Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +3768 -6
tokenizer_config.json
CHANGED
@@ -26,6 +26,3350 @@
|
|
26 |
"special": true
|
27 |
},
|
28 |
"151646": {
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
29 |
"content": "<im_start>",
|
30 |
"lstrip": false,
|
31 |
"normalized": false,
|
@@ -33,7 +3377,7 @@
|
|
33 |
"single_word": false,
|
34 |
"special": true
|
35 |
},
|
36 |
-
"
|
37 |
"content": "<im_end>",
|
38 |
"lstrip": false,
|
39 |
"normalized": false,
|
@@ -41,7 +3385,7 @@
|
|
41 |
"single_word": false,
|
42 |
"special": true
|
43 |
},
|
44 |
-
"
|
45 |
"content": "<im_patch>",
|
46 |
"lstrip": false,
|
47 |
"normalized": false,
|
@@ -49,7 +3393,7 @@
|
|
49 |
"single_word": false,
|
50 |
"special": true
|
51 |
},
|
52 |
-
"
|
53 |
"content": "<im_col>",
|
54 |
"lstrip": false,
|
55 |
"normalized": false,
|
@@ -57,7 +3401,7 @@
|
|
57 |
"single_word": false,
|
58 |
"special": true
|
59 |
},
|
60 |
-
"
|
61 |
"content": "<|image|>",
|
62 |
"lstrip": false,
|
63 |
"normalized": false,
|
@@ -67,6 +3411,424 @@
|
|
67 |
}
|
68 |
},
|
69 |
"additional_special_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
"<im_start>",
|
71 |
"<im_end>",
|
72 |
"<im_patch>",
|
@@ -77,11 +3839,11 @@
|
|
77 |
"AutoProcessor": "preprocessing_molmo.MolmoProcessor"
|
78 |
},
|
79 |
"bos_token": null,
|
80 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant
|
81 |
"clean_up_tokenization_spaces": false,
|
82 |
"eos_token": "<|endoftext|>",
|
83 |
"errors": "replace",
|
84 |
-
"model_max_length":
|
85 |
"pad_token": "<|endoftext|>",
|
86 |
"processor_class": "MolmoProcessor",
|
87 |
"split_special_tokens": false,
|
|
|
26 |
"special": true
|
27 |
},
|
28 |
"151646": {
|
29 |
+
"content": "|<EXTRA_TOKENS_0>|",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"151647": {
|
37 |
+
"content": "|<EXTRA_TOKENS_1>|",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
},
|
44 |
+
"151648": {
|
45 |
+
"content": "|<EXTRA_TOKENS_2>|",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": false,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": true
|
51 |
+
},
|
52 |
+
"151649": {
|
53 |
+
"content": "|<EXTRA_TOKENS_3>|",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": false,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": true
|
59 |
+
},
|
60 |
+
"151650": {
|
61 |
+
"content": "|<EXTRA_TOKENS_4>|",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": false,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": true
|
67 |
+
},
|
68 |
+
"151651": {
|
69 |
+
"content": "|<EXTRA_TOKENS_5>|",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": false,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": true
|
75 |
+
},
|
76 |
+
"151652": {
|
77 |
+
"content": "|<EXTRA_TOKENS_6>|",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": false,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": true
|
83 |
+
},
|
84 |
+
"151653": {
|
85 |
+
"content": "|<EXTRA_TOKENS_7>|",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": false,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": true
|
91 |
+
},
|
92 |
+
"151654": {
|
93 |
+
"content": "|<EXTRA_TOKENS_8>|",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": false,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": true
|
99 |
+
},
|
100 |
+
"151655": {
|
101 |
+
"content": "|<EXTRA_TOKENS_9>|",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": false,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": true
|
107 |
+
},
|
108 |
+
"151656": {
|
109 |
+
"content": "|<EXTRA_TOKENS_10>|",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": false,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": true
|
115 |
+
},
|
116 |
+
"151657": {
|
117 |
+
"content": "|<EXTRA_TOKENS_11>|",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": false,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": true
|
123 |
+
},
|
124 |
+
"151658": {
|
125 |
+
"content": "|<EXTRA_TOKENS_12>|",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": false,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": true
|
131 |
+
},
|
132 |
+
"151659": {
|
133 |
+
"content": "|<EXTRA_TOKENS_13>|",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": false,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": true
|
139 |
+
},
|
140 |
+
"151660": {
|
141 |
+
"content": "|<EXTRA_TOKENS_14>|",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": false,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": true
|
147 |
+
},
|
148 |
+
"151661": {
|
149 |
+
"content": "|<EXTRA_TOKENS_15>|",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": false,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": true
|
155 |
+
},
|
156 |
+
"151662": {
|
157 |
+
"content": "|<EXTRA_TOKENS_16>|",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": false,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": true
|
163 |
+
},
|
164 |
+
"151663": {
|
165 |
+
"content": "|<EXTRA_TOKENS_17>|",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": false,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": true
|
171 |
+
},
|
172 |
+
"151664": {
|
173 |
+
"content": "|<EXTRA_TOKENS_18>|",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": false,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": true
|
179 |
+
},
|
180 |
+
"151665": {
|
181 |
+
"content": "|<EXTRA_TOKENS_19>|",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": false,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": true
|
187 |
+
},
|
188 |
+
"151666": {
|
189 |
+
"content": "|<EXTRA_TOKENS_20>|",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": false,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": true
|
195 |
+
},
|
196 |
+
"151667": {
|
197 |
+
"content": "|<EXTRA_TOKENS_21>|",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": false,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": true
|
203 |
+
},
|
204 |
+
"151668": {
|
205 |
+
"content": "|<EXTRA_TOKENS_22>|",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": false,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": true
|
211 |
+
},
|
212 |
+
"151669": {
|
213 |
+
"content": "|<EXTRA_TOKENS_23>|",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": false,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": true
|
219 |
+
},
|
220 |
+
"151670": {
|
221 |
+
"content": "|<EXTRA_TOKENS_24>|",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": false,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": true
|
227 |
+
},
|
228 |
+
"151671": {
|
229 |
+
"content": "|<EXTRA_TOKENS_25>|",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": false,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": true
|
235 |
+
},
|
236 |
+
"151672": {
|
237 |
+
"content": "|<EXTRA_TOKENS_26>|",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": false,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": true
|
243 |
+
},
|
244 |
+
"151673": {
|
245 |
+
"content": "|<EXTRA_TOKENS_27>|",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": false,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": true
|
251 |
+
},
|
252 |
+
"151674": {
|
253 |
+
"content": "|<EXTRA_TOKENS_28>|",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": false,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": true
|
259 |
+
},
|
260 |
+
"151675": {
|
261 |
+
"content": "|<EXTRA_TOKENS_29>|",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": false,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": true
|
267 |
+
},
|
268 |
+
"151676": {
|
269 |
+
"content": "|<EXTRA_TOKENS_30>|",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": false,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": true
|
275 |
+
},
|
276 |
+
"151677": {
|
277 |
+
"content": "|<EXTRA_TOKENS_31>|",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": false,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": true
|
283 |
+
},
|
284 |
+
"151678": {
|
285 |
+
"content": "|<EXTRA_TOKENS_32>|",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": false,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": true
|
291 |
+
},
|
292 |
+
"151679": {
|
293 |
+
"content": "|<EXTRA_TOKENS_33>|",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": false,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": true
|
299 |
+
},
|
300 |
+
"151680": {
|
301 |
+
"content": "|<EXTRA_TOKENS_34>|",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": false,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": true
|
307 |
+
},
|
308 |
+
"151681": {
|
309 |
+
"content": "|<EXTRA_TOKENS_35>|",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": false,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": true
|
315 |
+
},
|
316 |
+
"151682": {
|
317 |
+
"content": "|<EXTRA_TOKENS_36>|",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"151683": {
|
325 |
+
"content": "|<EXTRA_TOKENS_37>|",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
},
|
332 |
+
"151684": {
|
333 |
+
"content": "|<EXTRA_TOKENS_38>|",
|
334 |
+
"lstrip": false,
|
335 |
+
"normalized": false,
|
336 |
+
"rstrip": false,
|
337 |
+
"single_word": false,
|
338 |
+
"special": true
|
339 |
+
},
|
340 |
+
"151685": {
|
341 |
+
"content": "|<EXTRA_TOKENS_39>|",
|
342 |
+
"lstrip": false,
|
343 |
+
"normalized": false,
|
344 |
+
"rstrip": false,
|
345 |
+
"single_word": false,
|
346 |
+
"special": true
|
347 |
+
},
|
348 |
+
"151686": {
|
349 |
+
"content": "|<EXTRA_TOKENS_40>|",
|
350 |
+
"lstrip": false,
|
351 |
+
"normalized": false,
|
352 |
+
"rstrip": false,
|
353 |
+
"single_word": false,
|
354 |
+
"special": true
|
355 |
+
},
|
356 |
+
"151687": {
|
357 |
+
"content": "|<EXTRA_TOKENS_41>|",
|
358 |
+
"lstrip": false,
|
359 |
+
"normalized": false,
|
360 |
+
"rstrip": false,
|
361 |
+
"single_word": false,
|
362 |
+
"special": true
|
363 |
+
},
|
364 |
+
"151688": {
|
365 |
+
"content": "|<EXTRA_TOKENS_42>|",
|
366 |
+
"lstrip": false,
|
367 |
+
"normalized": false,
|
368 |
+
"rstrip": false,
|
369 |
+
"single_word": false,
|
370 |
+
