danielhanchen
commited on
Commit
•
4caf5ac
1
Parent(s):
9d81b01
Upload tokenizer
Browse files- special_tokens_map.json +2 -2
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -14,10 +14,10 @@
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
-
"content": "<|
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
-
"rstrip":
|
21 |
"single_word": false
|
22 |
},
|
23 |
"unk_token": {
|
|
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": {
|
17 |
+
"content": "<|placeholder6|>",
|
18 |
"lstrip": false,
|
19 |
"normalized": false,
|
20 |
+
"rstrip": true,
|
21 |
"single_word": false
|
22 |
},
|
23 |
"unk_token": {
|
tokenizer_config.json
CHANGED
@@ -121,7 +121,7 @@
|
|
121 |
"eos_token": "<|endoftext|>",
|
122 |
"legacy": false,
|
123 |
"model_max_length": 4096,
|
124 |
-
"pad_token": "<|
|
125 |
"padding_side": "left",
|
126 |
"sp_model_kwargs": {},
|
127 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
121 |
"eos_token": "<|endoftext|>",
|
122 |
"legacy": false,
|
123 |
"model_max_length": 4096,
|
124 |
+
"pad_token": "<|placeholder6|>",
|
125 |
"padding_side": "left",
|
126 |
"sp_model_kwargs": {},
|
127 |
"tokenizer_class": "LlamaTokenizer",
|