Upload tokenizer
Browse files- tokenizer.json +1 -6
- tokenizer_config.json +4 -0
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 700,
|
| 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
|
@@ -121,11 +121,15 @@
|
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"legacy": false,
|
|
|
|
| 124 |
"model_max_length": 131072,
|
| 125 |
"pad_token": "<|endoftext|>",
|
| 126 |
"padding_side": "right",
|
| 127 |
"sp_model_kwargs": {},
|
|
|
|
| 128 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 129 |
"unk_token": "<unk>",
|
| 130 |
"use_default_system_prompt": false
|
| 131 |
}
|
|
|
|
| 121 |
"clean_up_tokenization_spaces": false,
|
| 122 |
"eos_token": "<|endoftext|>",
|
| 123 |
"legacy": false,
|
| 124 |
+
"max_length": 700,
|
| 125 |
"model_max_length": 131072,
|
| 126 |
"pad_token": "<|endoftext|>",
|
| 127 |
"padding_side": "right",
|
| 128 |
"sp_model_kwargs": {},
|
| 129 |
+
"stride": 0,
|
| 130 |
"tokenizer_class": "LlamaTokenizer",
|
| 131 |
+
"truncation_side": "right",
|
| 132 |
+
"truncation_strategy": "longest_first",
|
| 133 |
"unk_token": "<unk>",
|
| 134 |
"use_default_system_prompt": false
|
| 135 |
}
|