"special": true
|
371 |
+
},
|
372 |
+
"151689": {
|
373 |
+
"content": "|<EXTRA_TOKENS_43>|",
|
374 |
+
"lstrip": false,
|
375 |
+
"normalized": false,
|
376 |
+
"rstrip": false,
|
377 |
+
"single_word": false,
|
378 |
+
"special": true
|
379 |
+
},
|
380 |
+
"151690": {
|
381 |
+
"content": "|<EXTRA_TOKENS_44>|",
|
382 |
+
"lstrip": false,
|
383 |
+
"normalized": false,
|
384 |
+
"rstrip": false,
|
385 |
+
"single_word": false,
|
386 |
+
"special": true
|
387 |
+
},
|
388 |
+
"151691": {
|
389 |
+
"content": "|<EXTRA_TOKENS_45>|",
|
390 |
+
"lstrip": false,
|
391 |
+
"normalized": false,
|
392 |
+
"rstrip": false,
|
393 |
+
"single_word": false,
|
394 |
+
"special": true
|
395 |
+
},
|
396 |
+
"151692": {
|
397 |
+
"content": "|<EXTRA_TOKENS_46>|",
|
398 |
+
"lstrip": false,
|
399 |
+
"normalized": false,
|
400 |
+
"rstrip": false,
|
401 |
+
"single_word": false,
|
402 |
+
"special": true
|
403 |
+
},
|
404 |
+
"151693": {
|
405 |
+
"content": "|<EXTRA_TOKENS_47>|",
|
406 |
+
"lstrip": false,
|
407 |
+
"normalized": false,
|
408 |
+
"rstrip": false,
|
409 |
+
"single_word": false,
|
410 |
+
"special": true
|
411 |
+
},
|
412 |
+
"151694": {
|
413 |
+
"content": "|<EXTRA_TOKENS_48>|",
|
414 |
+
"lstrip": false,
|
415 |
+
"normalized": false,
|
416 |
+
"rstrip": false,
|
417 |
+
"single_word": false,
|
418 |
+
"special": true
|
419 |
+
},
|
420 |
+
"151695": {
|
421 |
+
"content": "|<EXTRA_TOKENS_49>|",
|
422 |
+
"lstrip": false,
|
423 |
+
"normalized": false,
|
424 |
+
"rstrip": false,
|
425 |
+
"single_word": false,
|
426 |
+
"special": true
|
427 |
+
},
|
428 |
+
"151696": {
|
429 |
+
"content": "|<EXTRA_TOKENS_50>|",
|
430 |
+
"lstrip": false,
|
431 |
+
"normalized": false,
|
432 |
+
"rstrip": false,
|
433 |
+
"single_word": false,
|
434 |
+
"special": true
|
435 |
+
},
|
436 |
+
"151697": {
|
437 |
+
"content": "|<EXTRA_TOKENS_51>|",
|
438 |
+
"lstrip": false,
|
439 |
+
"normalized": false,
|
440 |
+
"rstrip": false,
|
441 |
+
"single_word": false,
|
442 |
+
"special": true
|
443 |
+
},
|
444 |
+
"151698": {
|
445 |
+
"content": "|<EXTRA_TOKENS_52>|",
|
446 |
+
"lstrip": false,
|
447 |
+
"normalized": false,
|
448 |
+
"rstrip": false,
|
449 |
+
"single_word": false,
|
450 |
+
"special": true
|
451 |
+
},
|
452 |
+
"151699": {
|
453 |
+
"content": "|<EXTRA_TOKENS_53>|",
|
454 |
+
"lstrip": false,
|
455 |
+
"normalized": false,
|
456 |
+
"rstrip": false,
|
457 |
+
"single_word": false,
|
458 |
+
"special": true
|
459 |
+
},
|
460 |
+
"151700": {
|
461 |
+
"content": "|<EXTRA_TOKENS_54>|",
|
462 |
+
"lstrip": false,
|
463 |
+
"normalized": false,
|
464 |
+
"rstrip": false,
|
465 |
+
"single_word": false,
|
466 |
+
"special": true
|
467 |
+
},
|
468 |
+
"151701": {
|
469 |
+
"content": "|<EXTRA_TOKENS_55>|",
|
470 |
+
"lstrip": false,
|
471 |
+
"normalized": false,
|
472 |
+
"rstrip": false,
|
473 |
+
"single_word": false,
|
474 |
+
"special": true
|
475 |
+
},
|
476 |
+
"151702": {
|
477 |
+
"content": "|<EXTRA_TOKENS_56>|",
|
478 |
+
"lstrip": false,
|
479 |
+
"normalized": false,
|
480 |
+
"rstrip": false,
|
481 |
+
"single_word": false,
|
482 |
+
"special": true
|
483 |
+
},
|
484 |
+
"151703": {
|
485 |
+
"content": "|<EXTRA_TOKENS_57>|",
|
486 |
+
"lstrip": false,
|
487 |
+
"normalized": false,
|
488 |
+
"rstrip": false,
|
489 |
+
"single_word": false,
|
490 |
+
"special": true
|
491 |
+
},
|
492 |
+
"151704": {
|
493 |
+
"content": "|<EXTRA_TOKENS_58>|",
|
494 |
+
"lstrip": false,
|
495 |
+
"normalized": false,
|
496 |
+
"rstrip": false,
|
497 |
+
"single_word": false,
|
498 |
+
"special": true
|
499 |
+
},
|
500 |
+
"151705": {
|
501 |
+
"content": "|<EXTRA_TOKENS_59>|",
|
502 |
+
"lstrip": false,
|
503 |
+
"normalized": false,
|
504 |
+
"rstrip": false,
|
505 |
+
"single_word": false,
|
506 |
+
"special": true
|
507 |
+
},
|
508 |
+
"151706": {
|
509 |
+
"content": "|<EXTRA_TOKENS_60>|",
|
510 |
+
"lstrip": false,
|
511 |
+
"normalized": false,
|
512 |
+
"rstrip": false,
|
513 |
+
"single_word": false,
|
514 |
+
"special": true
|
515 |
+
},
|
516 |
+
"151707": {
|
517 |
+
"content": "|<EXTRA_TOKENS_61>|",
|
518 |
+
"lstrip": false,
|
519 |
+
"normalized": false,
|
520 |
+
"rstrip": false,
|
521 |
+
"single_word": false,
|
522 |
+
"special": true
|
523 |
+
},
|
524 |
+
"151708": {
|
525 |
+
"content": "|<EXTRA_TOKENS_62>|",
|
526 |
+
"lstrip": false,
|
527 |
+
"normalized": false,
|
528 |
+
"rstrip": false,
|
529 |
+
"single_word": false,
|
530 |
+
"special": true
|
531 |
+
},
|
532 |
+
"151709": {
|
533 |
+
"content": "|<EXTRA_TOKENS_63>|",
|
534 |
+
"lstrip": false,
|
535 |
+
"normalized": false,
|
536 |
+
"rstrip": false,
|
537 |
+
"single_word": false,
|
538 |
+
"special": true
|
539 |
+
},
|
540 |
+
"151710": {
|
541 |
+
"content": "|<EXTRA_TOKENS_64>|",
|
542 |
+
"lstrip": false,
|
543 |
+
"normalized": false,
|
544 |
+
"rstrip": false,
|
545 |
+
"single_word": false,
|
546 |
+
"special": true
|
547 |
+
},
|
548 |
+
"151711": {
|
549 |
+
"content": "|<EXTRA_TOKENS_65>|",
|
550 |
+
"lstrip": false,
|
551 |
+
"normalized": false,
|
552 |
+
"rstrip": false,
|
553 |
+
"single_word": false,
|
554 |
+
"special": true
|
555 |
+
},
|
556 |
+
"151712": {
|
557 |
+
"content": "|<EXTRA_TOKENS_66>|",
|
558 |
+
"lstrip": false,
|
559 |
+
"normalized": false,
|
560 |
+
"rstrip": false,
|
561 |
+
"single_word": false,
|
562 |
+
"special": true
|
563 |
+
},
|
564 |
+
"151713": {
|
565 |
+
"content": "|<EXTRA_TOKENS_67>|",
|
566 |
+
"lstrip": false,
|
567 |
+
"normalized": false,
|
568 |
+
"rstrip": false,
|
569 |
+
"single_word": false,
|
570 |
+
"special": true
|
571 |
+
},
|
572 |
+
"151714": {
|
573 |
+
"content": "|<EXTRA_TOKENS_68>|",
|
574 |
+
"lstrip": false,
|
575 |
+
"normalized": false,
|
576 |
+
"rstrip": false,
|
577 |
+
"single_word": false,
|
578 |
+
"special": true
|
579 |
+
},
|
580 |
+
"151715": {
|
581 |
+
"content": "|<EXTRA_TOKENS_69>|",
|
582 |
+
"lstrip": false,
|
583 |
+
"normalized": false,
|
584 |
+
"rstrip": false,
|
585 |
+
"single_word": false,
|
586 |
+
"special": true
|
587 |
+
},
|
588 |
+
"151716": {
|
589 |
+
"content": "|<EXTRA_TOKENS_70>|",
|
590 |
+
"lstrip": false,
|
591 |
+
"normalized": false,
|
592 |
+
"rstrip": false,
|
593 |
+
"single_word": false,
|
594 |
+
"special": true
|
595 |
+
},
|
596 |
+
"151717": {
|
597 |
+
"content": "|<EXTRA_TOKENS_71>|",
|
598 |
+
"lstrip": false,
|
599 |
+
"normalized": false,
|
600 |
+
"rstrip": false,
|
601 |
+
"single_word": false,
|
602 |
+
"special": true
|
603 |
+
},
|
604 |
+
"151718": {
|
605 |
+
"content": "|<EXTRA_TOKENS_72>|",
|
606 |
+
"lstrip": false,
|
607 |
+
"normalized": false,
|
608 |
+
"rstrip": false,
|
609 |
+
"single_word": false,
|
610 |
+
"special": true
|
611 |
+
},
|
612 |
+
"151719": {
|
613 |
+
"content": "|<EXTRA_TOKENS_73>|",
|
614 |
+
"lstrip": false,
|
615 |
+
"normalized": false,
|
616 |
+
"rstrip": false,
|
617 |
+
"single_word": false,
|
618 |
+
"special": true
|
619 |
+
},
|
620 |
+
"151720": {
|
621 |
+
"content": "|<EXTRA_TOKENS_74>|",
|
622 |
+
"lstrip": false,
|
623 |
+
"normalized": false,
|
624 |
+
"rstrip": false,
|
625 |
+
"single_word": false,
|
626 |
+
"special": true
|
627 |
+
},
|
628 |
+
"151721": {
|
629 |
+
"content": "|<EXTRA_TOKENS_75>|",
|
630 |
+
"lstrip": false,
|
631 |
+
"normalized": false,
|
632 |
+
"rstrip": false,
|
633 |
+
"single_word": false,
|
634 |
+
"special": true
|
635 |
+
},
|
636 |
+
"151722": {
|
637 |
+
"content": "|<EXTRA_TOKENS_76>|",
|
638 |
+
"lstrip": false,
|
639 |
+
"normalized": false,
|
640 |
+
"rstrip": false,
|
641 |
+
"single_word": false,
|
642 |
+
"special": true
|
643 |
+
},
|
644 |
+
"151723": {
|
645 |
+
"content": "|<EXTRA_TOKENS_77>|",
|
646 |
+
"lstrip": false,
|
647 |
+
"normalized": false,
|
648 |
+
"rstrip": false,
|
649 |
+
"single_word": false,
|
650 |
+
"special": true
|
651 |
+
},
|
652 |
+
"151724": {
|
653 |
+
"content": "|<EXTRA_TOKENS_78>|",
|
654 |
+
"lstrip": false,
|
655 |
+
"normalized": false,
|
656 |
+
"rstrip": false,
|
657 |
+
"single_word": false,
|
658 |
+
"special": true
|
659 |
+
},
|
660 |
+
"151725": {
|
661 |
+
"content": "|<EXTRA_TOKENS_79>|",
|
662 |
+
"lstrip": false,
|
663 |
+
"normalized": false,
|
664 |
+
"rstrip": false,
|
665 |
+
"single_word": false,
|
666 |
+
"special": true
|
667 |
+
},
|
668 |
+
"151726": {
|
669 |
+
"content": "|<EXTRA_TOKENS_80>|",
|
670 |
+
"lstrip": false,
|
671 |
+
"normalized": false,
|
672 |
+
"rstrip": false,
|
673 |
+
"single_word": false,
|
674 |
+
"special": true
|
675 |
+
},
|
676 |
+
"151727": {
|
677 |
+
"content": "|<EXTRA_TOKENS_81>|",
|
678 |
+
"lstrip": false,
|
679 |
+
"normalized": false,
|
680 |
+
"rstrip": false,
|
681 |
+
"single_word": false,
|
682 |
+
"special": true
|
683 |
+
},
|
684 |
+
"151728": {
|
685 |
+
"content": "|<EXTRA_TOKENS_82>|",
|
686 |
+
"lstrip": false,
|
687 |
+
"normalized": false,
|
688 |
+
"rstrip": false,
|
689 |
+
"single_word": false,
|
690 |
+
"special": true
|
691 |
+
},
|
692 |
+
"151729": {
|
693 |
+
"content": "|<EXTRA_TOKENS_83>|",
|
694 |
+
"lstrip": false,
|
695 |
+
"normalized": false,
|
696 |
+
"rstrip": false,
|
697 |
+
"single_word": false,
|
698 |
+
"special": true
|
699 |
+
},
|
700 |
+
"151730": {
|
701 |
+
"content": "|<EXTRA_TOKENS_84>|",
|
702 |
+
"lstrip": false,
|
703 |
+
"normalized": false,
|
704 |
+
"rstrip": false,
|
705 |
+
"single_word": false,
|
706 |
+
"special": true
|
707 |
+
},
|
708 |
+
"151731": {
|
709 |
+
"content": "|<EXTRA_TOKENS_85>|",
|
710 |
+
"lstrip": false,
|
711 |
+
"normalized": false,
|
712 |
+
"rstrip": false,
|
713 |
+
"single_word": false,
|
714 |
+
"special": true
|
715 |
+
},
|
716 |
+
"151732": {
|
717 |
+
"content": "|<EXTRA_TOKENS_86>|",
|
718 |
+
"lstrip": false,
|
719 |
+
"normalized": false,
|
720 |
+
"rstrip": false,
|
721 |
+
"single_word": false,
|
722 |
+
"special": true
|
723 |
+
},
|
724 |
+
"151733": {
|
725 |
+
"content": "|<EXTRA_TOKENS_87>|",
|
726 |
+
"lstrip": false,
|
727 |
+
"normalized": false,
|
728 |
+
"rstrip": false,
|
729 |
+
"single_word": false,
|
730 |
+
"special": true
|
731 |
+
},
|
732 |
+
