Upload tokenizer
Browse files- tokenizer_config.json +1 -4
tokenizer_config.json
CHANGED
|
@@ -1,6 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": false,
|
| 3 |
-
"add_eos_token": false,
|
| 4 |
"added_tokens_decoder": {
|
| 5 |
"0": {
|
| 6 |
"content": "<unk>",
|
|
@@ -35,13 +33,12 @@
|
|
| 35 |
"bos_token": "<s>",
|
| 36 |
"clean_up_tokenization_spaces": false,
|
| 37 |
"eos_token": "</s>",
|
| 38 |
-
"legacy":
|
| 39 |
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
"pad_token": "<unk>",
|
| 41 |
"sp_model_kwargs": {},
|
| 42 |
"spaces_between_special_tokens": false,
|
| 43 |
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
-
"tokenizer_file": "/home/ubuntu/disk/cache/hub/models--ocisd4--mistral_tokenizer_ext_dataprep/snapshots/5db4d4b8804943e2962e19882281f1254c454890/tokenizer.json",
|
| 45 |
"unk_token": "<unk>",
|
| 46 |
"use_default_system_prompt": false
|
| 47 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
|
|
| 33 |
"bos_token": "<s>",
|
| 34 |
"clean_up_tokenization_spaces": false,
|
| 35 |
"eos_token": "</s>",
|
| 36 |
+
"legacy": true,
|
| 37 |
"model_max_length": 1000000000000000019884624838656,
|
| 38 |
"pad_token": "<unk>",
|
| 39 |
"sp_model_kwargs": {},
|
| 40 |
"spaces_between_special_tokens": false,
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": false
|
| 44 |
}
|