Upload tokenizer
Browse files- special_tokens_map.json +1 -1
- tokenizer_config.json +3 -3
special_tokens_map.json
CHANGED
@@ -13,7 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<s>",
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
-
"add_eos_token":
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -40,8 +40,8 @@
|
|
40 |
"eos_token": "</s>",
|
41 |
"legacy": false,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
-
"pad_token": "
|
44 |
-
"padding_side": "
|
45 |
"sp_model_kwargs": {},
|
46 |
"spaces_between_special_tokens": false,
|
47 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
1 |
{
|
2 |
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
40 |
"eos_token": "</s>",
|
41 |
"legacy": false,
|
42 |
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<s>",
|
44 |
+
"padding_side": "right",
|
45 |
"sp_model_kwargs": {},
|
46 |
"spaces_between_special_tokens": false,
|
47 |
"tokenizer_class": "LlamaTokenizer",
|