Update tokenizer_config.json
Browse files- tokenizer_config.json +3 -7
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
| 4 |
-
"add_prefix_space": false,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|
| 7 |
"content": "<unk>",
|
|
@@ -31,13 +30,10 @@
|
|
| 31 |
"additional_special_tokens": [],
|
| 32 |
"bos_token": "<s>",
|
| 33 |
"clean_up_tokenization_spaces": false,
|
| 34 |
-
"cls_token": "</s>",
|
| 35 |
"eos_token": "</s>",
|
| 36 |
-
"legacy":
|
| 37 |
-
"model_max_length":
|
| 38 |
-
"pad_token":
|
| 39 |
-
"padding_side": "left",
|
| 40 |
-
"sep_token": "</s>",
|
| 41 |
"sp_model_kwargs": {},
|
| 42 |
"spaces_between_special_tokens": false,
|
| 43 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
"add_bos_token": false,
|
| 3 |
"add_eos_token": false,
|
|
|
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
|
|
| 30 |
"additional_special_tokens": [],
|
| 31 |
"bos_token": "<s>",
|
| 32 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 33 |
"eos_token": "</s>",
|
| 34 |
+
"legacy": true,
|
| 35 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 36 |
+
"pad_token": null,
|
|
|
|
|
|
|
| 37 |
"sp_model_kwargs": {},
|
| 38 |
"spaces_between_special_tokens": false,
|
| 39 |
"tokenizer_class": "LlamaTokenizer",
|