"151734": {
|
733 |
+
"content": "|<EXTRA_TOKENS_88>|",
|
734 |
+
"lstrip": false,
|
735 |
+
"normalized": false,
|
736 |
+
"rstrip": false,
|
737 |
+
"single_word": false,
|
738 |
+
"special": true
|
739 |
+
},
|
740 |
+
"151735": {
|
741 |
+
"content": "|<EXTRA_TOKENS_89>|",
|
742 |
+
"lstrip": false,
|
743 |
+
"normalized": false,
|
744 |
+
"rstrip": false,
|
745 |
+
"single_word": false,
|
746 |
+
"special": true
|
747 |
+
},
|
748 |
+
"151736": {
|
749 |
+
"content": "|<EXTRA_TOKENS_90>|",
|
750 |
+
"lstrip": false,
|
751 |
+
"normalized": false,
|
752 |
+
"rstrip": false,
|
753 |
+
"single_word": false,
|
754 |
+
"special": true
|
755 |
+
},
|
756 |
+
"151737": {
|
757 |
+
"content": "|<EXTRA_TOKENS_91>|",
|
758 |
+
"lstrip": false,
|
759 |
+
"normalized": false,
|
760 |
+
"rstrip": false,
|
761 |
+
"single_word": false,
|
762 |
+
"special": true
|
763 |
+
},
|
764 |
+
"151738": {
|
765 |
+
"content": "|<EXTRA_TOKENS_92>|",
|
766 |
+
"lstrip": false,
|
767 |
+
"normalized": false,
|
768 |
+
"rstrip": false,
|
769 |
+
"single_word": false,
|
770 |
+
"special": true
|
771 |
+
},
|
772 |
+
"151739": {
|
773 |
+
"content": "|<EXTRA_TOKENS_93>|",
|
774 |
+
"lstrip": false,
|
775 |
+
"normalized": false,
|
776 |
+
"rstrip": false,
|
777 |
+
"single_word": false,
|
778 |
+
"special": true
|
779 |
+
},
|
780 |
+
"151740": {
|
781 |
+
"content": "|<EXTRA_TOKENS_94>|",
|
782 |
+
"lstrip": false,
|
783 |
+
"normalized": false,
|
784 |
+
"rstrip": false,
|
785 |
+
"single_word": false,
|
786 |
+
"special": true
|
787 |
+
},
|
788 |
+
"151741": {
|
789 |
+
"content": "|<EXTRA_TOKENS_95>|",
|
790 |
+
"lstrip": false,
|
791 |
+
"normalized": false,
|
792 |
+
"rstrip": false,
|
793 |
+
"single_word": false,
|
794 |
+
"special": true
|
795 |
+
},
|
796 |
+
"151742": {
|
797 |
+
"content": "|<EXTRA_TOKENS_96>|",
|
798 |
+
"lstrip": false,
|
799 |
+
"normalized": false,
|
800 |
+
"rstrip": false,
|
801 |
+
"single_word": false,
|
802 |
+
"special": true
|
803 |
+
},
|
804 |
+
"151743": {
|
805 |
+
"content": "|<EXTRA_TOKENS_97>|",
|
806 |
+
"lstrip": false,
|
807 |
+
"normalized": false,
|
808 |
+
"rstrip": false,
|
809 |
+
"single_word": false,
|
810 |
+
"special": true
|
811 |
+
},
|
812 |
+
"151744": {
|
813 |
+
"content": "|<EXTRA_TOKENS_98>|",
|
814 |
+
"lstrip": false,
|
815 |
+
"normalized": false,
|
816 |
+
"rstrip": false,
|
817 |
+
"single_word": false,
|
818 |
+
"special": true
|
819 |
+
},
|
820 |
+
"151745": {
|
821 |
+
"content": "|<EXTRA_TOKENS_99>|",
|
822 |
+
"lstrip": false,
|
823 |
+
"normalized": false,
|
824 |
+
"rstrip": false,
|
825 |
+
"single_word": false,
|
826 |
+
"special": true
|
827 |
+
},
|
828 |
+
"151746": {
|
829 |
+
"content": "|<EXTRA_TOKENS_100>|",
|
830 |
+
"lstrip": false,
|
831 |
+
"normalized": false,
|
832 |
+
"rstrip": false,
|
833 |
+
"single_word": false,
|
834 |
+
"special": true
|
835 |
+
},
|
836 |
+
"151747": {
|
837 |
+
"content": "|<EXTRA_TOKENS_101>|",
|
838 |
+
"lstrip": false,
|
839 |
+
"normalized": false,
|
840 |
+
"rstrip": false,
|
841 |
+
"single_word": false,
|
842 |
+
"special": true
|
843 |
+
},
|
844 |
+
"151748": {
|
845 |
+
"content": "|<EXTRA_TOKENS_102>|",
|
846 |
+
"lstrip": false,
|
847 |
+
"normalized": false,
|
848 |
+
"rstrip": false,
|
849 |
+
"single_word": false,
|
850 |
+
"special": true
|
851 |
+
},
|
852 |
+
"151749": {
|
853 |
+
"content": "|<EXTRA_TOKENS_103>|",
|
854 |
+
"lstrip": false,
|
855 |
+
"normalized": false,
|
856 |
+
"rstrip": false,
|
857 |
+
"single_word": false,
|
858 |
+
"special": true
|
859 |
+
},
|
860 |
+
"151750": {
|
861 |
+
"content": "|<EXTRA_TOKENS_104>|",
|
862 |
+
"lstrip": false,
|
863 |
+
"normalized": false,
|
864 |
+
"rstrip": false,
|
865 |
+
"single_word": false,
|
866 |
+
"special": true
|
867 |
+
},
|
868 |
+
"151751": {
|
869 |
+
"content": "|<EXTRA_TOKENS_105>|",
|
870 |
+
"lstrip": false,
|
871 |
+
"normalized": false,
|
872 |
+
"rstrip": false,
|
873 |
+
"single_word": false,
|
874 |
+
"special": true
|
875 |
+
},
|
876 |
+
"151752": {
|
877 |
+
"content": "|<EXTRA_TOKENS_106>|",
|
878 |
+
"lstrip": false,
|
879 |
+
"normalized": false,
|
880 |
+
"rstrip": false,
|
881 |
+
"single_word": false,
|
882 |
+
"special": true
|
883 |
+
},
|
884 |
+
"151753": {
|
885 |
+
"content": "|<EXTRA_TOKENS_107>|",
|
886 |
+
"lstrip": false,
|
887 |
+
"normalized": false,
|
888 |
+
"rstrip": false,
|
889 |
+
"single_word": false,
|
890 |
+
"special": true
|
891 |
+
},
|
892 |
+
"151754": {
|
893 |
+
"content": "|<EXTRA_TOKENS_108>|",
|
894 |
+
"lstrip": false,
|
895 |
+
"normalized": false,
|
896 |
+
"rstrip": false,
|
897 |
+
"single_word": false,
|
898 |
+
"special": true
|
899 |
+
},
|
900 |
+
"151755": {
|
901 |
+
"content": "|<EXTRA_TOKENS_109>|",
|
902 |
+
"lstrip": false,
|
903 |
+
"normalized": false,
|
904 |
+
"rstrip": false,
|
905 |
+
"single_word": false,
|
906 |
+
"special": true
|
907 |
+
},
|
908 |
+
"151756": {
|
909 |
+
"content": "|<EXTRA_TOKENS_110>|",
|
910 |
+
"lstrip": false,
|
911 |
+
"normalized": false,
|
912 |
+
"rstrip": false,
|
913 |
+
"single_word": false,
|
914 |
+
"special": true
|
915 |
+
},
|
916 |
+
"151757": {
|
917 |
+
"content": "|<EXTRA_TOKENS_111>|",
|
918 |
+
"lstrip": false,
|
919 |
+
"normalized": false,
|
920 |
+
"rstrip": false,
|
921 |
+
"single_word": false,
|
922 |
+
"special": true
|
923 |
+
},
|
924 |
+
"151758": {
|
925 |
+
"content": "|<EXTRA_TOKENS_112>|",
|
926 |
+
"lstrip": false,
|
927 |
+
"normalized": false,
|
928 |
+
"rstrip": false,
|
929 |
+
"single_word": false,
|
930 |
+
"special": true
|
931 |
+
},
|
932 |
+
"151759": {
|
933 |
+
"content": "|<EXTRA_TOKENS_113>|",
|
934 |
+
"lstrip": false,
|
935 |
+
"normalized": false,
|
936 |
+
"rstrip": false,
|
937 |
+
"single_word": false,
|
938 |
+
"special": true
|
939 |
+
},
|
940 |
+
"151760": {
|
941 |
+
"content": "|<EXTRA_TOKENS_114>|",
|
942 |
+
"lstrip": false,
|
943 |
+
"normalized": false,
|
944 |
+
"rstrip": false,
|
945 |
+
"single_word": false,
|
946 |
+
"special": true
|
947 |
+
},
|
948 |
+
"151761": {
|
949 |
+
"content": "|<EXTRA_TOKENS_115>|",
|
950 |
+
"lstrip": false,
|
951 |
+
"normalized": false,
|
952 |
+
"rstrip": false,
|
953 |
+
"single_word": false,
|
954 |
+
"special": true
|
955 |
+
},
|
956 |
+
"151762": {
|
957 |
+
"content": "|<EXTRA_TOKENS_116>|",
|
958 |
+
"lstrip": false,
|
959 |
+
"normalized": false,
|
960 |
+
"rstrip": false,
|
961 |
+
"single_word": false,
|
962 |
+
"special": true
|
963 |
+
},
|
964 |
+
"151763": {
|
965 |
+
"content": "|<EXTRA_TOKENS_117>|",
|
966 |
+
"lstrip": false,
|
967 |
+
"normalized": false,
|
968 |
+
"rstrip": false,
|
969 |
+
"single_word": false,
|
970 |
+
"special": true
|
971 |
+
},
|
972 |
+
"151764": {
|
973 |
+
"content": "|<EXTRA_TOKENS_118>|",
|
974 |
+
"lstrip": false,
|
975 |
+
"normalized": false,
|
976 |
+
"rstrip": false,
|
977 |
+
"single_word": false,
|
978 |
+
"special": true
|
979 |
+
},
|
980 |
+
"151765": {
|
981 |
+
"content": "|<EXTRA_TOKENS_119>|",
|
982 |
+
"lstrip": false,
|
983 |
+
"normalized": false,
|
984 |
+
"rstrip": false,
|
985 |
+
"single_word": false,
|
986 |
+
"special": true
|
987 |
+
},
|
988 |
+
"151766": {
|
989 |
+
"content": "|<EXTRA_TOKENS_120>|",
|
990 |
+
"lstrip": false,
|
991 |
+
"normalized": false,
|
992 |
+
"rstrip": false,
|
993 |
+
"single_word": false,
|
994 |
+
"special": true
|
995 |
+
},
|
996 |
+
"151767": {
|
997 |
+
"content": "|<EXTRA_TOKENS_121>|",
|
998 |
+
"lstrip": false,
|
999 |
+
"normalized": false,
|
1000 |
+
"rstrip": false,
|
1001 |
+
"single_word": false,
|
1002 |
+
"special": true
|
1003 |
+
},
|
1004 |
+
"151768": {
|
1005 |
+
"content": "|<EXTRA_TOKENS_122>|",
|
1006 |
+
"lstrip": false,
|
1007 |
+
"normalized": false,
|
1008 |
+
"rstrip": false,
|
1009 |
+
"single_word": false,
|
1010 |
+
"special": true
|
1011 |
+
},
|
1012 |
+
"151769": {
|
1013 |
+
"content": "|<EXTRA_TOKENS_123>|",
|
1014 |
+
"lstrip": false,
|
1015 |
+
"normalized": false,
|
1016 |
+
"rstrip": false,
|
1017 |
+
"single_word": false,
|
1018 |
+
"special": true
|
1019 |
+
},
|
1020 |
+
"151770": {
|
1021 |
+
"content": "|<EXTRA_TOKENS_124>|",
|
1022 |
+
"lstrip": false,
|
1023 |
+
"normalized": false,
|
1024 |
+
"rstrip": false,
|
1025 |
+
"single_word": false,
|
1026 |
+
"special": true
|
1027 |
+
},
|
1028 |
+
"151771": {
|
1029 |
+
"content": "|<EXTRA_TOKENS_125>|",
|
1030 |
+
"lstrip": false,
|
1031 |
+
"normalized": false,
|
1032 |
+
"rstrip": false,
|
1033 |
+
"single_word": false,
|
1034 |
+
"special": true
|
1035 |
+
},
|
1036 |
+
"151772": {
|
1037 |
+
"content": "|<EXTRA_TOKENS_126>|",
|
1038 |
+
"lstrip": false,
|
1039 |
+
"normalized": false,
|
1040 |
+
"rstrip": false,
|
1041 |
+
"single_word": false,
|
1042 |
+
"special": true
|
1043 |
+
},
|
1044 |
+
"151773": {
|
1045 |
+
"content": "|<EXTRA_TOKENS_127>|",
|
1046 |
+
"lstrip": false,
|
1047 |
+
"normalized": false,
|
1048 |
+
"rstrip": false,
|
1049 |
+
"single_word": false,
|
1050 |
+
"special": true
|
1051 |
+
},
|
1052 |
+
"151774": {
|
1053 |
+
"content": "|<EXTRA_TOKENS_128>|",
|
1054 |
+
"lstrip": false,
|
1055 |
+
"normalized": false,
|
1056 |
+
"rstrip": false,
|
1057 |
+
"single_word": false,
|
1058 |
+
"special": true
|
1059 |
+
},
|
1060 |
+
"151775": {
|
1061 |
+
"content": "|<EXTRA_TOKENS_129>|",
|
1062 |
+
"lstrip": false,
|
1063 |
+
"normalized": false,
|
1064 |
+
"rstrip": false,
|
1065 |
+
"single_word": false,
|
1066 |
+
"special": true
|
1067 |
+
},
|
1068 |
+
"151776": {
|
1069 |
+
"content": "|<EXTRA_TOKENS_130>|",
|
1070 |
+
"lstrip": false,
|
1071 |
+
"normalized": false,
|
1072 |
+
"rstrip": false,
|
1073 |
+
"single_word": false,
|
1074 |
+
"special": true
|
1075 |
+
},
|
1076 |
+
"151777": {
|
1077 |
+
"content": "|<EXTRA_TOKENS_131>|",
|
1078 |
+
"lstrip": false,
|
1079 |
+
"normalized": false,
|
1080 |
+
"rstrip": false,
|
1081 |
+
"single_word": false,
|
1082 |
+
"special": true
|
1083 |
+
},
|
1084 |
+
"151778": {
|
1085 |
+
"content": "|<EXTRA_TOKENS_132>|",
|
1086 |
+
"lstrip": false,
|
1087 |
+
"normalized": false,
|
1088 |
+
"rstrip": false,
