Upload tokenizer
Browse files- rwkv_vocab_v20230424.txt +0 -0
- special_tokens_map.json +1 -7
- tokenizer_config.json +2 -3
rwkv_vocab_v20230424.txt
ADDED
|
Binary file (437 kB). View file
|
|
|
special_tokens_map.json
CHANGED
|
@@ -1,11 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token":
|
| 3 |
-
"content": "<s>",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
"eos_token": "<s>",
|
| 10 |
"unk_token": "<s>"
|
| 11 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "<s>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
"eos_token": "<s>",
|
| 4 |
"unk_token": "<s>"
|
| 5 |
}
|
tokenizer_config.json
CHANGED
|
@@ -3,13 +3,12 @@
|
|
| 3 |
"0": {
|
| 4 |
"content": "<s>",
|
| 5 |
"lstrip": false,
|
| 6 |
-
"normalized":
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
-
"special":
|
| 10 |
}
|
| 11 |
},
|
| 12 |
-
"additional_special_tokens": [],
|
| 13 |
"bos_token": "<s>",
|
| 14 |
"clean_up_tokenization_spaces": true,
|
| 15 |
"eos_token": "<s>",
|
|
|
|
| 3 |
"0": {
|
| 4 |
"content": "<s>",
|
| 5 |
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
"rstrip": false,
|
| 8 |
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
}
|
| 11 |
},
|
|
|
|
| 12 |
"bos_token": "<s>",
|
| 13 |
"clean_up_tokenization_spaces": true,
|
| 14 |
"eos_token": "<s>",
|