Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer.json +2153 -0
- tokenizer_config.json +10 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "([bos])",
|
| 3 |
+
"eos_token": "([eos])",
|
| 4 |
+
"mask_token": "([mask])",
|
| 5 |
+
"pad_token": "([pad])",
|
| 6 |
+
"unk_token": "([unk])"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,2153 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "([bos])",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "([eos])",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "([unk])",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "([pad])",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "([mask])",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
}
|
| 51 |
+
],
|
| 52 |
+
"normalizer": {
|
| 53 |
+
"type": "Sequence",
|
| 54 |
+
"normalizers": [
|
| 55 |
+
{
|
| 56 |
+
"type": "Replace",
|
| 57 |
+
"pattern": {
|
| 58 |
+
"String": "``"
|
| 59 |
+
},
|
| 60 |
+
"content": "\""
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"type": "Replace",
|
| 64 |
+
"pattern": {
|
| 65 |
+
"String": "''"
|
| 66 |
+
},
|
| 67 |
+
"content": "\""
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"type": "Lowercase"
|
| 71 |
+
}
|
| 72 |
+
]
|
| 73 |
+
},
|
| 74 |
+
"pre_tokenizer": {
|
| 75 |
+
"type": "Metaspace",
|
| 76 |
+
"replacement": "▁",
|
| 77 |
+
"add_prefix_space": true
|
| 78 |
+
},
|
| 79 |
+
"post_processor": {
|
| 80 |
+
"type": "TemplateProcessing",
|
| 81 |
+
"single": [
|
| 82 |
+
{
|
| 83 |
+
"Sequence": {
|
| 84 |
+
"id": "A",
|
| 85 |
+
"type_id": 0
|
| 86 |
+
}
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"SpecialToken": {
|
| 90 |
+
"id": "([eos])",
|
| 91 |
+
"type_id": 0
|
| 92 |
+
}
|
| 93 |
+
}
|
| 94 |
+
],
|
| 95 |
+
"pair": [
|
| 96 |
+
{
|
| 97 |
+
"Sequence": {
|
| 98 |
+
"id": "A",
|
| 99 |
+
"type_id": 0
|
| 100 |
+
}
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"SpecialToken": {
|
| 104 |
+
"id": "([eos])",
|
| 105 |
+
"type_id": 0
|
| 106 |
+
}
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"Sequence": {
|
| 110 |
+
"id": "B",
|
| 111 |
+
"type_id": 1
|
| 112 |
+
}
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"SpecialToken": {
|
| 116 |
+
"id": "([eos])",
|
| 117 |
+
"type_id": 1
|
| 118 |
+
}
|
| 119 |
+
}
|
| 120 |
+
],
|
| 121 |
+
"special_tokens": {
|
| 122 |
+
"([bos])": {
|
| 123 |
+
"id": "([bos])",
|
| 124 |
+
"ids": [
|
| 125 |
+
0
|
| 126 |
+
],
|
| 127 |
+
"tokens": [
|
| 128 |
+
"([bos])"
|
| 129 |
+
]
|
| 130 |
+
},
|
| 131 |
+
"([eos])": {
|
| 132 |
+
"id": "([eos])",
|
| 133 |
+
"ids": [
|
| 134 |
+
1
|
| 135 |
+
],
|
| 136 |
+
"tokens": [
|
| 137 |
+
"([eos])"
|
| 138 |
+
]
|
| 139 |
+
}
|
| 140 |
+
}
|
| 141 |
+
},
|
| 142 |
+
"decoder": {
|
| 143 |
+
"type": "Metaspace",
|
| 144 |
+
"replacement": "▁",
|
| 145 |
+
"add_prefix_space": true
|
| 146 |
+
},
|
| 147 |
+
"model": {
|
| 148 |
+
"type": "Unigram",
|
| 149 |
+
"unk_id": 2,
|
| 150 |
+
"vocab": [
|
| 151 |
+
[
|
| 152 |
+
"([bos])",
|
| 153 |
+
0.0
|
| 154 |
+
],
|
| 155 |
+
[
|
| 156 |
+
"([eos])",
|
| 157 |
+
0.0
|
| 158 |
+
],
|
| 159 |
+
[
|
| 160 |
+
"([unk])",
|
| 161 |
+
0.0
|
| 162 |
+
],
|
| 163 |
+
[
|
| 164 |
+
"([pad])",
|
| 165 |
+
0.0
|
| 166 |
+
],
|
| 167 |
+
[
|
| 168 |
+
"([mask])",
|
| 169 |
+
0.0
|
| 170 |
+
],
|
| 171 |
+
[
|
| 172 |
+
"▁",
|
| 173 |
+
-2.6754905386285905
|
| 174 |
+
],
|
| 175 |
+
[
|
| 176 |
+
"s",
|
| 177 |
+
-2.8768613408851564
|
| 178 |
+
],
|
| 179 |
+
[
|
| 180 |
+
"e",
|
| 181 |
+
-3.2762470735395457
|
| 182 |
+
],
|
| 183 |
+
[
|
| 184 |
+
"t",
|
| 185 |
+
-3.346505232415412
|
| 186 |
+
],
|
| 187 |
+
[
|
| 188 |
+
"▁the",
|
| 189 |
+
-3.4613494666908995
|
| 190 |
+
],
|
| 191 |
+
[
|
| 192 |
+
"d",
|
| 193 |
+
-3.90460894182274
|
| 194 |
+
],
|
| 195 |
+
[
|
| 196 |
+
"a",
|
| 197 |
+
-3.988983277321309
|
| 198 |
+
],
|
| 199 |
+
[
|
| 200 |
+
"▁a",
|
| 201 |
+
-4.1043433268201825
|
| 202 |
+
],
|
| 203 |
+
[
|
| 204 |
+
"m",
|
| 205 |
+
-4.130835343792769
|
| 206 |
+
],
|
| 207 |
+
[
|
| 208 |
+
"y",
|
| 209 |
+
-4.187992643366066
|
| 210 |
+
],
|
| 211 |
+
[
|
| 212 |
+
"n",
|
| 213 |
+
-4.217156675408131
|
| 214 |
+
],
|
| 215 |
+
[
|
| 216 |
+
"i",
|
| 217 |
+
-4.232281987977052
|
| 218 |
+
],
|
| 219 |
+
[
|
| 220 |
+
"ed",
|
| 221 |
+
-4.311072875814168
|
| 222 |
+
],
|
| 223 |
+
[
|
| 224 |
+
"ing",
|
| 225 |
+
-4.317765051829164
|
| 226 |
+
],
|
| 227 |
+
[
|
| 228 |
+
"▁to",
|
| 229 |
+
-4.331294592787134
|
| 230 |
+
],
|
| 231 |
+
[
|
| 232 |
+
"o",
|
| 233 |
+
-4.346337287814527
|
| 234 |
+
],
|
| 235 |
+
[
|
| 236 |
+
"c",
|
| 237 |
+
-4.3537456912204755
|
| 238 |
+
],
|
| 239 |
+
[
|
| 240 |
+
"▁of",
|
| 241 |
+
-4.408302422120218
|
| 242 |
+
],
|
| 243 |
+
[
|
| 244 |
+
"▁in",
|
| 245 |
+
-4.439226546242843
|
| 246 |
+
],
|
| 247 |
+
[
|
| 248 |
+
"and",
|
| 249 |
+
-4.447707206682657
|
| 250 |
+
],
|
| 251 |
+
[
|
| 252 |
+
"p",
|
| 253 |
+
-4.557523898205941
|
| 254 |
+
],
|
| 255 |
+
[
|
| 256 |
+
"u",
|
| 257 |
+
-4.599969020077225
|
| 258 |
+
],
|
| 259 |
+
[
|
| 260 |
+
"g",
|
| 261 |
+
-4.644611077920461
|
| 262 |
+
],
|
| 263 |
+
[
|
| 264 |
+
"r",
|
| 265 |
+
-4.706481270700311
|
| 266 |
+
],
|
| 267 |
+
[
|
| 268 |
+
"l",
|
| 269 |
+
-4.713380466456869
|
| 270 |
+
],
|
| 271 |
+
[
|
| 272 |
+
"er",
|
| 273 |
+
-4.74899222065031
|
| 274 |
+
],
|
| 275 |
+
[
|
| 276 |
+
"al",
|
| 277 |
+
-4.832948319811666
|
| 278 |
+
],
|
| 279 |
+
[
|
| 280 |
+
"▁is",
|
| 281 |
+
-4.870481905541696
|
| 282 |
+
],
|
| 283 |
+
[
|
| 284 |
+
"in",
|
| 285 |
+
-4.893132701006505
|
| 286 |
+
],
|
| 287 |
+
[
|
| 288 |
+
"k",
|
