danielhanchen
commited on
Commit
•
cfe38f8
1
Parent(s):
1c0c6f4
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +2 -0
special_tokens_map.json
CHANGED
@@ -12,5 +12,12 @@
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
15 |
}
|
16 |
}
|
|
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|finetune_right_pad_id|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
}
|
23 |
}
|
tokenizer_config.json
CHANGED
@@ -2058,5 +2058,7 @@
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 131072,
|
|
|
|
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
}
|
|
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 131072,
|
2061 |
+
"pad_token": "<|finetune_right_pad_id|>",
|
2062 |
+
"padding_side": "left",
|
2063 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2064 |
}
|