|
1089 |
+
"single_word": false,
|
1090 |
+
"special": true
|
1091 |
+
},
|
1092 |
+
"151779": {
|
1093 |
+
"content": "|<EXTRA_TOKENS_133>|",
|
1094 |
+
"lstrip": false,
|
1095 |
+
"normalized": false,
|
1096 |
+
"rstrip": false,
|
1097 |
+
"single_word": false,
|
1098 |
+
"special": true
|
1099 |
+
},
|
1100 |
+
"151780": {
|
1101 |
+
"content": "|<EXTRA_TOKENS_134>|",
|
1102 |
+
"lstrip": false,
|
1103 |
+
"normalized": false,
|
1104 |
+
"rstrip": false,
|
1105 |
+
"single_word": false,
|
1106 |
+
"special": true
|
1107 |
+
},
|
1108 |
+
"151781": {
|
1109 |
+
"content": "|<EXTRA_TOKENS_135>|",
|
1110 |
+
"lstrip": false,
|
1111 |
+
"normalized": false,
|
1112 |
+
"rstrip": false,
|
1113 |
+
"single_word": false,
|
1114 |
+
"special": true
|
1115 |
+
},
|
1116 |
+
"151782": {
|
1117 |
+
"content": "|<EXTRA_TOKENS_136>|",
|
1118 |
+
"lstrip": false,
|
1119 |
+
"normalized": false,
|
1120 |
+
"rstrip": false,
|
1121 |
+
"single_word": false,
|
1122 |
+
"special": true
|
1123 |
+
},
|
1124 |
+
"151783": {
|
1125 |
+
"content": "|<EXTRA_TOKENS_137>|",
|
1126 |
+
"lstrip": false,
|
1127 |
+
"normalized": false,
|
1128 |
+
"rstrip": false,
|
1129 |
+
"single_word": false,
|
1130 |
+
"special": true
|
1131 |
+
},
|
1132 |
+
"151784": {
|
1133 |
+
"content": "|<EXTRA_TOKENS_138>|",
|
1134 |
+
"lstrip": false,
|
1135 |
+
"normalized": false,
|
1136 |
+
"rstrip": false,
|
1137 |
+
"single_word": false,
|
1138 |
+
"special": true
|
1139 |
+
},
|
1140 |
+
"151785": {
|
1141 |
+
"content": "|<EXTRA_TOKENS_139>|",
|
1142 |
+
"lstrip": false,
|
1143 |
+
"normalized": false,
|
1144 |
+
"rstrip": false,
|
1145 |
+
"single_word": false,
|
1146 |
+
"special": true
|
1147 |
+
},
|
1148 |
+
"151786": {
|
1149 |
+
"content": "|<EXTRA_TOKENS_140>|",
|
1150 |
+
"lstrip": false,
|
1151 |
+
"normalized": false,
|
1152 |
+
"rstrip": false,
|
1153 |
+
"single_word": false,
|
1154 |
+
"special": true
|
1155 |
+
},
|
1156 |
+
"151787": {
|
1157 |
+
"content": "|<EXTRA_TOKENS_141>|",
|
1158 |
+
"lstrip": false,
|
1159 |
+
"normalized": false,
|
1160 |
+
"rstrip": false,
|
1161 |
+
"single_word": false,
|
1162 |
+
"special": true
|
1163 |
+
},
|
1164 |
+
"151788": {
|
1165 |
+
"content": "|<EXTRA_TOKENS_142>|",
|
1166 |
+
"lstrip": false,
|
1167 |
+
"normalized": false,
|
1168 |
+
"rstrip": false,
|
1169 |
+
"single_word": false,
|
1170 |
+
"special": true
|
1171 |
+
},
|
1172 |
+
"151789": {
|
1173 |
+
"content": "|<EXTRA_TOKENS_143>|",
|
1174 |
+
"lstrip": false,
|
1175 |
+
"normalized": false,
|
1176 |
+
"rstrip": false,
|
1177 |
+
"single_word": false,
|
1178 |
+
"special": true
|
1179 |
+
},
|
1180 |
+
"151790": {
|
1181 |
+
"content": "|<EXTRA_TOKENS_144>|",
|
1182 |
+
"lstrip": false,
|
1183 |
+
"normalized": false,
|
1184 |
+
"rstrip": false,
|
1185 |
+
"single_word": false,
|
1186 |
+
"special": true
|
1187 |
+
},
|
1188 |
+
"151791": {
|
1189 |
+
"content": "|<EXTRA_TOKENS_145>|",
|
1190 |
+
"lstrip": false,
|
1191 |
+
"normalized": false,
|
1192 |
+
"rstrip": false,
|
1193 |
+
"single_word": false,
|
1194 |
+
"special": true
|
1195 |
+
},
|
1196 |
+
"151792": {
|
1197 |
+
"content": "|<EXTRA_TOKENS_146>|",
|
1198 |
+
"lstrip": false,
|
1199 |
+
"normalized": false,
|
1200 |
+
"rstrip": false,
|
1201 |
+
"single_word": false,
|
1202 |
+
"special": true
|
1203 |
+
},
|
1204 |
+
"151793": {
|
1205 |
+
"content": "|<EXTRA_TOKENS_147>|",
|
1206 |
+
"lstrip": false,
|
1207 |
+
"normalized": false,
|
1208 |
+
"rstrip": false,
|
1209 |
+
"single_word": false,
|
1210 |
+
"special": true
|
1211 |
+
},
|
1212 |
+
"151794": {
|
1213 |
+
"content": "|<EXTRA_TOKENS_148>|",
|
1214 |
+
"lstrip": false,
|
1215 |
+
"normalized": false,
|
1216 |
+
"rstrip": false,
|
1217 |
+
"single_word": false,
|
1218 |
+
"special": true
|
1219 |
+
},
|
1220 |
+
"151795": {
|
1221 |
+
"content": "|<EXTRA_TOKENS_149>|",
|
1222 |
+
"lstrip": false,
|
1223 |
+
"normalized": false,
|
1224 |
+
"rstrip": false,
|
1225 |
+
"single_word": false,
|
1226 |
+
"special": true
|
1227 |
+
},
|
1228 |
+
"151796": {
|
1229 |
+
"content": "|<EXTRA_TOKENS_150>|",
|
1230 |
+
"lstrip": false,
|
1231 |
+
"normalized": false,
|
1232 |
+
"rstrip": false,
|
1233 |
+
"single_word": false,
|
1234 |
+
"special": true
|
1235 |
+
},
|
1236 |
+
"151797": {
|
1237 |
+
"content": "|<EXTRA_TOKENS_151>|",
|
1238 |
+
"lstrip": false,
|
1239 |
+
"normalized": false,
|
1240 |
+
"rstrip": false,
|
1241 |
+
"single_word": false,
|
1242 |
+
"special": true
|
1243 |
+
},
|
1244 |
+
"151798": {
|
1245 |
+
"content": "|<EXTRA_TOKENS_152>|",
|
1246 |
+
"lstrip": false,
|
1247 |
+
"normalized": false,
|
1248 |
+
"rstrip": false,
|
1249 |
+
"single_word": false,
|
1250 |
+
"special": true
|
1251 |
+
},
|
1252 |
+
"151799": {
|
1253 |
+
"content": "|<EXTRA_TOKENS_153>|",
|
1254 |
+
"lstrip": false,
|
1255 |
+
"normalized": false,
|
1256 |
+
"rstrip": false,
|
1257 |
+
"single_word": false,
|
1258 |
+
"special": true
|
1259 |
+
},
|
1260 |
+
"151800": {
|
1261 |
+
"content": "|<EXTRA_TOKENS_154>|",
|
1262 |
+
"lstrip": false,
|
1263 |
+
"normalized": false,
|
1264 |
+
"rstrip": false,
|
1265 |
+
"single_word": false,
|
1266 |
+
"special": true
|
1267 |
+
},
|
1268 |
+
"151801": {
|
1269 |
+
"content": "|<EXTRA_TOKENS_155>|",
|
1270 |
+
"lstrip": false,
|
1271 |
+
"normalized": false,
|
1272 |
+
"rstrip": false,
|
1273 |
+
"single_word": false,
|
1274 |
+
"special": true
|
1275 |
+
},
|
1276 |
+
"151802": {
|
1277 |
+
"content": "|<EXTRA_TOKENS_156>|",
|
1278 |
+
"lstrip": false,
|
1279 |
+
"normalized": false,
|
1280 |
+
"rstrip": false,
|
1281 |
+
"single_word": false,
|
1282 |
+
"special": true
|
1283 |
+
},
|
1284 |
+
"151803": {
|
1285 |
+
"content": "|<EXTRA_TOKENS_157>|",
|
1286 |
+
"lstrip": false,
|
1287 |
+
"normalized": false,
|
1288 |
+
"rstrip": false,
|
1289 |
+
"single_word": false,
|
1290 |
+
"special": true
|
1291 |
+
},
|
1292 |
+
"151804": {
|
1293 |
+
"content": "|<EXTRA_TOKENS_158>|",
|
1294 |
+
"lstrip": false,
|
1295 |
+
"normalized": false,
|
1296 |
+
"rstrip": false,
|
1297 |
+
"single_word": false,
|
1298 |
+
"special": true
|
1299 |
+
},
|
1300 |
+
"151805": {
|
1301 |
+
"content": "|<EXTRA_TOKENS_159>|",
|
1302 |
+
"lstrip": false,
|
1303 |
+
"normalized": false,
|
1304 |
+
"rstrip": false,
|
1305 |
+
"single_word": false,
|
1306 |
+
"special": true
|
1307 |
+
},
|
1308 |
+
"151806": {
|
1309 |
+
"content": "|<EXTRA_TOKENS_160>|",
|
1310 |
+
"lstrip": false,
|
1311 |
+
"normalized": false,
|
1312 |
+
"rstrip": false,
|
1313 |
+
"single_word": false,
|
1314 |
+
"special": true
|
1315 |
+
},
|
1316 |
+
"151807": {
|
1317 |
+
"content": "|<EXTRA_TOKENS_161>|",
|
1318 |
+
"lstrip": false,
|
1319 |
+
"normalized": false,
|
1320 |
+
"rstrip": false,
|
1321 |
+
"single_word": false,
|
1322 |
+
"special": true
|
1323 |
+
},
|
1324 |
+
"151808": {
|
1325 |
+
"content": "|<EXTRA_TOKENS_162>|",
|
1326 |
+
"lstrip": false,
|
1327 |
+
"normalized": false,
|
1328 |
+
"rstrip": false,
|
1329 |
+
"single_word": false,
|
1330 |
+
"special": true
|
1331 |
+
},
|
1332 |
+
"151809": {
|
1333 |
+
"content": "|<EXTRA_TOKENS_163>|",
|
1334 |
+
"lstrip": false,
|
1335 |
+
"normalized": false,
|
1336 |
+
"rstrip": false,
|
1337 |
+
"single_word": false,
|
1338 |
+
"special": true
|
1339 |
+
},
|
1340 |
+
"151810": {
|
1341 |
+
"content": "|<EXTRA_TOKENS_164>|",
|
1342 |
+
"lstrip": false,
|
1343 |
+
"normalized": false,
|
1344 |
+
"rstrip": false,
|
1345 |
+
"single_word": false,
|
1346 |
+
"special": true
|
1347 |
+
},
|
1348 |
+
"151811": {
|
1349 |
+
"content": "|<EXTRA_TOKENS_165>|",
|
1350 |
+
"lstrip": false,
|
1351 |
+
"normalized": false,
|
1352 |
+
"rstrip": false,
|
1353 |
+
"single_word": false,
|
1354 |
+
"special": true
|
1355 |
+
},
|
1356 |
+
"151812": {
|
1357 |
+
"content": "|<EXTRA_TOKENS_166>|",
|
1358 |
+
"lstrip": false,
|
1359 |
+
"normalized": false,
|
1360 |
+
"rstrip": false,
|
1361 |
+
"single_word": false,
|
1362 |
+
"special": true
|
1363 |
+
},
|
1364 |
+
"151813": {
|
1365 |
+
"content": "|<EXTRA_TOKENS_167>|",
|
1366 |
+
"lstrip": false,
|
1367 |
+
"normalized": false,
|
1368 |
+
"rstrip": false,
|
1369 |
+
"single_word": false,
|
1370 |
+
"special": true
|
1371 |
+
},
|
1372 |
+
"151814": {
|
1373 |
+
"content": "|<EXTRA_TOKENS_168>|",
|
1374 |
+
"lstrip": false,
|
1375 |
+
"normalized": false,
|
1376 |
+
"rstrip": false,
|
1377 |
+
"single_word": false,
|
1378 |
+
"special": true
|
1379 |
+
},
|
1380 |
+
"151815": {
|
1381 |
+
"content": "|<EXTRA_TOKENS_169>|",
|
1382 |
+
"lstrip": false,
|
1383 |
+
"normalized": false,
|
1384 |
+
"rstrip": false,
|
1385 |
+
"single_word": false,
|
1386 |
+
"special": true
|
1387 |
+
},
|
1388 |
+
"151816": {
|
1389 |
+
"content": "|<EXTRA_TOKENS_170>|",
|
1390 |
+
"lstrip": false,
|
1391 |
+
"normalized": false,
|
1392 |
+
"rstrip": false,
|
1393 |
+
"single_word": false,
|
1394 |
+
"special": true
|
1395 |
+
},
|
1396 |
+
"151817": {
|
1397 |
+
"content": "|<EXTRA_TOKENS_171>|",
|
1398 |
+
"lstrip": false,
|
1399 |
+
"normalized": false,
|
1400 |
+
"rstrip": false,
|
1401 |
+
"single_word": false,
|
1402 |
+
"special": true
|
1403 |
+
},
|
1404 |
+
"151818": {
|
1405 |
+
"content": "|<EXTRA_TOKENS_172>|",
|
1406 |
+
"lstrip": false,
|
1407 |
+
"normalized": false,
|
1408 |
+
"rstrip": false,
|
1409 |
+
"single_word": false,
|
1410 |
+
"special": true
|
1411 |
+
},
|
1412 |
+
"151819": {
|
1413 |
+
"content": "|<EXTRA_TOKENS_173>|",
|
1414 |
+
"lstrip": false,
|
1415 |
+
"normalized": false,
|
1416 |
+
"rstrip": false,
|
1417 |
+
"single_word": false,
|
1418 |
+
"special": true
|
1419 |
+
},
|
1420 |
+
"151820": {
|
1421 |
+
"content": "|<EXTRA_TOKENS_174>|",
|
1422 |
+
"lstrip": false,
|
1423 |
+
"normalized": false,
|
1424 |
+
"rstrip": false,
|
1425 |
+
"single_word": false,
|
1426 |
+
"special": true
|
1427 |
+
},
|
1428 |
+
"151821": {
|
1429 |
+
"content": "|<EXTRA_TOKENS_175>|",
|
1430 |
+
"lstrip": false,
|
1431 |
+
"normalized": false,
|
1432 |
+
"rstrip": false,
|
1433 |
+
"single_word": false,
|
1434 |
+
"special": true
|
1435 |
+
},
|
1436 |
+
