Upload tokenizer
Browse files- special_tokens_map.json +1 -7
- tokenizer.model +3 -0
- tokenizer_config.json +2 -1
special_tokens_map.json
CHANGED
|
@@ -17,13 +17,7 @@
|
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
-
"pad_token":
|
| 21 |
-
"content": "<pad>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false
|
| 26 |
-
},
|
| 27 |
"unk_token": {
|
| 28 |
"content": "<unk>",
|
| 29 |
"lstrip": false,
|
|
|
|
| 17 |
"rstrip": false,
|
| 18 |
"single_word": false
|
| 19 |
},
|
| 20 |
+
"pad_token": "<pad>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 21 |
"unk_token": {
|
| 22 |
"content": "<unk>",
|
| 23 |
"lstrip": false,
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
|
| 3 |
+
size 4241003
|
tokenizer_config.json
CHANGED
|
@@ -2004,8 +2004,9 @@
|
|
| 2004 |
"clean_up_tokenization_spaces": false,
|
| 2005 |
"eos_token": "<eos>",
|
| 2006 |
"extra_special_tokens": {},
|
| 2007 |
-
"model_max_length":
|
| 2008 |
"pad_token": "<pad>",
|
|
|
|
| 2009 |
"sp_model_kwargs": {},
|
| 2010 |
"spaces_between_special_tokens": false,
|
| 2011 |
"tokenizer_class": "GemmaTokenizer",
|
|
|
|
| 2004 |
"clean_up_tokenization_spaces": false,
|
| 2005 |
"eos_token": "<eos>",
|
| 2006 |
"extra_special_tokens": {},
|
| 2007 |
+
"model_max_length": 8192,
|
| 2008 |
"pad_token": "<pad>",
|
| 2009 |
+
"padding_side": "left",
|
| 2010 |
"sp_model_kwargs": {},
|
| 2011 |
"spaces_between_special_tokens": false,
|
| 2012 |
"tokenizer_class": "GemmaTokenizer",
|