| 289 |
+
-4.974102278368674
|
| 290 |
+
],
|
| 291 |
+
[
|
| 292 |
+
"or",
|
| 293 |
+
-5.0025052704507935
|
| 294 |
+
],
|
| 295 |
+
[
|
| 296 |
+
"b",
|
| 297 |
+
-5.035860350244143
|
| 298 |
+
],
|
| 299 |
+
[
|
| 300 |
+
"▁be",
|
| 301 |
+
-5.071977878617131
|
| 302 |
+
],
|
| 303 |
+
[
|
| 304 |
+
"ly",
|
| 305 |
+
-5.110970671924331
|
| 306 |
+
],
|
| 307 |
+
[
|
| 308 |
+
"en",
|
| 309 |
+
-5.176639562119152
|
| 310 |
+
],
|
| 311 |
+
[
|
| 312 |
+
"it",
|
| 313 |
+
-5.2223464220674005
|
| 314 |
+
],
|
| 315 |
+
[
|
| 316 |
+
"v",
|
| 317 |
+
-5.230571121824163
|
| 318 |
+
],
|
| 319 |
+
[
|
| 320 |
+
"le",
|
| 321 |
+
-5.261011559598946
|
| 322 |
+
],
|
| 323 |
+
[
|
| 324 |
+
"ar",
|
| 325 |
+
-5.28733580866414
|
| 326 |
+
],
|
| 327 |
+
[
|
| 328 |
+
"ch",
|
| 329 |
+
-5.331946977557094
|
| 330 |
+
],
|
| 331 |
+
[
|
| 332 |
+
"st",
|
| 333 |
+
-5.34591745748041
|
| 334 |
+
],
|
| 335 |
+
[
|
| 336 |
+
"an",
|
| 337 |
+
-5.355807230421707
|
| 338 |
+
],
|
| 339 |
+
[
|
| 340 |
+
"▁f",
|
| 341 |
+
-5.391744389389056
|
| 342 |
+
],
|
| 343 |
+
[
|
| 344 |
+
"ic",
|
| 345 |
+
-5.423546538328285
|
| 346 |
+
],
|
| 347 |
+
[
|
| 348 |
+
"▁for",
|
| 349 |
+
-5.447670532180611
|
| 350 |
+
],
|
| 351 |
+
[
|
| 352 |
+
"f",
|
| 353 |
+
-5.48303699228936
|
| 354 |
+
],
|
| 355 |
+
[
|
| 356 |
+
"w",
|
| 357 |
+
-5.5198467796805755
|
| 358 |
+
],
|
| 359 |
+
[
|
| 360 |
+
"ur",
|
| 361 |
+
-5.530880383304706
|
| 362 |
+
],
|
| 363 |
+
[
|
| 364 |
+
"es",
|
| 365 |
+
-5.5501989639084055
|
| 366 |
+
],
|
| 367 |
+
[
|
| 368 |
+
"on",
|
| 369 |
+
-5.557399947373246
|
| 370 |
+
],
|
| 371 |
+
[
|
| 372 |
+
"▁re",
|
| 373 |
+
-5.567545311958694
|
| 374 |
+
],
|
| 375 |
+
[
|
| 376 |
+
"▁are",
|
| 377 |
+
-5.573269832805648
|
| 378 |
+
],
|
| 379 |
+
[
|
| 380 |
+
"▁on",
|
| 381 |
+
-5.59021385720431
|
| 382 |
+
],
|
| 383 |
+
[
|
| 384 |
+
"th",
|
| 385 |
+
-5.627197447181516
|
| 386 |
+
],
|
| 387 |
+
[
|
| 388 |
+
"▁h",
|
| 389 |
+
-5.644403198021651
|
| 390 |
+
],
|
| 391 |
+
[
|
| 392 |
+
"▁tha",
|
| 393 |
+
-5.647913682947817
|
| 394 |
+
],
|
| 395 |
+
[
|
| 396 |
+
"▁c",
|
| 397 |
+
-5.6522531999839325
|
| 398 |
+
],
|
| 399 |
+
[
|
| 400 |
+
"h",
|
| 401 |
+
-5.6671890386742785
|
| 402 |
+
],
|
| 403 |
+
[
|
| 404 |
+
"▁w",
|
| 405 |
+
-5.688082766473154
|
| 406 |
+
],
|
| 407 |
+
[
|
| 408 |
+
"re",
|
| 409 |
+
-5.722153275438761
|
| 410 |
+
],
|
| 411 |
+
[
|
| 412 |
+
"ir",
|
| 413 |
+
-5.7903344504118595
|
| 414 |
+
],
|
| 415 |
+
[
|
| 416 |
+
"▁b",
|
| 417 |
+
-5.801750081259955
|
| 418 |
+
],
|
| 419 |
+
[
|
| 420 |
+
"▁with",
|
| 421 |
+
-5.819491368215889
|
| 422 |
+
],
|
| 423 |
+
[
|
| 424 |
+
"ro",
|
| 425 |
+
-5.822405765770177
|
| 426 |
+
],
|
| 427 |
+
[
|
| 428 |
+
"ri",
|
| 429 |
+
-5.854370618582819
|
| 430 |
+
],
|
| 431 |
+
[
|
| 432 |
+
"ation",
|
| 433 |
+
-5.855145426489802
|
| 434 |
+
],
|
| 435 |
+
[
|
| 436 |
+
"0",
|
| 437 |
+
-5.8872829347974
|
| 438 |
+
],
|
| 439 |
+
[
|
| 440 |
+
"▁was",
|
| 441 |
+
-5.894023413092957
|
| 442 |
+
],
|
| 443 |
+
[
|
| 444 |
+
"ent",
|
| 445 |
+
-5.913173819895014
|
| 446 |
+
],
|
| 447 |
+
[
|
| 448 |
+
"▁or",
|
| 449 |
+
-5.929829545288575
|
| 450 |
+
],
|
| 451 |
+
[
|
| 452 |
+
"ce",
|
| 453 |
+
-5.94118778631942
|
| 454 |
+
],
|
| 455 |
+
[
|
| 456 |
+
"▁an",
|
| 457 |
+
-5.942275864998134
|
| 458 |
+
],
|
| 459 |
+
[
|
| 460 |
+
"▁st",
|
| 461 |
+
-5.959845626706876
|
| 462 |
+
],
|
| 463 |
+
[
|
| 464 |
+
"▁p",
|
| 465 |
+
-5.979182853147907
|
| 466 |
+
],
|
| 467 |
+
[
|
| 468 |
+
"▁co",
|
| 469 |
+
-5.99464444437195
|
| 470 |
+
],
|
| 471 |
+
[
|
| 472 |
+
"tion",
|
| 473 |
+
-6.018005629870164
|
| 474 |
+
],
|
| 475 |
+
[
|
| 476 |
+
"▁de",
|
| 477 |
+
-6.0197214334498375
|
| 478 |
+
],
|
| 479 |
+
[
|
| 480 |
+
"at",
|
| 481 |
+
-6.023872247567192
|
| 482 |
+
],
|
| 483 |
+
[
|
| 484 |
+
"▁it",
|
| 485 |
+
-6.0468006319666525
|
| 486 |
+
],
|
| 487 |
+
[
|
| 488 |
+
"il",
|
| 489 |
+
-6.071419632524207
|
| 490 |
+
],
|
| 491 |
+
[
|
| 492 |
+
"▁su",
|
| 493 |
+
-6.087265345738892
|
| 494 |
+
],
|
| 495 |
+
[
|
| 496 |
+
"▁ma",
|
| 497 |
+
-6.0955072307599565
|
| 498 |
+
],
|
| 499 |
+
[
|
| 500 |
+
"▁as",
|
| 501 |
+
-6.096445849090732
|
| 502 |
+
],
|
| 503 |
+
[
|
| 504 |
+
"▁fro",
|
| 505 |
+
-6.129354549270313
|
| 506 |
+
],
|
| 507 |
+
[
|
| 508 |
+
"▁you",
|
| 509 |
+
-6.131897252589564
|
| 510 |
+
],
|
| 511 |
+
[
|
| 512 |
+
"ol",
|
| 513 |
+
-6.1390576793196425
|
| 514 |
+
],
|
| 515 |
+
[
|
| 516 |
+
"▁con",
|
| 517 |
+
-6.145755126990158
|
| 518 |
+
],
|
| 519 |
+
[
|
| 520 |
+
"la",
|
| 521 |
+
-6.146651426274379
|
| 522 |
+
],
|
| 523 |
+
[
|
| 524 |
+
"▁can",
|
| 525 |
+
-6.149043410740569
|
| 526 |
+
],
|
| 527 |
+
[
|
| 528 |
+
"▁he",
|
| 529 |
+
-6.152763862900574
|
| 530 |
+
],
|
| 531 |
+
[
|
| 532 |
+
"▁hav",
|
| 533 |
+
-6.156435802908428
|
| 534 |
+
],
|
| 535 |
+
[
|
| 536 |
+
"▁1",
|
| 537 |
+
-6.160132051411401
|
| 538 |
+
],
|
| 539 |
+
[
|
| 540 |
+
"is",
|
| 541 |
+
-6.195569695401377
|
| 542 |
+
],
|
| 543 |
+
[
|
| 544 |
+
"▁by",
|
| 545 |
+
-6.212529629983307
|
| 546 |
+
],
|
| 547 |
+
[
|
| 548 |
+
"lo",
|
| 549 |
+
-6.220446873243513
|
| 550 |
+
],
|
| 551 |
+
[
|
| 552 |
+
"ll",
|
| 553 |
+
-6.228179292983937
|
| 554 |
+
],
|
| 555 |
+
[
|
| 556 |
+
"ies",
|
| 557 |
+
-6.245665905271688
|
| 558 |
+
],
|
| 559 |
+
[
|
| 560 |
+
"id",
|
| 561 |
+
-6.260508224854381
|
| 562 |
+
],
|
| 563 |
+
[
|
| 564 |
+
"▁not",
|
| 565 |
+
-6.267819101117954
|
| 566 |
+
],
|
| 567 |
+
[
|
| 568 |
+
"if",
|
| 569 |
+
-6.270644329586759
|
| 570 |
+
],
|
| 571 |
+
[
|
| 572 |
+
"un",
|
| 573 |
+