"151822": {
|
1437 |
+
"content": "|<EXTRA_TOKENS_176>|",
|
1438 |
+
"lstrip": false,
|
1439 |
+
"normalized": false,
|
1440 |
+
"rstrip": false,
|
1441 |
+
"single_word": false,
|
1442 |
+
"special": true
|
1443 |
+
},
|
1444 |
+
"151823": {
|
1445 |
+
"content": "|<EXTRA_TOKENS_177>|",
|
1446 |
+
"lstrip": false,
|
1447 |
+
"normalized": false,
|
1448 |
+
"rstrip": false,
|
1449 |
+
"single_word": false,
|
1450 |
+
"special": true
|
1451 |
+
},
|
1452 |
+
"151824": {
|
1453 |
+
"content": "|<EXTRA_TOKENS_178>|",
|
1454 |
+
"lstrip": false,
|
1455 |
+
"normalized": false,
|
1456 |
+
"rstrip": false,
|
1457 |
+
"single_word": false,
|
1458 |
+
"special": true
|
1459 |
+
},
|
1460 |
+
"151825": {
|
1461 |
+
"content": "|<EXTRA_TOKENS_179>|",
|
1462 |
+
"lstrip": false,
|
1463 |
+
"normalized": false,
|
1464 |
+
"rstrip": false,
|
1465 |
+
"single_word": false,
|
1466 |
+
"special": true
|
1467 |
+
},
|
1468 |
+
"151826": {
|
1469 |
+
"content": "|<EXTRA_TOKENS_180>|",
|
1470 |
+
"lstrip": false,
|
1471 |
+
"normalized": false,
|
1472 |
+
"rstrip": false,
|
1473 |
+
"single_word": false,
|
1474 |
+
"special": true
|
1475 |
+
},
|
1476 |
+
"151827": {
|
1477 |
+
"content": "|<EXTRA_TOKENS_181>|",
|
1478 |
+
"lstrip": false,
|
1479 |
+
"normalized": false,
|
1480 |
+
"rstrip": false,
|
1481 |
+
"single_word": false,
|
1482 |
+
"special": true
|
1483 |
+
},
|
1484 |
+
"151828": {
|
1485 |
+
"content": "|<EXTRA_TOKENS_182>|",
|
1486 |
+
"lstrip": false,
|
1487 |
+
"normalized": false,
|
1488 |
+
"rstrip": false,
|
1489 |
+
"single_word": false,
|
1490 |
+
"special": true
|
1491 |
+
},
|
1492 |
+
"151829": {
|
1493 |
+
"content": "|<EXTRA_TOKENS_183>|",
|
1494 |
+
"lstrip": false,
|
1495 |
+
"normalized": false,
|
1496 |
+
"rstrip": false,
|
1497 |
+
"single_word": false,
|
1498 |
+
"special": true
|
1499 |
+
},
|
1500 |
+
"151830": {
|
1501 |
+
"content": "|<EXTRA_TOKENS_184>|",
|
1502 |
+
"lstrip": false,
|
1503 |
+
"normalized": false,
|
1504 |
+
"rstrip": false,
|
1505 |
+
"single_word": false,
|
1506 |
+
"special": true
|
1507 |
+
},
|
1508 |
+
"151831": {
|
1509 |
+
"content": "|<EXTRA_TOKENS_185>|",
|
1510 |
+
"lstrip": false,
|
1511 |
+
"normalized": false,
|
1512 |
+
"rstrip": false,
|
1513 |
+
"single_word": false,
|
1514 |
+
"special": true
|
1515 |
+
},
|
1516 |
+
"151832": {
|
1517 |
+
"content": "|<EXTRA_TOKENS_186>|",
|
1518 |
+
"lstrip": false,
|
1519 |
+
"normalized": false,
|
1520 |
+
"rstrip": false,
|
1521 |
+
"single_word": false,
|
1522 |
+
"special": true
|
1523 |
+
},
|
1524 |
+
"151833": {
|
1525 |
+
"content": "|<EXTRA_TOKENS_187>|",
|
1526 |
+
"lstrip": false,
|
1527 |
+
"normalized": false,
|
1528 |
+
"rstrip": false,
|
1529 |
+
"single_word": false,
|
1530 |
+
"special": true
|
1531 |
+
},
|
1532 |
+
"151834": {
|
1533 |
+
"content": "|<EXTRA_TOKENS_188>|",
|
1534 |
+
"lstrip": false,
|
1535 |
+
"normalized": false,
|
1536 |
+
"rstrip": false,
|
1537 |
+
"single_word": false,
|
1538 |
+
"special": true
|
1539 |
+
},
|
1540 |
+
"151835": {
|
1541 |
+
"content": "|<EXTRA_TOKENS_189>|",
|
1542 |
+
"lstrip": false,
|
1543 |
+
"normalized": false,
|
1544 |
+
"rstrip": false,
|
1545 |
+
"single_word": false,
|
1546 |
+
"special": true
|
1547 |
+
},
|
1548 |
+
"151836": {
|
1549 |
+
"content": "|<EXTRA_TOKENS_190>|",
|
1550 |
+
"lstrip": false,
|
1551 |
+
"normalized": false,
|
1552 |
+
"rstrip": false,
|
1553 |
+
"single_word": false,
|
1554 |
+
"special": true
|
1555 |
+
},
|
1556 |
+
"151837": {
|
1557 |
+
"content": "|<EXTRA_TOKENS_191>|",
|
1558 |
+
"lstrip": false,
|
1559 |
+
"normalized": false,
|
1560 |
+
"rstrip": false,
|
1561 |
+
"single_word": false,
|
1562 |
+
"special": true
|
1563 |
+
},
|
1564 |
+
"151838": {
|
1565 |
+
"content": "|<EXTRA_TOKENS_192>|",
|
1566 |
+
"lstrip": false,
|
1567 |
+
"normalized": false,
|
1568 |
+
"rstrip": false,
|
1569 |
+
"single_word": false,
|
1570 |
+
"special": true
|
1571 |
+
},
|
1572 |
+
"151839": {
|
1573 |
+
"content": "|<EXTRA_TOKENS_193>|",
|
1574 |
+
"lstrip": false,
|
1575 |
+
"normalized": false,
|
1576 |
+
"rstrip": false,
|
1577 |
+
"single_word": false,
|
1578 |
+
"special": true
|
1579 |
+
},
|
1580 |
+
"151840": {
|
1581 |
+
"content": "|<EXTRA_TOKENS_194>|",
|
1582 |
+
"lstrip": false,
|
1583 |
+
"normalized": false,
|
1584 |
+
"rstrip": false,
|
1585 |
+
"single_word": false,
|
1586 |
+
"special": true
|
1587 |
+
},
|
1588 |
+
"151841": {
|
1589 |
+
"content": "|<EXTRA_TOKENS_195>|",
|
1590 |
+
"lstrip": false,
|
1591 |
+
"normalized": false,
|
1592 |
+
"rstrip": false,
|
1593 |
+
"single_word": false,
|
1594 |
+
"special": true
|
1595 |
+
},
|
1596 |
+
"151842": {
|
1597 |
+
"content": "|<EXTRA_TOKENS_196>|",
|
1598 |
+
"lstrip": false,
|
1599 |
+
"normalized": false,
|
1600 |
+
"rstrip": false,
|
1601 |
+
"single_word": false,
|
1602 |
+
"special": true
|
1603 |
+
},
|
1604 |
+
"151843": {
|
1605 |
+
"content": "|<EXTRA_TOKENS_197>|",
|
1606 |
+
"lstrip": false,
|
1607 |
+
"normalized": false,
|
1608 |
+
"rstrip": false,
|
1609 |
+
"single_word": false,
|
1610 |
+
"special": true
|
1611 |
+
},
|
1612 |
+
"151844": {
|
1613 |
+
"content": "|<EXTRA_TOKENS_198>|",
|
1614 |
+
"lstrip": false,
|
1615 |
+
"normalized": false,
|
1616 |
+
"rstrip": false,
|
1617 |
+
"single_word": false,
|
1618 |
+
"special": true
|
1619 |
+
},
|
1620 |
+
"151845": {
|
1621 |
+
"content": "|<EXTRA_TOKENS_199>|",
|
1622 |
+
"lstrip": false,
|
1623 |
+
"normalized": false,
|
1624 |
+
"rstrip": false,
|
1625 |
+
"single_word": false,
|
1626 |
+
"special": true
|
1627 |
+
},
|
1628 |
+
"151846": {
|
1629 |
+
"content": "|<EXTRA_TOKENS_200>|",
|
1630 |
+
"lstrip": false,
|
1631 |
+
"normalized": false,
|
1632 |
+
"rstrip": false,
|
1633 |
+
"single_word": false,
|
1634 |
+
"special": true
|
1635 |
+
},
|
1636 |
+
"151847": {
|
1637 |
+
"content": "|<EXTRA_TOKENS_201>|",
|
1638 |
+
"lstrip": false,
|
1639 |
+
"normalized": false,
|
1640 |
+
"rstrip": false,
|
1641 |
+
"single_word": false,
|
1642 |
+
"special": true
|
1643 |
+
},
|
1644 |
+
"151848": {
|
1645 |
+
"content": "|<EXTRA_TOKENS_202>|",
|
1646 |
+
"lstrip": false,
|
1647 |
+
"normalized": false,
|
1648 |
+
"rstrip": false,
|
1649 |
+
"single_word": false,
|
1650 |
+
"special": true
|
1651 |
+
},
|
1652 |
+
"151849": {
|
1653 |
+
"content": "|<EXTRA_TOKENS_203>|",
|
1654 |
+
"lstrip": false,
|
1655 |
+
"normalized": false,
|
1656 |
+
"rstrip": false,
|
1657 |
+
"single_word": false,
|
1658 |
+
"special": true
|
1659 |
+
},
|
1660 |
+
"151850": {
|
1661 |
+
"content": "|<EXTRA_TOKENS_204>|",
|
1662 |
+
"lstrip": false,
|
1663 |
+
"normalized": false,
|
1664 |
+
"rstrip": false,
|
1665 |
+
"single_word": false,
|
1666 |
+
"special": true
|
1667 |
+
},
|
1668 |
+
"151851": {
|
1669 |
+
"content": "|<EXTRA_TOKENS_205>|",
|
1670 |
+
"lstrip": false,
|
1671 |
+
"normalized": false,
|
1672 |
+
"rstrip": false,
|
1673 |
+
"single_word": false,
|
1674 |
+
"special": true
|
1675 |
+
},
|
1676 |
+
"151852": {
|
1677 |
+
"content": "|<EXTRA_TOKENS_206>|",
|
1678 |
+
"lstrip": false,
|
1679 |
+
"normalized": false,
|
1680 |
+
"rstrip": false,
|
1681 |
+
"single_word": false,
|
1682 |
+
"special": true
|
1683 |
+
},
|
1684 |
+
"151853": {
|
1685 |
+
"content": "|<EXTRA_TOKENS_207>|",
|
1686 |
+
"lstrip": false,
|
1687 |
+
"normalized": false,
|
1688 |
+
"rstrip": false,
|
1689 |
+
"single_word": false,
|
1690 |
+
"special": true
|
1691 |
+
},
|
1692 |
+
"151854": {
|
1693 |
+
"content": "|<EXTRA_TOKENS_208>|",
|
1694 |
+
"lstrip": false,
|
1695 |
+
"normalized": false,
|
1696 |
+
"rstrip": false,
|
1697 |
+
"single_word": false,
|
1698 |
+
"special": true
|
1699 |
+
},
|
1700 |
+
"151855": {
|
1701 |
+
"content": "|<EXTRA_TOKENS_209>|",
|
1702 |
+
"lstrip": false,
|
1703 |
+
"normalized": false,
|
1704 |
+
"rstrip": false,
|
1705 |
+
"single_word": false,
|
1706 |
+
"special": true
|
1707 |
+
},
|
1708 |
+
"151856": {
|
1709 |
+
"content": "|<EXTRA_TOKENS_210>|",
|
1710 |
+
"lstrip": false,
|
1711 |
+
"normalized": false,
|
1712 |
+
"rstrip": false,
|
1713 |
+
"single_word": false,
|
1714 |
+
"special": true
|
1715 |
+
},
|
1716 |
+
"151857": {
|
1717 |
+
"content": "|<EXTRA_TOKENS_211>|",
|
1718 |
+
"lstrip": false,
|
1719 |
+
"normalized": false,
|
1720 |
+
"rstrip": false,
|
1721 |
+
"single_word": false,
|
1722 |
+
"special": true
|
1723 |
+
},
|
1724 |
+
"151858": {
|
1725 |
+
"content": "|<EXTRA_TOKENS_212>|",
|
1726 |
+
"lstrip": false,
|
1727 |
+
"normalized": false,
|
1728 |
+
"rstrip": false,
|
1729 |
+
"single_word": false,
|
1730 |
+
"special": true
|
1731 |
+
},
|
1732 |
+
"151859": {
|
1733 |
+
"content": "|<EXTRA_TOKENS_213>|",
|
1734 |
+
"lstrip": false,
|
1735 |
+
"normalized": false,
|
1736 |
+
"rstrip": false,
|
1737 |
+
"single_word": false,
|
1738 |
+
"special": true
|
1739 |
+
},
|
1740 |
+
"151860": {
|
1741 |
+
"content": "|<EXTRA_TOKENS_214>|",
|
1742 |
+
"lstrip": false,
|
1743 |
+
"normalized": false,
|
1744 |
+
"rstrip": false,
|
1745 |
+
"single_word": false,
|
1746 |
+
"special": true
|
1747 |
+
},
|
1748 |
+
"151861": {
|
1749 |
+
"content": "|<EXTRA_TOKENS_215>|",
|
1750 |
+
"lstrip": false,
|
1751 |
+
"normalized": false,
|
1752 |
+
"rstrip": false,
|
1753 |
+
"single_word": false,
|
1754 |
+
"special": true
|
1755 |
+
},
|
1756 |
+
"151862": {
|
1757 |
+
"content": "|<EXTRA_TOKENS_216>|",
|
1758 |
+
"lstrip": false,
|
1759 |
+
"normalized": false,
|
1760 |
+
"rstrip": false,
|
1761 |
+
"single_word": false,
|
1762 |
+
"special": true
|
1763 |
+
},
|
1764 |
+
"151863": {
|
1765 |
+
"content": "|<EXTRA_TOKENS_217>|",
|
1766 |
+
"lstrip": false,
|
1767 |
+
"normalized": false,
|
1768 |
+
"rstrip": false,
|
1769 |
+
"single_word": false,
|
1770 |
+
"special": true
|
1771 |
+
},
|
1772 |
+
"151864": {
|
1773 |
+
"content": "|<EXTRA_TOKENS_218>|",
|
1774 |
+
"lstrip": false,
|
1775 |
+
"normalized": false,
|
1776 |
+
"rstrip": false,
|
1777 |
+
"single_word": false,
|
1778 |
+
"special": true
|
1779 |
+
},
|
1780 |
+
"151865": {
|
1781 |
+
"content": "|<EXTRA_TOKENS_219>|",
|
1782 |
+
"lstrip": false,
|
1783 |
+
