_token": null,
|
24 |
+
"padding_side": "right",
|
25 |
"sp_model_kwargs": {},
|
26 |
"tokenizer_class": "LlamaTokenizer",
|
27 |
"unk_token": {
|
28 |
"__type": "AddedToken",
|
29 |
"content": "<unk>",
|
30 |
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
"rstrip": false,
|
33 |
"single_word": false
|
34 |
}
|