-6.275506263031922
|
| 574 |
+
],
|
| 575 |
+
[
|
| 576 |
+
"▁thi",
|
| 577 |
+
-6.2881655764394235
|
| 578 |
+
],
|
| 579 |
+
[
|
| 580 |
+
"▁di",
|
| 581 |
+
-6.329588431001757
|
| 582 |
+
],
|
| 583 |
+
[
|
| 584 |
+
"us",
|
| 585 |
+
-6.333327209962254
|
| 586 |
+
],
|
| 587 |
+
[
|
| 588 |
+
"ra",
|
| 589 |
+
-6.340865501780096
|
| 590 |
+
],
|
| 591 |
+
[
|
| 592 |
+
"▁at",
|
| 593 |
+
-6.355182350030107
|
| 594 |
+
],
|
| 595 |
+
[
|
| 596 |
+
"j",
|
| 597 |
+
-6.357964711000992
|
| 598 |
+
],
|
| 599 |
+
[
|
| 600 |
+
"ve",
|
| 601 |
+
-6.372531519329924
|
| 602 |
+
],
|
| 603 |
+
[
|
| 604 |
+
"om",
|
| 605 |
+
-6.37496567318558
|
| 606 |
+
],
|
| 607 |
+
[
|
| 608 |
+
"ate",
|
| 609 |
+
-6.3753246003687005
|
| 610 |
+
],
|
| 611 |
+
[
|
| 612 |
+
"el",
|
| 613 |
+
-6.390196095937399
|
| 614 |
+
],
|
| 615 |
+
[
|
| 616 |
+
"ion",
|
| 617 |
+
-6.396975087246941
|
| 618 |
+
],
|
| 619 |
+
[
|
| 620 |
+
"▁2",
|
| 621 |
+
-6.400755836647712
|
| 622 |
+
],
|
| 623 |
+
[
|
| 624 |
+
"▁we",
|
| 625 |
+
-6.412240561664114
|
| 626 |
+
],
|
| 627 |
+
[
|
| 628 |
+
"▁g",
|
| 629 |
+
-6.416027622473206
|
| 630 |
+
],
|
| 631 |
+
[
|
| 632 |
+
"z",
|
| 633 |
+
-6.43633541535936
|
| 634 |
+
],
|
| 635 |
+
[
|
| 636 |
+
"▁sa",
|
| 637 |
+
-6.43850552769723
|
| 638 |
+
],
|
| 639 |
+
[
|
| 640 |
+
"ver",
|
| 641 |
+
-6.447887731618186
|
| 642 |
+
],
|
| 643 |
+
[
|
| 644 |
+
"▁whi",
|
| 645 |
+
-6.457883910972052
|
| 646 |
+
],
|
| 647 |
+
[
|
| 648 |
+
"x",
|
| 649 |
+
-6.459583214795332
|
| 650 |
+
],
|
| 651 |
+
[
|
| 652 |
+
"▁pa",
|
| 653 |
+
-6.503480316267584
|
| 654 |
+
],
|
| 655 |
+
[
|
| 656 |
+
"ive",
|
| 657 |
+
-6.5110947788952975
|
| 658 |
+
],
|
| 659 |
+
[
|
| 660 |
+
"ight",
|
| 661 |
+
-6.536365914035072
|
| 662 |
+
],
|
| 663 |
+
[
|
| 664 |
+
"ers",
|
| 665 |
+
-6.5428103154111135
|
| 666 |
+
],
|
| 667 |
+
[
|
| 668 |
+
"▁bo",
|
| 669 |
+
-6.546150816046826
|
| 670 |
+
],
|
| 671 |
+
[
|
| 672 |
+
"▁no",
|
| 673 |
+
-6.547088192255935
|
| 674 |
+
],
|
| 675 |
+
[
|
| 676 |
+
"ment",
|
| 677 |
+
-6.562479873766899
|
| 678 |
+
],
|
| 679 |
+
[
|
| 680 |
+
"▁pro",
|
| 681 |
+
-6.571064898982521
|
| 682 |
+
],
|
| 683 |
+
[
|
| 684 |
+
"act",
|
| 685 |
+
-6.583990559778682
|
| 686 |
+
],
|
| 687 |
+
[
|
| 688 |
+
"▁has",
|
| 689 |
+
-6.603654202468725
|
| 690 |
+
],
|
| 691 |
+
[
|
| 692 |
+
"out",
|
| 693 |
+
-6.60580960365786
|
| 694 |
+
],
|
| 695 |
+
[
|
| 696 |
+
"▁mo",
|
| 697 |
+
-6.612206063842681
|
| 698 |
+
],
|
| 699 |
+
[
|
| 700 |
+
"▁man",
|
| 701 |
+
-6.641204427471876
|
| 702 |
+
],
|
| 703 |
+
[
|
| 704 |
+
"age",
|
| 705 |
+
-6.641280763657149
|
| 706 |
+
],
|
| 707 |
+
[
|
| 708 |
+
"▁will",
|
| 709 |
+
-6.64270247271019
|
| 710 |
+
],
|
| 711 |
+
[
|
| 712 |
+
"▁me",
|
| 713 |
+
-6.647724830351693
|
| 714 |
+
],
|
| 715 |
+
[
|
| 716 |
+
"4",
|
| 717 |
+
-6.651679234308922
|
| 718 |
+
],
|
| 719 |
+
[
|
| 720 |
+
"ant",
|
| 721 |
+
-6.653057213377799
|
| 722 |
+
],
|
| 723 |
+
[
|
| 724 |
+
"▁sp",
|
| 725 |
+
-6.653170671243362
|
| 726 |
+
],
|
| 727 |
+
[
|
| 728 |
+
"▁us",
|
| 729 |
+
-6.660440017314415
|
| 730 |
+
],
|
| 731 |
+
[
|
| 732 |
+
"5",
|
| 733 |
+
-6.669223493954846
|
| 734 |
+
],
|
| 735 |
+
[
|
| 736 |
+
"▁k",
|
| 737 |
+
-6.669597778381468
|
| 738 |
+
],
|
| 739 |
+
[
|
| 740 |
+
"▁some",
|
| 741 |
+
-6.6818801214084935
|
| 742 |
+
],
|
| 743 |
+
[
|
| 744 |
+
"were",
|
| 745 |
+
-6.685358326258509
|
| 746 |
+
],
|
| 747 |
+
[
|
| 748 |
+
"day",
|
| 749 |
+
-6.685810790026934
|
| 750 |
+
],
|
| 751 |
+
[
|
| 752 |
+
"est",
|
| 753 |
+
-6.692698060575062
|
| 754 |
+
],
|
| 755 |
+
[
|
| 756 |
+
"ul",
|
| 757 |
+
-6.710575311022998
|
| 758 |
+
],
|
| 759 |
+
[
|
| 760 |
+
"ph",
|
| 761 |
+
-6.73056730249125
|
| 762 |
+
],
|
| 763 |
+
[
|
| 764 |
+
"▁ex",
|
| 765 |
+
-6.733336219158555
|
| 766 |
+
],
|
| 767 |
+
[
|
| 768 |
+
"▁fa",
|
| 769 |
+
-6.765091874615061
|
| 770 |
+
],
|
| 771 |
+
[
|
| 772 |
+
"▁so",
|
| 773 |
+
-6.767286242386988
|
| 774 |
+
],
|
| 775 |
+
[
|
| 776 |
+
"ard",
|
| 777 |
+
-6.772605838493793
|
| 778 |
+
],
|
| 779 |
+
[
|
| 780 |
+
"▁un",
|
| 781 |
+
-6.787572388877607
|
| 782 |
+
],
|
| 783 |
+
[
|
| 784 |
+
"▁do",
|
| 785 |
+
-6.795074557643034
|
| 786 |
+
],
|
| 787 |
+
[
|
| 788 |
+
"▁other",
|
| 789 |
+
-6.7956782657022545
|
| 790 |
+
],
|
| 791 |
+
[
|
| 792 |
+
"▁but",
|
| 793 |
+
-6.8025729087235485
|
| 794 |
+
],
|
| 795 |
+
[
|
| 796 |
+
"ther",
|
| 797 |
+
-6.803231620372917
|
| 798 |
+
],
|
| 799 |
+
[
|
| 800 |
+
"ian",
|
| 801 |
+
-6.812902667758519
|
| 802 |
+
],
|
| 803 |
+
[
|
| 804 |
+
"▁one",
|
| 805 |
+
-6.821076061857491
|
| 806 |
+
],
|
| 807 |
+
[
|
| 808 |
+
"▁more",
|
| 809 |
+
-6.8266493698278925
|
| 810 |
+
],
|
| 811 |
+
[
|
| 812 |
+
"6",
|
| 813 |
+
-6.82879636799627
|
| 814 |
+
],
|
| 815 |
+
[
|
| 816 |
+
"ous",
|
| 817 |
+
-6.855962306912703
|
| 818 |
+
],
|
| 819 |
+
[
|
| 820 |
+
"▁whe",
|
| 821 |
+
-6.859091467805891
|
| 822 |
+
],
|
| 823 |
+
[
|
| 824 |
+
"able",
|
| 825 |
+
-6.8654555236076575
|
| 826 |
+
],
|
| 827 |
+
[
|
| 828 |
+
"▁most",
|
| 829 |
+
-6.865507428780849
|
| 830 |
+
],
|
| 831 |
+
[
|
| 832 |
+
"▁all",
|
| 833 |
+
-6.868332909576947
|
| 834 |
+
],
|
| 835 |
+
[
|
| 836 |
+
"ca",
|
| 837 |
+
-6.868732115162404
|
| 838 |
+
],
|
| 839 |
+
[
|
| 840 |
+
"▁mi",
|
| 841 |
+
-6.871663607421129
|
| 842 |
+
],
|
| 843 |
+
[
|
| 844 |
+
"▁car",
|
| 845 |
+
-6.872038781117334
|
| 846 |
+
],
|
| 847 |
+
[
|
| 848 |
+
"▁en",
|
| 849 |
+
-6.877446929350223
|
| 850 |
+
],
|
| 851 |
+
[
|
| 852 |
+
"per",
|
| 853 |
+
-6.892167759263063
|
| 854 |
+
],
|
| 855 |
+
[
|
