Upload tokenizer
Browse files- special_tokens_map.json +2 -14
- tokenizer_config.json +4 -0
special_tokens_map.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
"lstrip": false,
|
| 6 |
-
"normalized": true,
|
| 7 |
-
"rstrip": false,
|
| 8 |
-
"single_word": false
|
| 9 |
-
},
|
| 10 |
-
{
|
| 11 |
-
"content": "</instruction>",
|
| 12 |
-
"lstrip": false,
|
| 13 |
-
"normalized": true,
|
| 14 |
-
"rstrip": false,
|
| 15 |
-
"single_word": false
|
| 16 |
-
}
|
| 17 |
],
|
| 18 |
"bos_token": {
|
| 19 |
"content": "<s>",
|
|
|
|
| 1 |
{
|
| 2 |
"additional_special_tokens": [
|
| 3 |
+
"<instruction>",
|
| 4 |
+
"</instruction>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
],
|
| 6 |
"bos_token": {
|
| 7 |
"content": "<s>",
|
tokenizer_config.json
CHANGED
|
@@ -62,12 +62,16 @@
|
|
| 62 |
"eos_token": "</s>",
|
| 63 |
"eos_token_id": 2,
|
| 64 |
"legacy": false,
|
|
|
|
| 65 |
"model_max_length": 1000000000000000019884624838656,
|
| 66 |
"pad_token": "<pad>",
|
| 67 |
"pad_token_id": 3,
|
| 68 |
"padding_side": "right",
|
| 69 |
"sp_model_kwargs": {},
|
|
|
|
| 70 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
|
|
| 71 |
"unk_token": "<unk>",
|
| 72 |
"unk_token_id": 0,
|
| 73 |
"use_default_system_prompt": false
|
|
|
|
| 62 |
"eos_token": "</s>",
|
| 63 |
"eos_token_id": 2,
|
| 64 |
"legacy": false,
|
| 65 |
+
"max_length": 2048,
|
| 66 |
"model_max_length": 1000000000000000019884624838656,
|
| 67 |
"pad_token": "<pad>",
|
| 68 |
"pad_token_id": 3,
|
| 69 |
"padding_side": "right",
|
| 70 |
"sp_model_kwargs": {},
|
| 71 |
+
"stride": 0,
|
| 72 |
"tokenizer_class": "LlamaTokenizer",
|
| 73 |
+
"truncation_side": "right",
|
| 74 |
+
"truncation_strategy": "longest_first",
|
| 75 |
"unk_token": "<unk>",
|
| 76 |
"unk_token_id": 0,
|
| 77 |
"use_default_system_prompt": false
|