Upload tokenizer
Browse files- special_tokens_map.json +0 -7
- tokenizer_config.json +1 -5
special_tokens_map.json
CHANGED
|
@@ -12,12 +12,5 @@
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "<|finetune_right_pad_id|>",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
}
|
| 23 |
}
|
|
|
|
| 12 |
"normalized": false,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
}
|
| 16 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_bos_token": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"128000": {
|
| 5 |
"content": "<|begin_of_text|>",
|
|
@@ -2059,8 +2058,5 @@
|
|
| 2059 |
"attention_mask"
|
| 2060 |
],
|
| 2061 |
"model_max_length": 131072,
|
| 2062 |
-
"
|
| 2063 |
-
"padding_side": "right",
|
| 2064 |
-
"tokenizer_class": "PreTrainedTokenizer",
|
| 2065 |
-
"unk_token": null
|
| 2066 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"128000": {
|
| 4 |
"content": "<|begin_of_text|>",
|
|
|
|
| 2058 |
"attention_mask"
|
| 2059 |
],
|
| 2060 |
"model_max_length": 131072,
|
| 2061 |
+
"tokenizer_class": "PreTrainedTokenizer"
|
|
|
|
|
|
|
|
|
|
| 2062 |
}
|