| 856 |
+
"▁time",
|
| 857 |
+
-6.8931312430041185
|
| 858 |
+
],
|
| 859 |
+
[
|
| 860 |
+
"▁vi",
|
| 861 |
+
-6.895209208386817
|
| 862 |
+
],
|
| 863 |
+
[
|
| 864 |
+
"had",
|
| 865 |
+
-6.898533648058522
|
| 866 |
+
],
|
| 867 |
+
[
|
| 868 |
+
"▁go",
|
| 869 |
+
-6.902336913332548
|
| 870 |
+
],
|
| 871 |
+
[
|
| 872 |
+
"lso",
|
| 873 |
+
-6.913439467216554
|
| 874 |
+
],
|
| 875 |
+
[
|
| 876 |
+
"▁sh",
|
| 877 |
+
-6.919449248503678
|
| 878 |
+
],
|
| 879 |
+
[
|
| 880 |
+
"▁li",
|
| 881 |
+
-6.922560430255311
|
| 882 |
+
],
|
| 883 |
+
[
|
| 884 |
+
"▁countr",
|
| 885 |
+
-6.923075365505835
|
| 886 |
+
],
|
| 887 |
+
[
|
| 888 |
+
"▁ra",
|
| 889 |
+
-6.924585801451686
|
| 890 |
+
],
|
| 891 |
+
[
|
| 892 |
+
"▁br",
|
| 893 |
+
-6.931064678460284
|
| 894 |
+
],
|
| 895 |
+
[
|
| 896 |
+
"▁ab",
|
| 897 |
+
-6.931940367854744
|
| 898 |
+
],
|
| 899 |
+
[
|
| 900 |
+
"ia",
|
| 901 |
+
-6.937806621480712
|
| 902 |
+
],
|
| 903 |
+
[
|
| 904 |
+
"ance",
|
| 905 |
+
-6.957346174263031
|
| 906 |
+
],
|
| 907 |
+
[
|
| 908 |
+
"8",
|
| 909 |
+
-6.961832959098544
|
| 910 |
+
],
|
| 911 |
+
[
|
| 912 |
+
"▁3",
|
| 913 |
+
-6.968100343799258
|
| 914 |
+
],
|
| 915 |
+
[
|
| 916 |
+
"▁there",
|
| 917 |
+
-6.9733914148350085
|
| 918 |
+
],
|
| 919 |
+
[
|
| 920 |
+
"ish",
|
| 921 |
+
-6.986137594465574
|
| 922 |
+
],
|
| 923 |
+
[
|
| 924 |
+
"▁even",
|
| 925 |
+
-7.002799148099052
|
| 926 |
+
],
|
| 927 |
+
[
|
| 928 |
+
"▁people",
|
| 929 |
+
-7.02716205152031
|
| 930 |
+
],
|
| 931 |
+
[
|
| 932 |
+
"▁per",
|
| 933 |
+
-7.0330618605904665
|
| 934 |
+
],
|
| 935 |
+
[
|
| 936 |
+
"way",
|
| 937 |
+
-7.03633517131352
|
| 938 |
+
],
|
| 939 |
+
[
|
| 940 |
+
"ern",
|
| 941 |
+
-7.042479278911798
|
| 942 |
+
],
|
| 943 |
+
[
|
| 944 |
+
"▁pre",
|
| 945 |
+
-7.0523064460866784
|
| 946 |
+
],
|
| 947 |
+
[
|
| 948 |
+
"ff",
|
| 949 |
+
-7.053031071467035
|
| 950 |
+
],
|
| 951 |
+
[
|
| 952 |
+
"▁your",
|
| 953 |
+
-7.066913374732923
|
| 954 |
+
],
|
| 955 |
+
[
|
| 956 |
+
"▁new",
|
| 957 |
+
-7.0793013547195525
|
| 958 |
+
],
|
| 959 |
+
[
|
| 960 |
+
"9",
|
| 961 |
+
-7.085883866389088
|
| 962 |
+
],
|
| 963 |
+
[
|
| 964 |
+
"ill",
|
| 965 |
+
-7.089598704000823
|
| 966 |
+
],
|
| 967 |
+
[
|
| 968 |
+
"▁over",
|
| 969 |
+
-7.098805832816234
|
| 970 |
+
],
|
| 971 |
+
[
|
| 972 |
+
"▁after",
|
| 973 |
+
-7.115356643253071
|
| 974 |
+
],
|
| 975 |
+
[
|
| 976 |
+
"▁tra",
|
| 977 |
+
-7.120228788920384
|
| 978 |
+
],
|
| 979 |
+
[
|
| 980 |
+
"low",
|
| 981 |
+
-7.122220040050001
|
| 982 |
+
],
|
| 983 |
+
[
|
| 984 |
+
"▁comp",
|
| 985 |
+
-7.133500815815238
|
| 986 |
+
],
|
| 987 |
+
[
|
| 988 |
+
"▁ba",
|
| 989 |
+
-7.141131224024946
|
| 990 |
+
],
|
| 991 |
+
[
|
| 992 |
+
"ical",
|
| 993 |
+
-7.1422260237143265
|
| 994 |
+
],
|
| 995 |
+
[
|
| 996 |
+
"round",
|
| 997 |
+
-7.1435233350247245
|
| 998 |
+
],
|
| 999 |
+
[
|
| 1000 |
+
"7",
|
| 1001 |
+
-7.152886984152966
|
| 1002 |
+
],
|
| 1003 |
+
[
|
| 1004 |
+
"▁year",
|
| 1005 |
+
-7.153144193143549
|
| 1006 |
+
],
|
| 1007 |
+
[
|
| 1008 |
+
"▁may",
|
| 1009 |
+
-7.159125415859334
|
| 1010 |
+
],
|
| 1011 |
+
[
|
| 1012 |
+
"▁na",
|
| 1013 |
+
-7.161008162022526
|
| 1014 |
+
],
|
| 1015 |
+
[
|
| 1016 |
+
"one",
|
| 1017 |
+
-7.184878065317987
|
| 1018 |
+
],
|
| 1019 |
+
[
|
| 1020 |
+
"▁al",
|
| 1021 |
+
-7.195461984655057
|
| 1022 |
+
],
|
| 1023 |
+
[
|
| 1024 |
+
"um",
|
| 1025 |
+
-7.209006967663773
|
| 1026 |
+
],
|
| 1027 |
+
[
|
| 1028 |
+
"▁pri",
|
| 1029 |
+
-7.210069850711059
|
| 1030 |
+
],
|
| 1031 |
+
[
|
| 1032 |
+
"▁world",
|
| 1033 |
+
-7.212023222385909
|
| 1034 |
+
],
|
| 1035 |
+
[
|
| 1036 |
+
"▁who",
|
| 1037 |
+
-7.223014137024571
|
| 1038 |
+
],
|
| 1039 |
+
[
|
| 1040 |
+
"ould",
|
| 1041 |
+
-7.226760603979994
|
| 1042 |
+
],
|
| 1043 |
+
[
|
| 1044 |
+
"▁out",
|
| 1045 |
+
-7.231998550417056
|
| 1046 |
+
],
|
| 1047 |
+
[
|
| 1048 |
+
"▁its",
|
| 1049 |
+
-7.233405561461712
|
| 1050 |
+
],
|
| 1051 |
+
[
|
| 1052 |
+
"▁up",
|
| 1053 |
+
-7.285142155426511
|
| 1054 |
+
],
|
| 1055 |
+
[
|
| 1056 |
+
"▁than",
|
| 1057 |
+
-7.299137896625927
|
| 1058 |
+
],
|
| 1059 |
+
[
|
| 1060 |
+
"▁state",
|
| 1061 |
+
-7.30645541347183
|
| 1062 |
+
],
|
| 1063 |
+
[
|
| 1064 |
+
"ence",
|
| 1065 |
+
-7.318807589581895
|
| 1066 |
+
],
|
| 1067 |
+
[
|
| 1068 |
+
"long",
|
| 1069 |
+
-7.332923092470053
|
| 1070 |
+
],
|
| 1071 |
+
[
|
| 1072 |
+
"▁his",
|
| 1073 |
+
-7.3354486738370595
|
| 1074 |
+
],
|
| 1075 |
+
[
|
| 1076 |
+
"ize",
|
| 1077 |
+
-7.335587746438243
|
| 1078 |
+
],
|
| 1079 |
+
[
|
| 1080 |
+
"ose",
|
| 1081 |
+
-7.339855014717346
|
| 1082 |
+
],
|
| 1083 |
+
[
|
| 1084 |
+
"▁know",
|
| 1085 |
+
-7.341930003063956
|
| 1086 |
+
],
|
| 1087 |
+
[
|
| 1088 |
+
"ry",
|
| 1089 |
+
-7.344186782226564
|
| 1090 |
+
],
|
| 1091 |
+
[
|
| 1092 |
+
"2",
|
| 1093 |
+
-7.344207514829643
|
| 1094 |
+
],
|
| 1095 |
+
[
|
| 1096 |
+
"▁imp",
|
| 1097 |
+
-7.353859464596262
|
| 1098 |
+
],
|
| 1099 |
+
[
|
| 1100 |
+
"ary",
|
| 1101 |
+
-7.354825893119824
|
| 1102 |
+
],
|
| 1103 |
+
[
|
| 1104 |
+
"▁often",
|
| 1105 |
+
-7.358854125859942
|
| 1106 |
+
],
|
| 1107 |
+
[
|
| 1108 |
+
"▁call",
|
| 1109 |
+
-7.378671801439579
|
| 1110 |
+
],
|
| 1111 |
+
[
|
| 1112 |
+
"▁into",
|
| 1113 |
+
-7.386238978021677
|
| 1114 |
+
],
|
| 1115 |
+
[
|
| 1116 |
+
"▁part",
|
| 1117 |
+
-7.392001248006106
|
| 1118 |
+
],
|
| 1119 |
+
[
|
| 1120 |
+
"ture",
|
| 1121 |
+
-7.395700798454083
|
| 1122 |
+
],
|
| 1123 |
+
[
|
| 1124 |
+
"▁how",
|
| 1125 |
+
-7.414132628968153
|
| 1126 |
+
],
|
| 1127 |
+
[
|
| 1128 |
+
"que",
|
| 1129 |
+