"normalized": false,
|
1784 |
+
"rstrip": false,
|
1785 |
+
"single_word": false,
|
1786 |
+
"special": true
|
1787 |
+
},
|
1788 |
+
"151866": {
|
1789 |
+
"content": "|<EXTRA_TOKENS_220>|",
|
1790 |
+
"lstrip": false,
|
1791 |
+
"normalized": false,
|
1792 |
+
"rstrip": false,
|
1793 |
+
"single_word": false,
|
1794 |
+
"special": true
|
1795 |
+
},
|
1796 |
+
"151867": {
|
1797 |
+
"content": "|<EXTRA_TOKENS_221>|",
|
1798 |
+
"lstrip": false,
|
1799 |
+
"normalized": false,
|
1800 |
+
"rstrip": false,
|
1801 |
+
"single_word": false,
|
1802 |
+
"special": true
|
1803 |
+
},
|
1804 |
+
"151868": {
|
1805 |
+
"content": "|<EXTRA_TOKENS_222>|",
|
1806 |
+
"lstrip": false,
|
1807 |
+
"normalized": false,
|
1808 |
+
"rstrip": false,
|
1809 |
+
"single_word": false,
|
1810 |
+
"special": true
|
1811 |
+
},
|
1812 |
+
"151869": {
|
1813 |
+
"content": "|<EXTRA_TOKENS_223>|",
|
1814 |
+
"lstrip": false,
|
1815 |
+
"normalized": false,
|
1816 |
+
"rstrip": false,
|
1817 |
+
"single_word": false,
|
1818 |
+
"special": true
|
1819 |
+
},
|
1820 |
+
"151870": {
|
1821 |
+
"content": "|<EXTRA_TOKENS_224>|",
|
1822 |
+
"lstrip": false,
|
1823 |
+
"normalized": false,
|
1824 |
+
"rstrip": false,
|
1825 |
+
"single_word": false,
|
1826 |
+
"special": true
|
1827 |
+
},
|
1828 |
+
"151871": {
|
1829 |
+
"content": "|<EXTRA_TOKENS_225>|",
|
1830 |
+
"lstrip": false,
|
1831 |
+
"normalized": false,
|
1832 |
+
"rstrip": false,
|
1833 |
+
"single_word": false,
|
1834 |
+
"special": true
|
1835 |
+
},
|
1836 |
+
"151872": {
|
1837 |
+
"content": "|<EXTRA_TOKENS_226>|",
|
1838 |
+
"lstrip": false,
|
1839 |
+
"normalized": false,
|
1840 |
+
"rstrip": false,
|
1841 |
+
"single_word": false,
|
1842 |
+
"special": true
|
1843 |
+
},
|
1844 |
+
"151873": {
|
1845 |
+
"content": "|<EXTRA_TOKENS_227>|",
|
1846 |
+
"lstrip": false,
|
1847 |
+
"normalized": false,
|
1848 |
+
"rstrip": false,
|
1849 |
+
"single_word": false,
|
1850 |
+
"special": true
|
1851 |
+
},
|
1852 |
+
"151874": {
|
1853 |
+
"content": "|<EXTRA_TOKENS_228>|",
|
1854 |
+
"lstrip": false,
|
1855 |
+
"normalized": false,
|
1856 |
+
"rstrip": false,
|
1857 |
+
"single_word": false,
|
1858 |
+
"special": true
|
1859 |
+
},
|
1860 |
+
"151875": {
|
1861 |
+
"content": "|<EXTRA_TOKENS_229>|",
|
1862 |
+
"lstrip": false,
|
1863 |
+
"normalized": false,
|
1864 |
+
"rstrip": false,
|
1865 |
+
"single_word": false,
|
1866 |
+
"special": true
|
1867 |
+
},
|
1868 |
+
"151876": {
|
1869 |
+
"content": "|<EXTRA_TOKENS_230>|",
|
1870 |
+
"lstrip": false,
|
1871 |
+
"normalized": false,
|
1872 |
+
"rstrip": false,
|
1873 |
+
"single_word": false,
|
1874 |
+
"special": true
|
1875 |
+
},
|
1876 |
+
"151877": {
|
1877 |
+
"content": "|<EXTRA_TOKENS_231>|",
|
1878 |
+
"lstrip": false,
|
1879 |
+
"normalized": false,
|
1880 |
+
"rstrip": false,
|
1881 |
+
"single_word": false,
|
1882 |
+
"special": true
|
1883 |
+
},
|
1884 |
+
"151878": {
|
1885 |
+
"content": "|<EXTRA_TOKENS_232>|",
|
1886 |
+
"lstrip": false,
|
1887 |
+
"normalized": false,
|
1888 |
+
"rstrip": false,
|
1889 |
+
"single_word": false,
|
1890 |
+
"special": true
|
1891 |
+
},
|
1892 |
+
"151879": {
|
1893 |
+
"content": "|<EXTRA_TOKENS_233>|",
|
1894 |
+
"lstrip": false,
|
1895 |
+
"normalized": false,
|
1896 |
+
"rstrip": false,
|
1897 |
+
"single_word": false,
|
1898 |
+
"special": true
|
1899 |
+
},
|
1900 |
+
"151880": {
|
1901 |
+
"content": "|<EXTRA_TOKENS_234>|",
|
1902 |
+
"lstrip": false,
|
1903 |
+
"normalized": false,
|
1904 |
+
"rstrip": false,
|
1905 |
+
"single_word": false,
|
1906 |
+
"special": true
|
1907 |
+
},
|
1908 |
+
"151881": {
|
1909 |
+
"content": "|<EXTRA_TOKENS_235>|",
|
1910 |
+
"lstrip": false,
|
1911 |
+
"normalized": false,
|
1912 |
+
"rstrip": false,
|
1913 |
+
"single_word": false,
|
1914 |
+
"special": true
|
1915 |
+
},
|
1916 |
+
"151882": {
|
1917 |
+
"content": "|<EXTRA_TOKENS_236>|",
|
1918 |
+
"lstrip": false,
|
1919 |
+
"normalized": false,
|
1920 |
+
"rstrip": false,
|
1921 |
+
"single_word": false,
|
1922 |
+
"special": true
|
1923 |
+
},
|
1924 |
+
"151883": {
|
1925 |
+
"content": "|<EXTRA_TOKENS_237>|",
|
1926 |
+
"lstrip": false,
|
1927 |
+
"normalized": false,
|
1928 |
+
"rstrip": false,
|
1929 |
+
"single_word": false,
|
1930 |
+
"special": true
|
1931 |
+
},
|
1932 |
+
"151884": {
|
1933 |
+
"content": "|<EXTRA_TOKENS_238>|",
|
1934 |
+
"lstrip": false,
|
1935 |
+
"normalized": false,
|
1936 |
+
"rstrip": false,
|
1937 |
+
"single_word": false,
|
1938 |
+
"special": true
|
1939 |
+
},
|
1940 |
+
"151885": {
|
1941 |
+
"content": "|<EXTRA_TOKENS_239>|",
|
1942 |
+
"lstrip": false,
|
1943 |
+
"normalized": false,
|
1944 |
+
"rstrip": false,
|
1945 |
+
"single_word": false,
|
1946 |
+
"special": true
|
1947 |
+
},
|
1948 |
+
"151886": {
|
1949 |
+
"content": "|<EXTRA_TOKENS_240>|",
|
1950 |
+
"lstrip": false,
|
1951 |
+
"normalized": false,
|
1952 |
+
"rstrip": false,
|
1953 |
+
"single_word": false,
|
1954 |
+
"special": true
|
1955 |
+
},
|
1956 |
+
"151887": {
|
1957 |
+
"content": "|<EXTRA_TOKENS_241>|",
|
1958 |
+
"lstrip": false,
|
1959 |
+
"normalized": false,
|
1960 |
+
"rstrip": false,
|
1961 |
+
"single_word": false,
|
1962 |
+
"special": true
|
1963 |
+
},
|
1964 |
+
"151888": {
|
1965 |
+
"content": "|<EXTRA_TOKENS_242>|",
|
1966 |
+
"lstrip": false,
|
1967 |
+
"normalized": false,
|
1968 |
+
"rstrip": false,
|
1969 |
+
"single_word": false,
|
1970 |
+
"special": true
|
1971 |
+
},
|
1972 |
+
"151889": {
|
1973 |
+
"content": "|<EXTRA_TOKENS_243>|",
|
1974 |
+
"lstrip": false,
|
1975 |
+
"normalized": false,
|
1976 |
+
"rstrip": false,
|
1977 |
+
"single_word": false,
|
1978 |
+
"special": true
|
1979 |
+
},
|
1980 |
+
"151890": {
|
1981 |
+
"content": "|<EXTRA_TOKENS_244>|",
|
1982 |
+
"lstrip": false,
|
1983 |
+
"normalized": false,
|
1984 |
+
"rstrip": false,
|
1985 |
+
"single_word": false,
|
1986 |
+
"special": true
|
1987 |
+
},
|
1988 |
+
"151891": {
|
1989 |
+
"content": "|<EXTRA_TOKENS_245>|",
|
1990 |
+
"lstrip": false,
|
1991 |
+
"normalized": false,
|
1992 |
+
"rstrip": false,
|
1993 |
+
"single_word": false,
|
1994 |
+
"special": true
|
1995 |
+
},
|
1996 |
+
"151892": {
|
1997 |
+
"content": "|<EXTRA_TOKENS_246>|",
|
1998 |
+
"lstrip": false,
|
1999 |
+
"normalized": false,
|
2000 |
+
"rstrip": false,
|
2001 |
+
"single_word": false,
|
2002 |
+
"special": true
|
2003 |
+
},
|
2004 |
+
"151893": {
|
2005 |
+
"content": "|<EXTRA_TOKENS_247>|",
|
2006 |
+
"lstrip": false,
|
2007 |
+
"normalized": false,
|
2008 |
+
"rstrip": false,
|
2009 |
+
"single_word": false,
|
2010 |
+
"special": true
|
2011 |
+
},
|
2012 |
+
"151894": {
|
2013 |
+
"content": "|<EXTRA_TOKENS_248>|",
|
2014 |
+
"lstrip": false,
|
2015 |
+
"normalized": false,
|
2016 |
+
"rstrip": false,
|
2017 |
+
"single_word": false,
|
2018 |
+
"special": true
|
2019 |
+
},
|
2020 |
+
"151895": {
|
2021 |
+
"content": "|<EXTRA_TOKENS_249>|",
|
2022 |
+
"lstrip": false,
|
2023 |
+
"normalized": false,
|
2024 |
+
"rstrip": false,
|
2025 |
+
"single_word": false,
|
2026 |
+
"special": true
|
2027 |
+
},
|
2028 |
+
"151896": {
|
2029 |
+
"content": "|<EXTRA_TOKENS_250>|",
|
2030 |
+
"lstrip": false,
|
2031 |
+
"normalized": false,
|
2032 |
+
"rstrip": false,
|
2033 |
+
"single_word": false,
|
2034 |
+
"special": true
|
2035 |
+
},
|
2036 |
+
"151897": {
|
2037 |
+
"content": "|<EXTRA_TOKENS_251>|",
|
2038 |
+
"lstrip": false,
|
2039 |
+
"normalized": false,
|
2040 |
+
"rstrip": false,
|
2041 |
+
"single_word": false,
|
2042 |
+
"special": true
|
2043 |
+
},
|
2044 |
+
"151898": {
|
2045 |
+
"content": "|<EXTRA_TOKENS_252>|",
|
2046 |
+
"lstrip": false,
|
2047 |
+
"normalized": false,
|
2048 |
+
"rstrip": false,
|
2049 |
+
"single_word": false,
|
2050 |
+
"special": true
|
2051 |
+
},
|
2052 |
+
"151899": {
|
2053 |
+
"content": "|<EXTRA_TOKENS_253>|",
|
2054 |
+
"lstrip": false,
|
2055 |
+
"normalized": false,
|
2056 |
+
"rstrip": false,
|
2057 |
+
"single_word": false,
|
2058 |
+
"special": true
|
2059 |
+
},
|
2060 |
+
"151900": {
|
2061 |
+
"content": "|<EXTRA_TOKENS_254>|",
|
2062 |
+
"lstrip": false,
|
2063 |
+
"normalized": false,
|
2064 |
+
"rstrip": false,
|
2065 |
+
"single_word": false,
|
2066 |
+
"special": true
|
2067 |
+
},
|
2068 |
+
"151901": {
|
2069 |
+
"content": "|<EXTRA_TOKENS_255>|",
|
2070 |
+
"lstrip": false,
|
2071 |
+
"normalized": false,
|
2072 |
+
"rstrip": false,
|
2073 |
+
"single_word": false,
|
2074 |
+
"special": true
|
2075 |
+
},
|
2076 |
+
"151902": {
|
2077 |
+
"content": "|<EXTRA_TOKENS_256>|",
|
2078 |
+
"lstrip": false,
|
2079 |
+
"normalized": false,
|
2080 |
+
"rstrip": false,
|
2081 |
+
"single_word": false,
|
2082 |
+
"special": true
|
2083 |
+
},
|
2084 |
+
"151903": {
|
2085 |
+
"content": "|<EXTRA_TOKENS_257>|",
|
2086 |
+
"lstrip": false,
|
2087 |
+
"normalized": false,
|
2088 |
+
"rstrip": false,
|
2089 |
+
"single_word": false,
|
2090 |
+
"special": true
|
2091 |
+
},
|
2092 |
+
"151904": {
|
2093 |
+
"content": "|<EXTRA_TOKENS_258>|",
|
2094 |
+
"lstrip": false,
|
2095 |
+
"normalized": false,
|
2096 |
+
"rstrip": false,
|
2097 |
+
"single_word": false,
|
2098 |
+
"special": true
|
2099 |
+
},
|
2100 |
+
"151905": {
|
2101 |
+
"content": "|<EXTRA_TOKENS_259>|",
|
2102 |
+
"lstrip": false,
|
2103 |
+
"normalized": false,
|
2104 |
+
"rstrip": false,
|
2105 |
+
"single_word": false,
|
2106 |
+
"special": true
|
2107 |
+
},
|
2108 |
+
"151906": {
|
2109 |
+
"content": "|<EXTRA_TOKENS_260>|",
|
2110 |
+
"lstrip": false,
|
2111 |
+
"normalized": false,
|
2112 |
+
"rstrip": false,
|
2113 |
+
"single_word": false,
|
2114 |
+
"special": true
|
2115 |
+
},
|
2116 |
+
"151907": {
|
2117 |
+
"content": "|<EXTRA_TOKENS_261>|",
|
2118 |
+
"lstrip": false,
|
2119 |
+
"normalized": false,
|
2120 |
+
"rstrip": false,
|
2121 |
+
"single_word": false,
|
2122 |
+
"special": true
|
2123 |
+
},
|
2124 |
+
"151908": {
|
2125 |
+
"content": "|<EXTRA_TOKENS_262>|",
|
2126 |
+
"lstrip": false,
|
2127 |
+
"normalized": false,
|
2128 |
+
"rstrip": false,
|
2129 |
+
"single_word": false,
|
2130 |
+
