chargoddard
commited on
Commit
•
eddfbc0
1
Parent(s):
1ec4b14
Correct json
Browse files- special_tokens_map.json +23 -0
- tokenizer_config.json +0 -1
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"unk_token": {
|
17 |
+
"content": "<unk>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer_config.json
CHANGED
@@ -20,7 +20,6 @@
|
|
20 |
},
|
21 |
"model_max_length": 2048,
|
22 |
"pad_token": null,
|
23 |
-
"padding_side": "right",
|
24 |
"sp_model_kwargs": {},
|
25 |
"tokenizer_class": "LlamaTokenizer",
|
26 |
"unk_token": {
|
|
|
20 |
},
|
21 |
"model_max_length": 2048,
|
22 |
"pad_token": null,
|
|
|
23 |
"sp_model_kwargs": {},
|
24 |
"tokenizer_class": "LlamaTokenizer",
|
25 |
"unk_token": {
|