Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +0 -4
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -95,15 +95,11 @@
|
|
| 95 |
"eos_token": "</s>",
|
| 96 |
"legacy": false,
|
| 97 |
"mask_token": "[MASK]",
|
| 98 |
-
"max_length": 512,
|
| 99 |
"model_max_length": 4096,
|
| 100 |
"pad_token": "<pad>",
|
| 101 |
"padding_side": "right",
|
| 102 |
"sp_model_kwargs": {},
|
| 103 |
-
"stride": 0,
|
| 104 |
"tokenizer_class": "LlamaTokenizer",
|
| 105 |
-
"truncation_side": "right",
|
| 106 |
-
"truncation_strategy": "longest_first",
|
| 107 |
"unk_token": "<unk>",
|
| 108 |
"use_default_system_prompt": false
|
| 109 |
}
|
|
|
|
| 95 |
"eos_token": "</s>",
|
| 96 |
"legacy": false,
|
| 97 |
"mask_token": "[MASK]",
|
|
|
|
| 98 |
"model_max_length": 4096,
|
| 99 |
"pad_token": "<pad>",
|
| 100 |
"padding_side": "right",
|
| 101 |
"sp_model_kwargs": {},
|
|
|
|
| 102 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 103 |
"unk_token": "<unk>",
|
| 104 |
"use_default_system_prompt": false
|
| 105 |
}
|