"special": true
|
2131 |
+
},
|
2132 |
+
"151909": {
|
2133 |
+
"content": "|<EXTRA_TOKENS_263>|",
|
2134 |
+
"lstrip": false,
|
2135 |
+
"normalized": false,
|
2136 |
+
"rstrip": false,
|
2137 |
+
"single_word": false,
|
2138 |
+
"special": true
|
2139 |
+
},
|
2140 |
+
"151910": {
|
2141 |
+
"content": "|<EXTRA_TOKENS_264>|",
|
2142 |
+
"lstrip": false,
|
2143 |
+
"normalized": false,
|
2144 |
+
"rstrip": false,
|
2145 |
+
"single_word": false,
|
2146 |
+
"special": true
|
2147 |
+
},
|
2148 |
+
"151911": {
|
2149 |
+
"content": "|<EXTRA_TOKENS_265>|",
|
2150 |
+
"lstrip": false,
|
2151 |
+
"normalized": false,
|
2152 |
+
"rstrip": false,
|
2153 |
+
"single_word": false,
|
2154 |
+
"special": true
|
2155 |
+
},
|
2156 |
+
"151912": {
|
2157 |
+
"content": "|<EXTRA_TOKENS_266>|",
|
2158 |
+
"lstrip": false,
|
2159 |
+
"normalized": false,
|
2160 |
+
"rstrip": false,
|
2161 |
+
"single_word": false,
|
2162 |
+
"special": true
|
2163 |
+
},
|
2164 |
+
"151913": {
|
2165 |
+
"content": "|<EXTRA_TOKENS_267>|",
|
2166 |
+
"lstrip": false,
|
2167 |
+
"normalized": false,
|
2168 |
+
"rstrip": false,
|
2169 |
+
"single_word": false,
|
2170 |
+
"special": true
|
2171 |
+
},
|
2172 |
+
"151914": {
|
2173 |
+
"content": "|<EXTRA_TOKENS_268>|",
|
2174 |
+
"lstrip": false,
|
2175 |
+
"normalized": false,
|
2176 |
+
"rstrip": false,
|
2177 |
+
"single_word": false,
|
2178 |
+
"special": true
|
2179 |
+
},
|
2180 |
+
"151915": {
|
2181 |
+
"content": "|<EXTRA_TOKENS_269>|",
|
2182 |
+
"lstrip": false,
|
2183 |
+
"normalized": false,
|
2184 |
+
"rstrip": false,
|
2185 |
+
"single_word": false,
|
2186 |
+
"special": true
|
2187 |
+
},
|
2188 |
+
"151916": {
|
2189 |
+
"content": "|<EXTRA_TOKENS_270>|",
|
2190 |
+
"lstrip": false,
|
2191 |
+
"normalized": false,
|
2192 |
+
"rstrip": false,
|
2193 |
+
"single_word": false,
|
2194 |
+
"special": true
|
2195 |
+
},
|
2196 |
+
"151917": {
|
2197 |
+
"content": "|<EXTRA_TOKENS_271>|",
|
2198 |
+
"lstrip": false,
|
2199 |
+
"normalized": false,
|
2200 |
+
"rstrip": false,
|
2201 |
+
"single_word": false,
|
2202 |
+
"special": true
|
2203 |
+
},
|
2204 |
+
"151918": {
|
2205 |
+
"content": "|<EXTRA_TOKENS_272>|",
|
2206 |
+
"lstrip": false,
|
2207 |
+
"normalized": false,
|
2208 |
+
"rstrip": false,
|
2209 |
+
"single_word": false,
|
2210 |
+
"special": true
|
2211 |
+
},
|
2212 |
+
"151919": {
|
2213 |
+
"content": "|<EXTRA_TOKENS_273>|",
|
2214 |
+
"lstrip": false,
|
2215 |
+
"normalized": false,
|
2216 |
+
"rstrip": false,
|
2217 |
+
"single_word": false,
|
2218 |
+
"special": true
|
2219 |
+
},
|
2220 |
+
"151920": {
|
2221 |
+
"content": "|<EXTRA_TOKENS_274>|",
|
2222 |
+
"lstrip": false,
|
2223 |
+
"normalized": false,
|
2224 |
+
"rstrip": false,
|
2225 |
+
"single_word": false,
|
2226 |
+
"special": true
|
2227 |
+
},
|
2228 |
+
"151921": {
|
2229 |
+
"content": "|<EXTRA_TOKENS_275>|",
|
2230 |
+
"lstrip": false,
|
2231 |
+
"normalized": false,
|
2232 |
+
"rstrip": false,
|
2233 |
+
"single_word": false,
|
2234 |
+
"special": true
|
2235 |
+
},
|
2236 |
+
"151922": {
|
2237 |
+
"content": "|<EXTRA_TOKENS_276>|",
|
2238 |
+
"lstrip": false,
|
2239 |
+
"normalized": false,
|
2240 |
+
"rstrip": false,
|
2241 |
+
"single_word": false,
|
2242 |
+
"special": true
|
2243 |
+
},
|
2244 |
+
"151923": {
|
2245 |
+
"content": "|<EXTRA_TOKENS_277>|",
|
2246 |
+
"lstrip": false,
|
2247 |
+
"normalized": false,
|
2248 |
+
"rstrip": false,
|
2249 |
+
"single_word": false,
|
2250 |
+
"special": true
|
2251 |
+
},
|
2252 |
+
"151924": {
|
2253 |
+
"content": "|<EXTRA_TOKENS_278>|",
|
2254 |
+
"lstrip": false,
|
2255 |
+
"normalized": false,
|
2256 |
+
"rstrip": false,
|
2257 |
+
"single_word": false,
|
2258 |
+
"special": true
|
2259 |
+
},
|
2260 |
+
"151925": {
|
2261 |
+
"content": "|<EXTRA_TOKENS_279>|",
|
2262 |
+
"lstrip": false,
|
2263 |
+
"normalized": false,
|
2264 |
+
"rstrip": false,
|
2265 |
+
"single_word": false,
|
2266 |
+
"special": true
|
2267 |
+
},
|
2268 |
+
"151926": {
|
2269 |
+
"content": "|<EXTRA_TOKENS_280>|",
|
2270 |
+
"lstrip": false,
|
2271 |
+
"normalized": false,
|
2272 |
+
"rstrip": false,
|
2273 |
+
"single_word": false,
|
2274 |
+
"special": true
|
2275 |
+
},
|
2276 |
+
"151927": {
|
2277 |
+
"content": "|<EXTRA_TOKENS_281>|",
|
2278 |
+
"lstrip": false,
|
2279 |
+
"normalized": false,
|
2280 |
+
"rstrip": false,
|
2281 |
+
"single_word": false,
|
2282 |
+
"special": true
|
2283 |
+
},
|
2284 |
+
"151928": {
|
2285 |
+
"content": "|<EXTRA_TOKENS_282>|",
|
2286 |
+
"lstrip": false,
|
2287 |
+
"normalized": false,
|
2288 |
+
"rstrip": false,
|
2289 |
+
"single_word": false,
|
2290 |
+
"special": true
|
2291 |
+
},
|
2292 |
+
"151929": {
|
2293 |
+
"content": "|<EXTRA_TOKENS_283>|",
|
2294 |
+
"lstrip": false,
|
2295 |
+
"normalized": false,
|
2296 |
+
"rstrip": false,
|
2297 |
+
"single_word": false,
|
2298 |
+
"special": true
|
2299 |
+
},
|
2300 |
+
"151930": {
|
2301 |
+
"content": "|<EXTRA_TOKENS_284>|",
|
2302 |
+
"lstrip": false,
|
2303 |
+
"normalized": false,
|
2304 |
+
"rstrip": false,
|
2305 |
+
"single_word": false,
|
2306 |
+
"special": true
|
2307 |
+
},
|
2308 |
+
"151931": {
|
2309 |
+
"content": "|<EXTRA_TOKENS_285>|",
|
2310 |
+
"lstrip": false,
|
2311 |
+
"normalized": false,
|
2312 |
+
"rstrip": false,
|
2313 |
+
"single_word": false,
|
2314 |
+
"special": true
|
2315 |
+
},
|
2316 |
+
"151932": {
|
2317 |
+
"content": "|<EXTRA_TOKENS_286>|",
|
2318 |
+
"lstrip": false,
|
2319 |
+
"normalized": false,
|
2320 |
+
"rstrip": false,
|
2321 |
+
"single_word": false,
|
2322 |
+
"special": true
|
2323 |
+
},
|
2324 |
+
"151933": {
|
2325 |
+
"content": "|<EXTRA_TOKENS_287>|",
|
2326 |
+
"lstrip": false,
|
2327 |
+
"normalized": false,
|
2328 |
+
"rstrip": false,
|
2329 |
+
"single_word": false,
|
2330 |
+
"special": true
|
2331 |
+
},
|
2332 |
+
"151934": {
|
2333 |
+
"content": "|<EXTRA_TOKENS_288>|",
|
2334 |
+
"lstrip": false,
|
2335 |
+
"normalized": false,
|
2336 |
+
"rstrip": false,
|
2337 |
+
"single_word": false,
|
2338 |
+
"special": true
|
2339 |
+
},
|
2340 |
+
"151935": {
|
2341 |
+
"content": "|<EXTRA_TOKENS_289>|",
|
2342 |
+
"lstrip": false,
|
2343 |
+
"normalized": false,
|
2344 |
+
"rstrip": false,
|
2345 |
+
"single_word": false,
|
2346 |
+
"special": true
|
2347 |
+
},
|
2348 |
+
"151936": {
|
2349 |
+
"content": "|<EXTRA_TOKENS_290>|",
|
2350 |
+
"lstrip": false,
|
2351 |
+
"normalized": false,
|
2352 |
+
"rstrip": false,
|
2353 |
+
"single_word": false,
|
2354 |
+
"special": true
|
2355 |
+
},
|
2356 |
+
"151937": {
|
2357 |
+
"content": "|<EXTRA_TOKENS_291>|",
|
2358 |
+
"lstrip": false,
|
2359 |
+
"normalized": false,
|
2360 |
+
"rstrip": false,
|
2361 |
+
"single_word": false,
|
2362 |
+
"special": true
|
2363 |
+
},
|
2364 |
+
"151938": {
|
2365 |
+
"content": "|<EXTRA_TOKENS_292>|",
|
2366 |
+
"lstrip": false,
|
2367 |
+
"normalized": false,
|
2368 |
+
"rstrip": false,
|
2369 |
+
"single_word": false,
|
2370 |
+
"special": true
|
2371 |
+
},
|
2372 |
+
"151939": {
|
2373 |
+
"content": "|<EXTRA_TOKENS_293>|",
|
2374 |
+
"lstrip": false,
|
2375 |
+
"normalized": false,
|
2376 |
+
"rstrip": false,
|
2377 |
+
"single_word": false,
|
2378 |
+
"special": true
|
2379 |
+
},
|
2380 |
+
"151940": {
|
2381 |
+
"content": "|<EXTRA_TOKENS_294>|",
|
2382 |
+
"lstrip": false,
|
2383 |
+
"normalized": false,
|
2384 |
+
"rstrip": false,
|
2385 |
+
"single_word": false,
|
2386 |
+
"special": true
|
2387 |
+
},
|
2388 |
+
"151941": {
|
2389 |
+
"content": "|<EXTRA_TOKENS_295>|",
|
2390 |
+
"lstrip": false,
|
2391 |
+
"normalized": false,
|
2392 |
+
"rstrip": false,
|
2393 |
+
"single_word": false,
|
2394 |
+
"special": true
|
2395 |
+
},
|
2396 |
+
"151942": {
|
2397 |
+
"content": "|<EXTRA_TOKENS_296>|",
|
2398 |
+
"lstrip": false,
|
2399 |
+
"normalized": false,
|
2400 |
+
"rstrip": false,
|
2401 |
+
"single_word": false,
|
2402 |
+
"special": true
|
2403 |
+
},
|
2404 |
+
"151943": {
|
2405 |
+
"content": "|<EXTRA_TOKENS_297>|",
|
2406 |
+
"lstrip": false,
|
2407 |
+
"normalized": false,
|
2408 |
+
"rstrip": false,
|
2409 |
+
"single_word": false,
|
2410 |
+
"special": true
|
2411 |
+
},
|
2412 |
+
"151944": {
|
2413 |
+
"content": "|<EXTRA_TOKENS_298>|",
|
2414 |
+
"lstrip": false,
|
2415 |
+
"normalized": false,
|
2416 |
+
"rstrip": false,
|
2417 |
+
"single_word": false,
|
2418 |
+
"special": true
|
2419 |
+
},
|
2420 |
+
"151945": {
|
2421 |
+
"content": "|<EXTRA_TOKENS_299>|",
|
2422 |
+
"lstrip": false,
|
2423 |
+
"normalized": false,
|
2424 |
+
"rstrip": false,
|
2425 |
+
"single_word": false,
|
2426 |
+
"special": true
|
2427 |
+
},
|
2428 |
+
"151946": {
|
2429 |
+
"content": "|<EXTRA_TOKENS_300>|",
|
2430 |
+
"lstrip": false,
|
2431 |
+
"normalized": false,
|
2432 |
+
"rstrip": false,
|
2433 |
+
"single_word": false,
|
2434 |
+
"special": true
|
2435 |
+
},
|
2436 |
+
"151947": {
|
2437 |
+
"content": "|<EXTRA_TOKENS_301>|",
|
2438 |
+
"lstrip": false,
|
2439 |
+
"normalized": false,
|
2440 |
+
"rstrip": false,
|
2441 |
+
"single_word": false,
|
2442 |
+
"special": true
|
2443 |
+
},
|
2444 |
+
"151948": {
|
2445 |
+
"content": "|<EXTRA_TOKENS_302>|",
|
2446 |
+
"lstrip": false,
|
2447 |
+
"normalized": false,
|
2448 |
+
"rstrip": false,
|
2449 |
+
"single_word": false,
|
2450 |
+
"special": true
|
2451 |
+
},
|
2452 |
+
"151949": {
|
2453 |
+
"content": "|<EXTRA_TOKENS_303>|",
|
2454 |
+
"lstrip": false,
|
2455 |
+
"normalized": false,
|
2456 |
+
"rstrip": false,
|
2457 |
+
"single_word": false,
|
2458 |
+
"special": true
|
2459 |
+
},
|
2460 |
+
"151950": {
|
2461 |
+
"content": "|<EXTRA_TOKENS_304>|",
|
2462 |
+
"lstrip": false,
|
2463 |
+
"normalized": false,
|
2464 |
+
"rstrip": false,
|
2465 |
+
"single_word": false,
|
2466 |
+
"special": true
|
2467 |
+
},
|
2468 |
+
"151951": {
|
2469 |
+
"content": "|<EXTRA_TOKENS_305>|",
|
2470 |
+
"lstrip": false,
|
2471 |
+
"normalized": false,
|
2472 |
+
"rstrip": false,
|
2473 |
+
"single_word": false,
|
2474 |
+
"special": true
|
2475 |
+
},
|
2476 |
+
"151952": {
|
2477 |
+
"content": "|<EXTRA_TOKENS_306>|",