-7.4158513488173
|
| 1130 |
+
],
|
| 1131 |
+
[
|
| 1132 |
+
"where",
|
| 1133 |
+
-7.416644301772499
|
| 1134 |
+
],
|
| 1135 |
+
[
|
| 1136 |
+
"▁19",
|
| 1137 |
+
-7.416822207519889
|
| 1138 |
+
],
|
| 1139 |
+
[
|
| 1140 |
+
"1",
|
| 1141 |
+
-7.434230018742243
|
| 1142 |
+
],
|
| 1143 |
+
[
|
| 1144 |
+
"▁travel",
|
| 1145 |
+
-7.451833886454098
|
| 1146 |
+
],
|
| 1147 |
+
[
|
| 1148 |
+
"▁dur",
|
| 1149 |
+
-7.487770219521905
|
| 1150 |
+
],
|
| 1151 |
+
[
|
| 1152 |
+
"▁mon",
|
| 1153 |
+
-7.48847200394581
|
| 1154 |
+
],
|
| 1155 |
+
[
|
| 1156 |
+
"▁work",
|
| 1157 |
+
-7.491585291065162
|
| 1158 |
+
],
|
| 1159 |
+
[
|
| 1160 |
+
"cause",
|
| 1161 |
+
-7.4924841199173855
|
| 1162 |
+
],
|
| 1163 |
+
[
|
| 1164 |
+
"▁war",
|
| 1165 |
+
-7.494757093128933
|
| 1166 |
+
],
|
| 1167 |
+
[
|
| 1168 |
+
"inter",
|
| 1169 |
+
-7.500819628415845
|
| 1170 |
+
],
|
| 1171 |
+
[
|
| 1172 |
+
"▁like",
|
| 1173 |
+
-7.505488775076321
|
| 1174 |
+
],
|
| 1175 |
+
[
|
| 1176 |
+
"thing",
|
| 1177 |
+
-7.510805171237376
|
| 1178 |
+
],
|
| 1179 |
+
[
|
| 1180 |
+
"▁comm",
|
| 1181 |
+
-7.521731365223375
|
| 1182 |
+
],
|
| 1183 |
+
[
|
| 1184 |
+
"▁cit",
|
| 1185 |
+
-7.524839744064275
|
| 1186 |
+
],
|
| 1187 |
+
[
|
| 1188 |
+
"▁sai",
|
| 1189 |
+
-7.525578186853979
|
| 1190 |
+
],
|
| 1191 |
+
[
|
| 1192 |
+
"read",
|
| 1193 |
+
-7.527557697032419
|
| 1194 |
+
],
|
| 1195 |
+
[
|
| 1196 |
+
"▁different",
|
| 1197 |
+
-7.5464568591042385
|
| 1198 |
+
],
|
| 1199 |
+
[
|
| 1200 |
+
"▁get",
|
| 1201 |
+
-7.552169862062854
|
| 1202 |
+
],
|
| 1203 |
+
[
|
| 1204 |
+
"ock",
|
| 1205 |
+
-7.555306657435667
|
| 1206 |
+
],
|
| 1207 |
+
[
|
| 1208 |
+
"▁show",
|
| 1209 |
+
-7.575335097438488
|
| 1210 |
+
],
|
| 1211 |
+
[
|
| 1212 |
+
"▁north",
|
| 1213 |
+
-7.575620423647008
|
| 1214 |
+
],
|
| 1215 |
+
[
|
| 1216 |
+
"▁make",
|
| 1217 |
+
-7.577043786702754
|
| 1218 |
+
],
|
| 1219 |
+
[
|
| 1220 |
+
"▁tri",
|
| 1221 |
+
-7.590393027908454
|
| 1222 |
+
],
|
| 1223 |
+
[
|
| 1224 |
+
"though",
|
| 1225 |
+
-7.593003994539069
|
| 1226 |
+
],
|
| 1227 |
+
[
|
| 1228 |
+
"▁jo",
|
| 1229 |
+
-7.617850059876274
|
| 1230 |
+
],
|
| 1231 |
+
[
|
| 1232 |
+
"ign",
|
| 1233 |
+
-7.621768802470928
|
| 1234 |
+
],
|
| 1235 |
+
[
|
| 1236 |
+
"▁fre",
|
| 1237 |
+
-7.625386647341769
|
| 1238 |
+
],
|
| 1239 |
+
[
|
| 1240 |
+
"▁see",
|
| 1241 |
+
-7.6336479886677315
|
| 1242 |
+
],
|
| 1243 |
+
[
|
| 1244 |
+
"▁app",
|
| 1245 |
+
-7.639523684019808
|
| 1246 |
+
],
|
| 1247 |
+
[
|
| 1248 |
+
"▁place",
|
| 1249 |
+
-7.651093729477778
|
| 1250 |
+
],
|
| 1251 |
+
[
|
| 1252 |
+
"▁water",
|
| 1253 |
+
-7.651415059507122
|
| 1254 |
+
],
|
| 1255 |
+
[
|
| 1256 |
+
"▁report",
|
| 1257 |
+
-7.666922795581368
|
| 1258 |
+
],
|
| 1259 |
+
[
|
| 1260 |
+
"▁just",
|
| 1261 |
+
-7.683062641491382
|
| 1262 |
+
],
|
| 1263 |
+
[
|
| 1264 |
+
"▁should",
|
| 1265 |
+
-7.684631124020186
|
| 1266 |
+
],
|
| 1267 |
+
[
|
| 1268 |
+
"▁cha",
|
| 1269 |
+
-7.686782915070514
|
| 1270 |
+
],
|
| 1271 |
+
[
|
| 1272 |
+
"side",
|
| 1273 |
+
-7.706471569720542
|
| 1274 |
+
],
|
| 1275 |
+
[
|
| 1276 |
+
"ness",
|
| 1277 |
+
-7.708460850991384
|
| 1278 |
+
],
|
| 1279 |
+
[
|
| 1280 |
+
"▁south",
|
| 1281 |
+
-7.716338337987308
|
| 1282 |
+
],
|
| 1283 |
+
[
|
| 1284 |
+
"▁10",
|
| 1285 |
+
-7.7273771012898225
|
| 1286 |
+
],
|
| 1287 |
+
[
|
| 1288 |
+
"▁includ",
|
| 1289 |
+
-7.733039602026582
|
| 1290 |
+
],
|
| 1291 |
+
[
|
| 1292 |
+
"▁back",
|
| 1293 |
+
-7.733220730712199
|
| 1294 |
+
],
|
| 1295 |
+
[
|
| 1296 |
+
"▁qu",
|
| 1297 |
+
-7.755042830237189
|
| 1298 |
+
],
|
| 1299 |
+
[
|
| 1300 |
+
"▁par",
|
| 1301 |
+
-7.761722791424332
|
| 1302 |
+
],
|
| 1303 |
+
[
|
| 1304 |
+
"▁small",
|
| 1305 |
+
-7.767843049176307
|
| 1306 |
+
],
|
| 1307 |
+
[
|
| 1308 |
+
"▁need",
|
| 1309 |
+
-7.769123438158099
|
| 1310 |
+
],
|
| 1311 |
+
[
|
| 1312 |
+
"3",
|
| 1313 |
+
-7.771541622268048
|
| 1314 |
+
],
|
| 1315 |
+
[
|
| 1316 |
+
"tter",
|
| 1317 |
+
-7.772352757891329
|
| 1318 |
+
],
|
| 1319 |
+
[
|
| 1320 |
+
"ough",
|
| 1321 |
+
-7.782401384709099
|
| 1322 |
+
],
|
| 1323 |
+
[
|
| 1324 |
+
"▁take",
|
| 1325 |
+
-7.803964097405506
|
| 1326 |
+
],
|
| 1327 |
+
[
|
| 1328 |
+
"▁require",
|
| 1329 |
+
-7.822395117221289
|
| 1330 |
+
],
|
| 1331 |
+
[
|
| 1332 |
+
"▁base",
|
| 1333 |
+
-7.823680575156837
|
| 1334 |
+
],
|
| 1335 |
+
[
|
| 1336 |
+
"▁gra",
|
| 1337 |
+
-7.825064277345991
|
| 1338 |
+
],
|
| 1339 |
+
[
|
| 1340 |
+
"▁through",
|
| 1341 |
+
-7.841251976339118
|
| 1342 |
+
],
|
| 1343 |
+
[
|
| 1344 |
+
"▁high",
|
| 1345 |
+
-7.841254254031162
|
| 1346 |
+
],
|
| 1347 |
+
[
|
| 1348 |
+
"▁visit",
|
| 1349 |
+
-7.861379901015909
|
| 1350 |
+
],
|
| 1351 |
+
[
|
| 1352 |
+
"▁home",
|
| 1353 |
+
-7.862319183680619
|
| 1354 |
+
],
|
| 1355 |
+
[
|
| 1356 |
+
"cient",
|
| 1357 |
+
-7.8663293686340445
|
| 1358 |
+
],
|
| 1359 |
+
[
|
| 1360 |
+
"▁ski",
|
| 1361 |
+
-7.872481670538821
|
| 1362 |
+
],
|
| 1363 |
+
[
|
| 1364 |
+
"▁island",
|
| 1365 |
+
-7.882319522995838
|
| 1366 |
+
],
|
| 1367 |
+
[
|
| 1368 |
+
"▁large",
|
| 1369 |
+
-7.900124903843213
|
| 1370 |
+
],
|
| 1371 |
+
[
|
| 1372 |
+
"▁down",
|
| 1373 |
+
-7.900275079303846
|
| 1374 |
+
],
|
| 1375 |
+
[
|
| 1376 |
+
"▁child",
|
| 1377 |
+
-7.900295796047779
|
| 1378 |
+
],
|
| 1379 |
+
[
|
| 1380 |
+
"▁near",
|
| 1381 |
+
-7.9006274881876095
|
| 1382 |
+
],
|
| 1383 |
+
[
|
| 1384 |
+
"each",
|
| 1385 |
+
-7.904823960369406
|
| 1386 |
+
],
|
| 1387 |
+
[
|
| 1388 |
+
"▁number",
|
| 1389 |
+
-7.92049657311796
|
| 1390 |
+
],
|
| 1391 |
+
[
|
| 1392 |
+
"ship",
|
