Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +6 -13
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
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>",
|
|
@@ -116,14 +114,9 @@
|
|
| 116 |
}
|
| 117 |
},
|
| 118 |
"bos_token": "<s>",
|
| 119 |
-
"clean_up_tokenization_spaces":
|
| 120 |
-
"eos_token": "<
|
| 121 |
-
"
|
| 122 |
-
"
|
| 123 |
-
"
|
| 124 |
-
|
| 125 |
-
"sp_model_kwargs": {},
|
| 126 |
-
"tokenizer_class": "LlamaTokenizer",
|
| 127 |
-
"unk_token": "<unk>",
|
| 128 |
-
"use_default_system_prompt": false
|
| 129 |
-
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<unk>",
|
|
|
|
| 114 |
}
|
| 115 |
},
|
| 116 |
"bos_token": "<s>",
|
| 117 |
+
"clean_up_tokenization_spaces": true,
|
| 118 |
+
"eos_token": "</s>",
|
| 119 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 120 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 121 |
+
"unk_token": "<unk>"
|
| 122 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|