add tokenizer
Browse files- special_tokens_map.json +9 -0
- tokenizer_config.json +13 -0
- vocab.json +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"unk_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
}
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"name_or_path": "ArthurZ/jukebox",
|
| 3 |
+
"special_tokens_map_file": "/home/arthur_huggingface_co/.cache/huggingface/transformers/efdb49f61ffbc19e9c36eeea7e62421b1d0110b1a853e8d4c05fe0d3f401c3a8.9b2de6ea77fa4bf0507fd7dcc84a702f98f98bad7c1a625004655d5a84b17ca9",
|
| 4 |
+
"tokenizer_class": "JukeboxTokenizer",
|
| 5 |
+
"unk_token": {
|
| 6 |
+
"__type": "AddedToken",
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false
|
| 12 |
+
}
|
| 13 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|