| 1393 |
+
-7.923714185081133
|
| 1394 |
+
],
|
| 1395 |
+
[
|
| 1396 |
+
"special",
|
| 1397 |
+
-7.924246082451086
|
| 1398 |
+
],
|
| 1399 |
+
[
|
| 1400 |
+
"▁found",
|
| 1401 |
+
-7.941336564660717
|
| 1402 |
+
],
|
| 1403 |
+
[
|
| 1404 |
+
"▁sea",
|
| 1405 |
+
-7.954838574459147
|
| 1406 |
+
],
|
| 1407 |
+
[
|
| 1408 |
+
"▁again",
|
| 1409 |
+
-7.962674285284644
|
| 1410 |
+
],
|
| 1411 |
+
[
|
| 1412 |
+
"▁learn",
|
| 1413 |
+
-7.962691878072893
|
| 1414 |
+
],
|
| 1415 |
+
[
|
| 1416 |
+
"ember",
|
| 1417 |
+
-7.965884834890247
|
| 1418 |
+
],
|
| 1419 |
+
[
|
| 1420 |
+
"▁vari",
|
| 1421 |
+
-7.96616597834795
|
| 1422 |
+
],
|
| 1423 |
+
[
|
| 1424 |
+
"▁animal",
|
| 1425 |
+
-7.984363992669607
|
| 1426 |
+
],
|
| 1427 |
+
[
|
| 1428 |
+
"▁what",
|
| 1429 |
+
-7.984502416198689
|
| 1430 |
+
],
|
| 1431 |
+
[
|
| 1432 |
+
"▁europe",
|
| 1433 |
+
-8.006567891721467
|
| 1434 |
+
],
|
| 1435 |
+
[
|
| 1436 |
+
"▁200",
|
| 1437 |
+
-8.00660766861835
|
| 1438 |
+
],
|
| 1439 |
+
[
|
| 1440 |
+
"000000",
|
| 1441 |
+
-8.012236019613125
|
| 1442 |
+
],
|
| 1443 |
+
[
|
| 1444 |
+
"mark",
|
| 1445 |
+
-8.01276901828499
|
| 1446 |
+
],
|
| 1447 |
+
[
|
| 1448 |
+
"sure",
|
| 1449 |
+
-8.015138086899906
|
| 1450 |
+
],
|
| 1451 |
+
[
|
| 1452 |
+
"▁adv",
|
| 1453 |
+
-8.023621444584538
|
| 1454 |
+
],
|
| 1455 |
+
[
|
| 1456 |
+
"▁whil",
|
| 1457 |
+
-8.02780271246084
|
| 1458 |
+
],
|
| 1459 |
+
[
|
| 1460 |
+
"▁chi",
|
| 1461 |
+
-8.045482944578183
|
| 1462 |
+
],
|
| 1463 |
+
[
|
| 1464 |
+
"▁buil",
|
| 1465 |
+
-8.052815943522955
|
| 1466 |
+
],
|
| 1467 |
+
[
|
| 1468 |
+
"▁every",
|
| 1469 |
+
-8.056538487431741
|
| 1470 |
+
],
|
| 1471 |
+
[
|
| 1472 |
+
"▁va",
|
| 1473 |
+
-8.06777735608203
|
| 1474 |
+
],
|
| 1475 |
+
[
|
| 1476 |
+
"▁become",
|
| 1477 |
+
-8.076393297026822
|
| 1478 |
+
],
|
| 1479 |
+
[
|
| 1480 |
+
"▁local",
|
| 1481 |
+
-8.076412720519006
|
| 1482 |
+
],
|
| 1483 |
+
[
|
| 1484 |
+
"▁stud",
|
| 1485 |
+
-8.07837962249372
|
| 1486 |
+
],
|
| 1487 |
+
[
|
| 1488 |
+
"▁due",
|
| 1489 |
+
-8.078849866853641
|
| 1490 |
+
],
|
| 1491 |
+
[
|
| 1492 |
+
"▁gree",
|
| 1493 |
+
-8.082887671546896
|
| 1494 |
+
],
|
| 1495 |
+
[
|
| 1496 |
+
"▁centur",
|
| 1497 |
+
-8.100942155064343
|
| 1498 |
+
],
|
| 1499 |
+
[
|
| 1500 |
+
"▁play",
|
| 1501 |
+
-8.101156837441584
|
| 1502 |
+
],
|
| 1503 |
+
[
|
| 1504 |
+
"cross",
|
| 1505 |
+
-8.102046351520748
|
| 1506 |
+
],
|
| 1507 |
+
[
|
| 1508 |
+
"▁government",
|
| 1509 |
+
-8.125750652904102
|
| 1510 |
+
],
|
| 1511 |
+
[
|
| 1512 |
+
"▁system",
|
| 1513 |
+
-8.125751292965452
|
| 1514 |
+
],
|
| 1515 |
+
[
|
| 1516 |
+
"▁point",
|
| 1517 |
+
-8.126694846256854
|
| 1518 |
+
],
|
| 1519 |
+
[
|
| 1520 |
+
"▁trans",
|
| 1521 |
+
-8.128116666544686
|
| 1522 |
+
],
|
| 1523 |
+
[
|
| 1524 |
+
"▁name",
|
| 1525 |
+
-8.13730426679406
|
| 1526 |
+
],
|
| 1527 |
+
[
|
| 1528 |
+
"▁german",
|
| 1529 |
+
-8.151397109598614
|
| 1530 |
+
],
|
| 1531 |
+
[
|
| 1532 |
+
"▁culture",
|
| 1533 |
+
-8.151404168932643
|
| 1534 |
+
],
|
| 1535 |
+
[
|
| 1536 |
+
"▁famil",
|
| 1537 |
+
-8.15169431433106
|
| 1538 |
+
],
|
| 1539 |
+
[
|
| 1540 |
+
"▁histor",
|
| 1541 |
+
-8.151992571385806
|
| 1542 |
+
],
|
| 1543 |
+
[
|
| 1544 |
+
"▁help",
|
| 1545 |
+
-8.152379382465845
|
| 1546 |
+
],
|
| 1547 |
+
[
|
| 1548 |
+
"▁find",
|
| 1549 |
+
-8.15399509736029
|
| 1550 |
+
],
|
| 1551 |
+
[
|
| 1552 |
+
"▁run",
|
| 1553 |
+
-8.15551819933091
|
| 1554 |
+
],
|
| 1555 |
+
[
|
| 1556 |
+
"▁medi",
|
| 1557 |
+
-8.175453324820076
|
| 1558 |
+
],
|
| 1559 |
+
[
|
| 1560 |
+
"▁general",
|
| 1561 |
+
-8.177711046639622
|
| 1562 |
+
],
|
| 1563 |
+
[
|
| 1564 |
+
"▁usual",
|
| 1565 |
+
-8.178143536295165
|
| 1566 |
+
],
|
| 1567 |
+
[
|
| 1568 |
+
"▁lead",
|
| 1569 |
+
-8.17819966076631
|
| 1570 |
+
],
|
| 1571 |
+
[
|
| 1572 |
+
"▁offer",
|
| 1573 |
+
-8.180232661192168
|
| 1574 |
+
],
|
| 1575 |
+
[
|
| 1576 |
+
"came",
|
| 1577 |
+
-8.183643902583706
|
| 1578 |
+
],
|
| 1579 |
+
[
|
| 1580 |
+
"qui",
|
| 1581 |
+
-8.192813528327466
|
| 1582 |
+
],
|
| 1583 |
+
[
|
| 1584 |
+
"imate",
|
| 1585 |
+
-8.204585093979773
|
| 1586 |
+
],
|
| 1587 |
+
[
|
| 1588 |
+
"▁provide",
|
| 1589 |
+
-8.204769066637121
|
| 1590 |
+
],
|
| 1591 |
+
[
|
| 1592 |
+
"▁start",
|
| 1593 |
+
-8.206828802738865
|
| 1594 |
+
],
|
| 1595 |
+
[
|
| 1596 |
+
"▁possibl",
|
| 1597 |
+
-8.23251237309725
|
| 1598 |
+
],
|
| 1599 |
+
[
|
| 1600 |
+
"▁temple",
|
| 1601 |
+
-8.232512443222566
|
| 1602 |
+
],
|
| 1603 |
+
[
|
| 1604 |
+
"▁develop",
|
| 1605 |
+
-8.23251253510426
|
| 1606 |
+
],
|
| 1607 |
+
[
|
| 1608 |
+
"▁before",
|
| 1609 |
+
-8.232542372986714
|
| 1610 |
+
],
|
| 1611 |
+
[
|
| 1612 |
+
"▁sever",
|
| 1613 |
+
-8.233431940537834
|
| 1614 |
+
],
|
| 1615 |
+
[
|
| 1616 |
+
"▁game",
|
| 1617 |
+
-8.234672632014709
|
| 1618 |
+
],
|
| 1619 |
+
[
|
| 1620 |
+
"▁human",
|
| 1621 |
+
-8.261150107977098
|
| 1622 |
+
],
|
| 1623 |
+
[
|
| 1624 |
+
"▁consider",
|
| 1625 |
+
-8.261160080863537
|
| 1626 |
+
],
|
| 1627 |
+
[
|
| 1628 |
+
"▁change",
|
| 1629 |
+
-8.261187464522354
|
| 1630 |
+
],
|
| 1631 |
+
[
|
| 1632 |
+
"▁book",
|
| 1633 |
+
-8.261600372522377
|
| 1634 |
+
],
|
| 1635 |
+
[
|
| 1636 |
+
"▁1000",
|
| 1637 |
+
-8.289718237006165
|
| 1638 |
+
],
|
| 1639 |
+
[
|
| 1640 |
+
"▁tourist",
|
| 1641 |
+
-8.29054215262876
|
| 1642 |
+
],
|
| 1643 |
+
[
|
| 1644 |
+
"▁great",
|
| 1645 |
+
-8.290624738675088
|
| 1646 |
+
],
|
| 1647 |
+
[
|
| 1648 |
+
"▁region",
|
| 1649 |
+
-8.290771793199044
|
| 1650 |
+
],
|
| 1651 |
+
[
|
| 1652 |
+
"▁protest",
|
| 1653 |
+
