AlphaRandy
commited on
Update tokenizer_config.json
Browse files- tokenizer_config.json +10 -16
tokenizer_config.json
CHANGED
@@ -1,19 +1,13 @@
|
|
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 |
-
},
|
13 |
-
"bos_token": "<|endoftext|>",
|
14 |
-
"clean_up_tokenization_spaces": true,
|
15 |
-
"eos_token": "<|endoftext|>",
|
16 |
-
"model_max_length": 1024,
|
17 |
"tokenizer_class": "GPT2Tokenizer",
|
18 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"tokenizer_class": "GPT2Tokenizer",
|
3 |
+
"bos_token": "<|startoftext|>",
|
4 |
+
"eos_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|unk|>",
|
6 |
+
"pad_token": "<|pad|>",
|
7 |
+
"additional_special_tokens": ["<|user|>", "<|bot|>", "<|system|>"],
|
8 |
+
"chat_template": {
|
9 |
+
"user": "<|user|>",
|
10 |
+
"bot": "<|bot|>",
|
11 |
+
"system": "<|system|>"
|
12 |
+
}
|
13 |
}
|