kunalkumarkhandodiya
commited on
Upload tokenizer
Browse files- special_tokens_map.json +21 -3
- tokenizer.json +2 -2
- tokenizer_config.json +3 -3
special_tokens_map.json
CHANGED
@@ -1,6 +1,24 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<eos>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"pad_token": "<|endoftext|>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
}
|
tokenizer.json
CHANGED
@@ -246,8 +246,8 @@
|
|
246 |
"id": 50277,
|
247 |
"content": "<eos>",
|
248 |
"single_word": false,
|
249 |
-
"lstrip":
|
250 |
-
"rstrip":
|
251 |
"normalized": false,
|
252 |
"special": true
|
253 |
}
|
|
|
246 |
"id": 50277,
|
247 |
"content": "<eos>",
|
248 |
"single_word": false,
|
249 |
+
"lstrip": false,
|
250 |
+
"rstrip": false,
|
251 |
"normalized": false,
|
252 |
"special": true
|
253 |
}
|
tokenizer_config.json
CHANGED
@@ -204,18 +204,18 @@
|
|
204 |
},
|
205 |
"50277": {
|
206 |
"content": "<eos>",
|
207 |
-
"lstrip":
|
208 |
"normalized": false,
|
209 |
-
"rstrip":
|
210 |
"single_word": false,
|
211 |
"special": true
|
212 |
}
|
213 |
},
|
214 |
-
"additional_special_tokens": [],
|
215 |
"bos_token": "<|endoftext|>",
|
216 |
"clean_up_tokenization_spaces": true,
|
217 |
"eos_token": "<eos>",
|
218 |
"model_max_length": 2048,
|
|
|
219 |
"tokenizer_class": "GPTNeoXTokenizer",
|
220 |
"unk_token": "<|endoftext|>"
|
221 |
}
|
|
|
204 |
},
|
205 |
"50277": {
|
206 |
"content": "<eos>",
|
207 |
+
"lstrip": false,
|
208 |
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
"single_word": false,
|
211 |
"special": true
|
212 |
}
|
213 |
},
|
|
|
214 |
"bos_token": "<|endoftext|>",
|
215 |
"clean_up_tokenization_spaces": true,
|
216 |
"eos_token": "<eos>",
|
217 |
"model_max_length": 2048,
|
218 |
+
"pad_token": "<|endoftext|>",
|
219 |
"tokenizer_class": "GPTNeoXTokenizer",
|
220 |
"unk_token": "<|endoftext|>"
|
221 |
}
|