-8.290809821436957
|
| 1654 |
+
],
|
| 1655 |
+
[
|
| 1656 |
+
"▁limit",
|
| 1657 |
+
-8.290876449378203
|
| 1658 |
+
],
|
| 1659 |
+
[
|
| 1660 |
+
"▁under",
|
| 1661 |
+
-8.291576583902883
|
| 1662 |
+
],
|
| 1663 |
+
[
|
| 1664 |
+
"▁driv",
|
| 1665 |
+
-8.291901980259404
|
| 1666 |
+
],
|
| 1667 |
+
[
|
| 1668 |
+
"▁cru",
|
| 1669 |
+
-8.29526860346621
|
| 1670 |
+
],
|
| 1671 |
+
[
|
| 1672 |
+
"▁relat",
|
| 1673 |
+
-8.315627957281512
|
| 1674 |
+
],
|
| 1675 |
+
[
|
| 1676 |
+
"▁language",
|
| 1677 |
+
-8.320798343228995
|
| 1678 |
+
],
|
| 1679 |
+
[
|
| 1680 |
+
"▁201",
|
| 1681 |
+
-8.320810101005854
|
| 1682 |
+
],
|
| 1683 |
+
[
|
| 1684 |
+
"▁remain",
|
| 1685 |
+
-8.320835267121115
|
| 1686 |
+
],
|
| 1687 |
+
[
|
| 1688 |
+
"▁receive",
|
| 1689 |
+
-8.32087919331787
|
| 1690 |
+
],
|
| 1691 |
+
[
|
| 1692 |
+
"▁team",
|
| 1693 |
+
-8.320905438873691
|
| 1694 |
+
],
|
| 1695 |
+
[
|
| 1696 |
+
"▁close",
|
| 1697 |
+
-8.321788682484456
|
| 1698 |
+
],
|
| 1699 |
+
[
|
| 1700 |
+
"▁follow",
|
| 1701 |
+
-8.352087907661254
|
| 1702 |
+
],
|
| 1703 |
+
[
|
| 1704 |
+
"▁major",
|
| 1705 |
+
-8.352166130913496
|
| 1706 |
+
],
|
| 1707 |
+
[
|
| 1708 |
+
"▁much",
|
| 1709 |
+
-8.352275564219338
|
| 1710 |
+
],
|
| 1711 |
+
[
|
| 1712 |
+
"▁wild",
|
| 1713 |
+
-8.352831893439728
|
| 1714 |
+
],
|
| 1715 |
+
[
|
| 1716 |
+
"ject",
|
| 1717 |
+
-8.352943963542865
|
| 1718 |
+
],
|
| 1719 |
+
[
|
| 1720 |
+
"▁case",
|
| 1721 |
+
-8.354836760378483
|
| 1722 |
+
],
|
| 1723 |
+
[
|
| 1724 |
+
"▁official",
|
| 1725 |
+
-8.384306537193822
|
| 1726 |
+
],
|
| 1727 |
+
[
|
| 1728 |
+
"▁group",
|
| 1729 |
+
-8.384309677325607
|
| 1730 |
+
],
|
| 1731 |
+
[
|
| 1732 |
+
"▁africa",
|
| 1733 |
+
-8.384310670398985
|
| 1734 |
+
],
|
| 1735 |
+
[
|
| 1736 |
+
"▁season",
|
| 1737 |
+
-8.38466131549998
|
| 1738 |
+
],
|
| 1739 |
+
[
|
| 1740 |
+
"▁service",
|
| 1741 |
+
-8.417640029535818
|
| 1742 |
+
],
|
| 1743 |
+
[
|
| 1744 |
+
"▁believe",
|
| 1745 |
+
-8.417644279258813
|
| 1746 |
+
],
|
| 1747 |
+
[
|
| 1748 |
+
"▁look",
|
| 1749 |
+
-8.417696460056247
|
| 1750 |
+
],
|
| 1751 |
+
[
|
| 1752 |
+
"▁camp",
|
| 1753 |
+
-8.4177560776734
|
| 1754 |
+
],
|
| 1755 |
+
[
|
| 1756 |
+
"▁own",
|
| 1757 |
+
-8.417875270619882
|
| 1758 |
+
],
|
| 1759 |
+
[
|
| 1760 |
+
"break",
|
| 1761 |
+
-8.417973529893512
|
| 1762 |
+
],
|
| 1763 |
+
[
|
| 1764 |
+
"▁affect",
|
| 1765 |
+
-8.452123796949778
|
| 1766 |
+
],
|
| 1767 |
+
[
|
| 1768 |
+
"▁sometime",
|
| 1769 |
+
-8.452127443718524
|
| 1770 |
+
],
|
| 1771 |
+
[
|
| 1772 |
+
"▁america",
|
| 1773 |
+
-8.452135735357338
|
| 1774 |
+
],
|
| 1775 |
+
[
|
| 1776 |
+
"▁charge",
|
| 1777 |
+
-8.45219566004275
|
| 1778 |
+
],
|
| 1779 |
+
[
|
| 1780 |
+
"▁understand",
|
| 1781 |
+
-8.452216747124485
|
| 1782 |
+
],
|
| 1783 |
+
[
|
| 1784 |
+
"▁type",
|
| 1785 |
+
-8.452232925203674
|
| 1786 |
+
],
|
| 1787 |
+
[
|
| 1788 |
+
"▁class",
|
| 1789 |
+
-8.452279844492605
|
| 1790 |
+
],
|
| 1791 |
+
[
|
| 1792 |
+
"▁earth",
|
| 1793 |
+
-8.452354317519077
|
| 1794 |
+
],
|
| 1795 |
+
[
|
| 1796 |
+
"▁communi",
|
| 1797 |
+
-8.45314714922437
|
| 1798 |
+
],
|
| 1799 |
+
[
|
| 1800 |
+
"▁locat",
|
| 1801 |
+
-8.458516662039814
|
| 1802 |
+
],
|
| 1803 |
+
[
|
| 1804 |
+
"▁problem",
|
| 1805 |
+
-8.487840831803812
|
| 1806 |
+
],
|
| 1807 |
+
[
|
| 1808 |
+
"▁public",
|
| 1809 |
+
-8.52487386512437
|
| 1810 |
+
],
|
| 1811 |
+
[
|
| 1812 |
+
"▁particular",
|
| 1813 |
+
-8.52487392465013
|
| 1814 |
+
],
|
| 1815 |
+
[
|
| 1816 |
+
"▁success",
|
| 1817 |
+
-8.52487575044468
|
| 1818 |
+
],
|
| 1819 |
+
[
|
| 1820 |
+
"▁popular",
|
| 1821 |
+
-8.563335769640975
|
| 1822 |
+
],
|
| 1823 |
+
[
|
| 1824 |
+
"▁japan",
|
| 1825 |
+
-8.563335928219438
|
| 1826 |
+
],
|
| 1827 |
+
[
|
| 1828 |
+
"▁transport",
|
| 1829 |
+
-8.56333935408694
|
| 1830 |
+
],
|
| 1831 |
+
[
|
| 1832 |
+
"▁snow",
|
| 1833 |
+
-8.563350743467298
|
| 1834 |
+
],
|
| 1835 |
+
[
|
| 1836 |
+
"▁legal",
|
| 1837 |
+
-8.56349422889885
|
| 1838 |
+
],
|
| 1839 |
+
[
|
| 1840 |
+
"company",
|
| 1841 |
+
-8.567823788313378
|
| 1842 |
+
],
|
| 1843 |
+
[
|
| 1844 |
+
"▁australia",
|
| 1845 |
+
-8.603335377698876
|
| 1846 |
+
],
|
| 1847 |
+
[
|
| 1848 |
+
"▁experience",
|
| 1849 |
+
-8.60333543690594
|
| 1850 |
+
],
|
| 1851 |
+
[
|
| 1852 |
+
"▁effect",
|
| 1853 |
+
-8.603335572481557
|
| 1854 |
+
],
|
| 1855 |
+
[
|
| 1856 |
+
"▁expect",
|
| 1857 |
+
-8.603336545491683
|
| 1858 |
+
],
|
| 1859 |
+
[
|
| 1860 |
+
"▁religio",
|
| 1861 |
+
-8.60333719794059
|
| 1862 |
+
],
|
| 1863 |
+
[
|
| 1864 |
+
"▁airline",
|
| 1865 |
+
-8.603337729717676
|
| 1866 |
+
],
|
| 1867 |
+
[
|
| 1868 |
+
"▁food",
|
| 1869 |
+
-8.603423880765625
|
| 1870 |
+
],
|
| 1871 |
+
[
|
| 1872 |
+
"▁process",
|
| 1873 |
+
-8.603434066309912
|
| 1874 |
+
],
|
| 1875 |
+
[
|
| 1876 |
+
"▁franc",
|
| 1877 |
+
-8.607137440189035
|
| 1878 |
+
],
|
| 1879 |
+
[
|
| 1880 |
+
"▁according",
|
| 1881 |
+
-8.645002056827511
|
| 1882 |
+
],
|
| 1883 |
+
[
|
| 1884 |
+
"▁international",
|
| 1885 |
+
-8.645002161206236
|
| 1886 |
+
],
|
| 1887 |
+
[
|
| 1888 |
+
"▁authorit",
|
| 1889 |
+
-8.645002186529833
|
| 1890 |
+
],
|
| 1891 |
+
[
|
| 1892 |
+
"▁econom",
|
| 1893 |
+
-8.645003467085711
|
| 1894 |
+
],
|
| 1895 |
+
[
|
| 1896 |
+
"▁check",
|
| 1897 |
+
-8.645008609181772
|
| 1898 |
+
],
|
| 1899 |
+
[
|
| 1900 |
+
"mission",
|
| 1901 |
+
-8.652738598036581
|
| 1902 |
+
],
|
| 1903 |
+
[
|
| 1904 |
+
"▁olympic",
|
| 1905 |
+
-8.688480321150827
|
| 1906 |
+
],
|
| 1907 |
+
[
|
| 1908 |
+
"▁discover",
|
| 1909 |
+
-8.688481280484586
|
| 1910 |
+
],
|
