Upload tokenizer
#9
by arumyancev - opened
- tokenizer.json +6 -1
- tokenizer_config.json +4 -0
tokenizer.json
CHANGED
|
@@ -1,6 +1,11 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
tokenizer_config.json
CHANGED
|
@@ -35,11 +35,15 @@
|
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "</s>",
|
| 37 |
"legacy": true,
|
|
|
|
| 38 |
"model_max_length": 1000000000000000019884624838656,
|
| 39 |
"pad_token": "</s>",
|
| 40 |
"sp_model_kwargs": {},
|
| 41 |
"spaces_between_special_tokens": false,
|
|
|
|
| 42 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 43 |
"unk_token": "<unk>",
|
| 44 |
"use_default_system_prompt": true
|
| 45 |
}
|
|
|
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
"eos_token": "</s>",
|
| 37 |
"legacy": true,
|
| 38 |
+
"max_length": 1024,
|
| 39 |
"model_max_length": 1000000000000000019884624838656,
|
| 40 |
"pad_token": "</s>",
|
| 41 |
"sp_model_kwargs": {},
|
| 42 |
"spaces_between_special_tokens": false,
|
| 43 |
+
"stride": 0,
|
| 44 |
"tokenizer_class": "LlamaTokenizer",
|
| 45 |
+
"truncation_side": "right",
|
| 46 |
+
"truncation_strategy": "longest_first",
|
| 47 |
"unk_token": "<unk>",
|
| 48 |
"use_default_system_prompt": true
|
| 49 |
}
|