Upload tokenizer
Browse files- tokenizer.json +2 -16
- tokenizer_config.json +0 -6
tokenizer.json
CHANGED
|
@@ -1,21 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 512
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 2,
|
| 16 |
-
"pad_type_id": 0,
|
| 17 |
-
"pad_token": "</s>"
|
| 18 |
-
},
|
| 19 |
"added_tokens": [
|
| 20 |
{
|
| 21 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -34,17 +34,11 @@
|
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"extra_special_tokens": {},
|
| 36 |
"legacy": false,
|
| 37 |
-
"max_length": 512,
|
| 38 |
"model_max_length": 2048,
|
| 39 |
-
"pad_to_multiple_of": null,
|
| 40 |
"pad_token": "</s>",
|
| 41 |
-
"pad_token_type_id": 0,
|
| 42 |
"padding_side": "right",
|
| 43 |
"sp_model_kwargs": {},
|
| 44 |
-
"stride": 0,
|
| 45 |
"tokenizer_class": "LlamaTokenizer",
|
| 46 |
-
"truncation_side": "right",
|
| 47 |
-
"truncation_strategy": "longest_first",
|
| 48 |
"unk_token": "<unk>",
|
| 49 |
"use_default_system_prompt": false
|
| 50 |
}
|
|
|
|
| 34 |
"eos_token": "</s>",
|
| 35 |
"extra_special_tokens": {},
|
| 36 |
"legacy": false,
|
|
|
|
| 37 |
"model_max_length": 2048,
|
|
|
|
| 38 |
"pad_token": "</s>",
|
|
|
|
| 39 |
"padding_side": "right",
|
| 40 |
"sp_model_kwargs": {},
|
|
|
|
| 41 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 42 |
"unk_token": "<unk>",
|
| 43 |
"use_default_system_prompt": false
|
| 44 |
}
|