| 1911 |
+
[
|
| 1912 |
+
"▁direct",
|
| 1913 |
+
-8.68862007392972
|
| 1914 |
+
],
|
| 1915 |
+
[
|
| 1916 |
+
"▁arriv",
|
| 1917 |
+
-8.68883024075118
|
| 1918 |
+
],
|
| 1919 |
+
[
|
| 1920 |
+
"strict",
|
| 1921 |
+
-8.689662128023302
|
| 1922 |
+
],
|
| 1923 |
+
[
|
| 1924 |
+
"%",
|
| 1925 |
+
-8.733934831176956
|
| 1926 |
+
],
|
| 1927 |
+
[
|
| 1928 |
+
"▁window",
|
| 1929 |
+
-8.733935012824286
|
| 1930 |
+
],
|
| 1931 |
+
[
|
| 1932 |
+
"▁support",
|
| 1933 |
+
-8.733935222634948
|
| 1934 |
+
],
|
| 1935 |
+
[
|
| 1936 |
+
"▁document",
|
| 1937 |
+
-8.733936433415515
|
| 1938 |
+
],
|
| 1939 |
+
[
|
| 1940 |
+
"▁school",
|
| 1941 |
+
-8.7339383128885
|
| 1942 |
+
],
|
| 1943 |
+
[
|
| 1944 |
+
"▁univers",
|
| 1945 |
+
-8.733952912966306
|
| 1946 |
+
],
|
| 1947 |
+
[
|
| 1948 |
+
"▁plann",
|
| 1949 |
+
-8.733959359687297
|
| 1950 |
+
],
|
| 1951 |
+
[
|
| 1952 |
+
"▁mountain",
|
| 1953 |
+
-8.781553962524354
|
| 1954 |
+
],
|
| 1955 |
+
[
|
| 1956 |
+
"▁attack",
|
| 1957 |
+
-8.78155483428725
|
| 1958 |
+
],
|
| 1959 |
+
[
|
| 1960 |
+
"▁addition",
|
| 1961 |
+
-8.781556055460403
|
| 1962 |
+
],
|
| 1963 |
+
[
|
| 1964 |
+
"▁education",
|
| 1965 |
+
-8.781556487999397
|
| 1966 |
+
],
|
| 1967 |
+
[
|
| 1968 |
+
"▁crash",
|
| 1969 |
+
-8.781565077101176
|
| 1970 |
+
],
|
| 1971 |
+
[
|
| 1972 |
+
"abilit",
|
| 1973 |
+
-8.782467496776816
|
| 1974 |
+
],
|
| 1975 |
+
[
|
| 1976 |
+
"▁similar",
|
| 1977 |
+
-8.831553958948293
|
| 1978 |
+
],
|
| 1979 |
+
[
|
| 1980 |
+
"▁regular",
|
| 1981 |
+
-8.831555814320183
|
| 1982 |
+
],
|
| 1983 |
+
[
|
| 1984 |
+
"▁involve",
|
| 1985 |
+
-8.831558534910847
|
| 1986 |
+
],
|
| 1987 |
+
[
|
| 1988 |
+
"▁infect",
|
| 1989 |
+
-8.831583753401237
|
| 1990 |
+
],
|
| 1991 |
+
[
|
| 1992 |
+
"▁photo",
|
| 1993 |
+
-8.831590339505494
|
| 1994 |
+
],
|
| 1995 |
+
[
|
| 1996 |
+
"▁establish",
|
| 1997 |
+
-8.884185458496821
|
| 1998 |
+
],
|
| 1999 |
+
[
|
| 2000 |
+
"▁independen",
|
| 2001 |
+
-8.884185473898746
|
| 2002 |
+
],
|
| 2003 |
+
[
|
| 2004 |
+
"▁physical",
|
| 2005 |
+
-8.884185942057826
|
| 2006 |
+
],
|
| 2007 |
+
[
|
| 2008 |
+
"▁current",
|
| 2009 |
+
-8.884189149406275
|
| 2010 |
+
],
|
| 2011 |
+
[
|
| 2012 |
+
"00000",
|
| 2013 |
+
-8.92697290848362
|
| 2014 |
+
],
|
| 2015 |
+
[
|
| 2016 |
+
"▁organization",
|
| 2017 |
+
-8.939741013377946
|
| 2018 |
+
],
|
| 2019 |
+
[
|
| 2020 |
+
"▁behavior",
|
| 2021 |
+
-8.93974101496351
|
| 2022 |
+
],
|
| 2023 |
+
[
|
| 2024 |
+
"▁investigat",
|
| 2025 |
+
-8.9397411668559
|
| 2026 |
+
],
|
| 2027 |
+
[
|
| 2028 |
+
"▁television",
|
| 2029 |
+
-8.998564542859848
|
| 2030 |
+
],
|
| 2031 |
+
[
|
| 2032 |
+
"▁republic",
|
| 2033 |
+
-8.99856454364473
|
| 2034 |
+
],
|
| 2035 |
+
[
|
| 2036 |
+
"▁potential",
|
| 2037 |
+
-8.998564656926455
|
| 2038 |
+
],
|
| 2039 |
+
[
|
| 2040 |
+
"▁example",
|
| 2041 |
+
-8.998564715546378
|
| 2042 |
+
],
|
| 2043 |
+
[
|
| 2044 |
+
"▁original",
|
| 2045 |
+
-8.99856478139713
|
| 2046 |
+
],
|
| 2047 |
+
[
|
| 2048 |
+
"▁population",
|
| 2049 |
+
-8.998564898026078
|
| 2050 |
+
],
|
| 2051 |
+
[
|
| 2052 |
+
"▁happen",
|
| 2053 |
+
-8.998564920034934
|
| 2054 |
+
],
|
| 2055 |
+
[
|
| 2056 |
+
"▁website",
|
| 2057 |
+
-8.998566502024065
|
| 2058 |
+
],
|
| 2059 |
+
[
|
| 2060 |
+
"▁individual",
|
| 2061 |
+
-9.061064542741311
|
| 2062 |
+
],
|
| 2063 |
+
[
|
| 2064 |
+
"▁surviv",
|
| 2065 |
+
-9.061074061068329
|
| 2066 |
+
],
|
| 2067 |
+
[
|
| 2068 |
+
"▁simpl",
|
| 2069 |
+
-9.06108516492456
|
| 2070 |
+
],
|
| 2071 |
+
[
|
| 2072 |
+
"▁neighbor",
|
| 2073 |
+
-9.127731209385104
|
| 2074 |
+
],
|
| 2075 |
+
[
|
| 2076 |
+
"▁observ",
|
| 2077 |
+
-9.12773163177753
|
| 2078 |
+
],
|
| 2079 |
+
[
|
| 2080 |
+
"▁associat",
|
| 2081 |
+
-9.127733727827064
|
| 2082 |
+
],
|
| 2083 |
+
[
|
| 2084 |
+
"▁earthquake",
|
| 2085 |
+
-9.199159780805967
|
| 2086 |
+
],
|
| 2087 |
+
[
|
| 2088 |
+
"$",
|
| 2089 |
+
-9.359416191062518
|
| 2090 |
+
],
|
| 2091 |
+
[
|
| 2092 |
+
".",
|
| 2093 |
+
-9.359416191062522
|
| 2094 |
+
],
|
| 2095 |
+
[
|
| 2096 |
+
"▁network",
|
| 2097 |
+
-9.359416194093198
|
| 2098 |
+
],
|
| 2099 |
+
[
|
| 2100 |
+
"▁agricultur",
|
| 2101 |
+
-9.359428904038964
|
| 2102 |
+
],
|
| 2103 |
+
[
|
| 2104 |
+
"▁geograph",
|
| 2105 |
+
-9.45032528230153
|
| 2106 |
+
],
|
| 2107 |
+
[
|
| 2108 |
+
"▁legislati",
|
| 2109 |
+
-9.450326304956086
|
| 2110 |
+
],
|
| 2111 |
+
[
|
| 2112 |
+
"]",
|
| 2113 |
+
-10.095960202659114
|
| 2114 |
+
],
|
| 2115 |
+
[
|
| 2116 |
+
"[",
|
| 2117 |
+
-10.095960202659116
|
| 2118 |
+
],
|
| 2119 |
+
[
|
| 2120 |
+
"-",
|
| 2121 |
+
-10.295960202619158
|
| 2122 |
+
],
|
| 2123 |
+
[
|
| 2124 |
+
"¢",
|
| 2125 |
+
-11.37929353599245
|
| 2126 |
+
],
|
| 2127 |
+
[
|
| 2128 |
+
"",
|
| 2129 |
+
-11.37929353599245
|
| 2130 |
+
],
|
| 2131 |
+
[
|
| 2132 |
+
"£",
|
| 2133 |
+
-12.378993535952503
|
| 2134 |
+
],
|
| 2135 |
+
[
|
| 2136 |
+
"q",
|
| 2137 |
+
-12.379093535952505
|
| 2138 |
+
],
|
| 2139 |
+
[
|
| 2140 |
+
")",
|
| 2141 |
+
-12.379193535952504
|
| 2142 |
+
],
|
| 2143 |
+
[
|
| 2144 |
+
"(",
|
| 2145 |
+
-12.379293535952502
|
| 2146 |
+
],
|
| 2147 |
+
[
|
| 2148 |
+
"€",
|
| 2149 |
+
-12.379293535952502
|
| 2150 |
+
]
|
| 2151 |
+
]
|
| 2152 |
+
}
|
| 2153 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "([bos])",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "([eos])",
|
| 5 |
+
"mask_token": "([mask])",
|
| 6 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
+
"pad_token": "([pad])",
|
| 8 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 9 |
+
"unk_token": "([unk])"
|
| 10 |
+
}
|