|
2478 |
+
"lstrip": false,
|
2479 |
+
"normalized": false,
|
2480 |
+
"rstrip": false,
|
2481 |
+
"single_word": false,
|
2482 |
+
"special": true
|
2483 |
+
},
|
2484 |
+
"151953": {
|
2485 |
+
"content": "|<EXTRA_TOKENS_307>|",
|
2486 |
+
"lstrip": false,
|
2487 |
+
"normalized": false,
|
2488 |
+
"rstrip": false,
|
2489 |
+
"single_word": false,
|
2490 |
+
"special": true
|
2491 |
+
},
|
2492 |
+
"151954": {
|
2493 |
+
"content": "|<EXTRA_TOKENS_308>|",
|
2494 |
+
"lstrip": false,
|
2495 |
+
"normalized": false,
|
2496 |
+
"rstrip": false,
|
2497 |
+
"single_word": false,
|
2498 |
+
"special": true
|
2499 |
+
},
|
2500 |
+
"151955": {
|
2501 |
+
"content": "|<EXTRA_TOKENS_309>|",
|
2502 |
+
"lstrip": false,
|
2503 |
+
"normalized": false,
|
2504 |
+
"rstrip": false,
|
2505 |
+
"single_word": false,
|
2506 |
+
"special": true
|
2507 |
+
},
|
2508 |
+
"151956": {
|
2509 |
+
"content": "|<EXTRA_TOKENS_310>|",
|
2510 |
+
"lstrip": false,
|
2511 |
+
"normalized": false,
|
2512 |
+
"rstrip": false,
|
2513 |
+
"single_word": false,
|
2514 |
+
"special": true
|
2515 |
+
},
|
2516 |
+
"151957": {
|
2517 |
+
"content": "|<EXTRA_TOKENS_311>|",
|
2518 |
+
"lstrip": false,
|
2519 |
+
"normalized": false,
|
2520 |
+
"rstrip": false,
|
2521 |
+
"single_word": false,
|
2522 |
+
"special": true
|
2523 |
+
},
|
2524 |
+
"151958": {
|
2525 |
+
"content": "|<EXTRA_TOKENS_312>|",
|
2526 |
+
"lstrip": false,
|
2527 |
+
"normalized": false,
|
2528 |
+
"rstrip": false,
|
2529 |
+
"single_word": false,
|
2530 |
+
"special": true
|
2531 |
+
},
|
2532 |
+
"151959": {
|
2533 |
+
"content": "|<EXTRA_TOKENS_313>|",
|
2534 |
+
"lstrip": false,
|
2535 |
+
"normalized": false,
|
2536 |
+
"rstrip": false,
|
2537 |
+
"single_word": false,
|
2538 |
+
"special": true
|
2539 |
+
},
|
2540 |
+
"151960": {
|
2541 |
+
"content": "|<EXTRA_TOKENS_314>|",
|
2542 |
+
"lstrip": false,
|
2543 |
+
"normalized": false,
|
2544 |
+
"rstrip": false,
|
2545 |
+
"single_word": false,
|
2546 |
+
"special": true
|
2547 |
+
},
|
2548 |
+
"151961": {
|
2549 |
+
"content": "|<EXTRA_TOKENS_315>|",
|
2550 |
+
"lstrip": false,
|
2551 |
+
"normalized": false,
|
2552 |
+
"rstrip": false,
|
2553 |
+
"single_word": false,
|
2554 |
+
"special": true
|
2555 |
+
},
|
2556 |
+
"151962": {
|
2557 |
+
"content": "|<EXTRA_TOKENS_316>|",
|
2558 |
+
"lstrip": false,
|
2559 |
+
"normalized": false,
|
2560 |
+
"rstrip": false,
|
2561 |
+
"single_word": false,
|
2562 |
+
"special": true
|
2563 |
+
},
|
2564 |
+
"151963": {
|
2565 |
+
"content": "|<EXTRA_TOKENS_317>|",
|
2566 |
+
"lstrip": false,
|
2567 |
+
"normalized": false,
|
2568 |
+
"rstrip": false,
|
2569 |
+
"single_word": false,
|
2570 |
+
"special": true
|
2571 |
+
},
|
2572 |
+
"151964": {
|
2573 |
+
"content": "|<EXTRA_TOKENS_318>|",
|
2574 |
+
"lstrip": false,
|
2575 |
+
"normalized": false,
|
2576 |
+
"rstrip": false,
|
2577 |
+
"single_word": false,
|
2578 |
+
"special": true
|
2579 |
+
},
|
2580 |
+
"151965": {
|
2581 |
+
"content": "|<EXTRA_TOKENS_319>|",
|
2582 |
+
"lstrip": false,
|
2583 |
+
"normalized": false,
|
2584 |
+
"rstrip": false,
|
2585 |
+
"single_word": false,
|
2586 |
+
"special": true
|
2587 |
+
},
|
2588 |
+
"151966": {
|
2589 |
+
"content": "|<EXTRA_TOKENS_320>|",
|
2590 |
+
"lstrip": false,
|
2591 |
+
"normalized": false,
|
2592 |
+
"rstrip": false,
|
2593 |
+
"single_word": false,
|
2594 |
+
"special": true
|
2595 |
+
},
|
2596 |
+
"151967": {
|
2597 |
+
"content": "|<EXTRA_TOKENS_321>|",
|
2598 |
+
"lstrip": false,
|
2599 |
+
"normalized": false,
|
2600 |
+
"rstrip": false,
|
2601 |
+
"single_word": false,
|
2602 |
+
"special": true
|
2603 |
+
},
|
2604 |
+
"151968": {
|
2605 |
+
"content": "|<EXTRA_TOKENS_322>|",
|
2606 |
+
"lstrip": false,
|
2607 |
+
"normalized": false,
|
2608 |
+
"rstrip": false,
|
2609 |
+
"single_word": false,
|
2610 |
+
"special": true
|
2611 |
+
},
|
2612 |
+
"151969": {
|
2613 |
+
"content": "|<EXTRA_TOKENS_323>|",
|
2614 |
+
"lstrip": false,
|
2615 |
+
"normalized": false,
|
2616 |
+
"rstrip": false,
|
2617 |
+
"single_word": false,
|
2618 |
+
"special": true
|
2619 |
+
},
|
2620 |
+
"151970": {
|
2621 |
+
"content": "|<EXTRA_TOKENS_324>|",
|
2622 |
+
"lstrip": false,
|
2623 |
+
"normalized": false,
|
2624 |
+
"rstrip": false,
|
2625 |
+
"single_word": false,
|
2626 |
+
"special": true
|
2627 |
+
},
|
2628 |
+
"151971": {
|
2629 |
+
"content": "|<EXTRA_TOKENS_325>|",
|
2630 |
+
"lstrip": false,
|
2631 |
+
"normalized": false,
|
2632 |
+
"rstrip": false,
|
2633 |
+
"single_word": false,
|
2634 |
+
"special": true
|
2635 |
+
},
|
2636 |
+
"151972": {
|
2637 |
+
"content": "|<EXTRA_TOKENS_326>|",
|
2638 |
+
"lstrip": false,
|
2639 |
+
"normalized": false,
|
2640 |
+
"rstrip": false,
|
2641 |
+
"single_word": false,
|
2642 |
+
"special": true
|
2643 |
+
},
|
2644 |
+
"151973": {
|
2645 |
+
"content": "|<EXTRA_TOKENS_327>|",
|
2646 |
+
"lstrip": false,
|
2647 |
+
"normalized": false,
|
2648 |
+
"rstrip": false,
|
2649 |
+
"single_word": false,
|
2650 |
+
"special": true
|
2651 |
+
},
|
2652 |
+
"151974": {
|
2653 |
+
"content": "|<EXTRA_TOKENS_328>|",
|
2654 |
+
"lstrip": false,
|
2655 |
+
"normalized": false,
|
2656 |
+
"rstrip": false,
|
2657 |
+
"single_word": false,
|
2658 |
+
"special": true
|
2659 |
+
},
|
2660 |
+
"151975": {
|
2661 |
+
"content": "|<EXTRA_TOKENS_329>|",
|
2662 |
+
"lstrip": false,
|
2663 |
+
"normalized": false,
|
2664 |
+
"rstrip": false,
|
2665 |
+
"single_word": false,
|
2666 |
+
"special": true
|
2667 |
+
},
|
2668 |
+
"151976": {
|
2669 |
+
"content": "|<EXTRA_TOKENS_330>|",
|
2670 |
+
"lstrip": false,
|
2671 |
+
"normalized": false,
|
2672 |
+
"rstrip": false,
|
2673 |
+
"single_word": false,
|
2674 |
+
"special": true
|
2675 |
+
},
|
2676 |
+
"151977": {
|
2677 |
+
"content": "|<EXTRA_TOKENS_331>|",
|
2678 |
+
"lstrip": false,
|
2679 |
+
"normalized": false,
|
2680 |
+
"rstrip": false,
|
2681 |
+
"single_word": false,
|
2682 |
+
"special": true
|
2683 |
+
},
|
2684 |
+
"151978": {
|
2685 |
+
"content": "|<EXTRA_TOKENS_332>|",
|
2686 |
+
"lstrip": false,
|
2687 |
+
"normalized": false,
|
2688 |
+
"rstrip": false,
|
2689 |
+
"single_word": false,
|
2690 |
+
"special": true
|
2691 |
+
},
|
2692 |
+
"151979": {
|
2693 |
+
"content": "|<EXTRA_TOKENS_333>|",
|
2694 |
+
"lstrip": false,
|
2695 |
+
"normalized": false,
|
2696 |
+
"rstrip": false,
|
2697 |
+
"single_word": false,
|
2698 |
+
"special": true
|
2699 |
+
},
|
2700 |
+
"151980": {
|
2701 |
+
"content": "|<EXTRA_TOKENS_334>|",
|
2702 |
+
"lstrip": false,
|
2703 |
+
"normalized": false,
|
2704 |
+
"rstrip": false,
|
2705 |
+
"single_word": false,
|
2706 |
+
"special": true
|
2707 |
+
},
|
2708 |
+
"151981": {
|
2709 |
+
"content": "|<EXTRA_TOKENS_335>|",
|
2710 |
+
"lstrip": false,
|
2711 |
+
"normalized": false,
|
2712 |
+
"rstrip": false,
|
2713 |
+
"single_word": false,
|
2714 |
+
"special": true
|
2715 |
+
},
|
2716 |
+
"151982": {
|
2717 |
+
"content": "|<EXTRA_TOKENS_336>|",
|
2718 |
+
"lstrip": false,
|
2719 |
+
"normalized": false,
|
2720 |
+
"rstrip": false,
|
2721 |
+
"single_word": false,
|
2722 |
+
"special": true
|
2723 |
+
},
|
2724 |
+
"151983": {
|
2725 |
+
"content": "|<EXTRA_TOKENS_337>|",
|
2726 |
+
"lstrip": false,
|
2727 |
+
"normalized": false,
|
2728 |
+
"rstrip": false,
|
2729 |
+
"single_word": false,
|
2730 |
+
"special": true
|
2731 |
+
},
|
2732 |
+
"151984": {
|
2733 |
+
"content": "|<EXTRA_TOKENS_338>|",
|
2734 |
+
"lstrip": false,
|
2735 |
+
"normalized": false,
|
2736 |
+
"rstrip": false,
|
2737 |
+
"single_word": false,
|
2738 |
+
"special": true
|
2739 |
+
},
|
2740 |
+
"151985": {
|
2741 |
+
"content": "|<EXTRA_TOKENS_339>|",
|
2742 |
+
"lstrip": false,
|
2743 |
+
"normalized": false,
|
2744 |
+
"rstrip": false,
|
2745 |
+
"single_word": false,
|
2746 |
+
"special": true
|
2747 |
+
},
|
2748 |
+
"151986": {
|
2749 |
+
"content": "|<EXTRA_TOKENS_340>|",
|
2750 |
+
"lstrip": false,
|
2751 |
+
"normalized": false,
|
2752 |
+
"rstrip": false,
|
2753 |
+
"single_word": false,
|
2754 |
+
"special": true
|
2755 |
+
},
|
2756 |
+
"151987": {
|
2757 |
+
"content": "|<EXTRA_TOKENS_341>|",
|
2758 |
+
"lstrip": false,
|
2759 |
+
"normalized": false,
|
2760 |
+
"rstrip": false,
|
2761 |
+
"single_word": false,
|
2762 |
+
"special": true
|
2763 |
+
},
|
2764 |
+
"151988": {
|
2765 |
+
"content": "|<EXTRA_TOKENS_342>|",
|
2766 |
+
"lstrip": false,
|
2767 |
+
"normalized": false,
|
2768 |
+
"rstrip": false,
|
2769 |
+
"single_word": false,
|
2770 |
+
"special": true
|
2771 |
+
},
|
2772 |
+
"151989": {
|
2773 |
+
"content": "|<EXTRA_TOKENS_343>|",
|
2774 |
+
"lstrip": false,
|
2775 |
+
"normalized": false,
|
2776 |
+
"rstrip": false,
|
2777 |
+
"single_word": false,
|
2778 |
+
"special": true
|
2779 |
+
},
|
2780 |
+
"151990": {
|
2781 |
+
"content": "|<EXTRA_TOKENS_344>|",
|
2782 |
+
"lstrip": false,
|
2783 |
+
"normalized": false,
|
2784 |
+
"rstrip": false,
|
2785 |
+
"single_word": false,
|
2786 |
+
"special": true
|
2787 |
+
},
|
2788 |
+
"151991": {
|
2789 |
+
"content": "|<EXTRA_TOKENS_345>|",
|
2790 |
+
"lstrip": false,
|
2791 |
+
"normalized": false,
|
2792 |
+
"rstrip": false,
|
2793 |
+
"single_word": false,
|
2794 |
+
"special": true
|
2795 |
+
},
|
2796 |
+
"151992": {
|
2797 |
+
"content": "|<EXTRA_TOKENS_346>|",
|
2798 |
+
"lstrip": false,
|
2799 |
+
"normalized": false,
|
2800 |
+
"rstrip": false,
|
2801 |
+
"single_word": false,
|
2802 |
+
"special": true
|
2803 |
+
},
|
2804 |
+
"151993": {
|
2805 |
+
"content": "|<EXTRA_TOKENS_347>|",
|
2806 |
+
"lstrip": false,
|
2807 |
+
"normalized": false,
|
2808 |
+
"rstrip": false,
|
2809 |
+
"single_word": false,
|
2810 |
+
"special": true
|
2811 |
+
},
|
2812 |
+
"151994": {
|
2813 |
+
"content": "|<EXTRA_TOKENS_348>|",
|
2814 |
+
"lstrip": false,
|
2815 |
+
"normalized": false,
|
2816 |
+
"rstrip": false,
|
2817 |
+
"single_word": false,
|
2818 |
+
"special": true
|
2819 |
+
},
|
2820 |
+
"151995": {
|
2821 |
+
"content": "|<EXTRA_TOKENS_349>|",
|
2822 |
+
"lstrip": false,
|
2823 |
+
"normalized": false,
|
2824 |
+
"rstrip": false,
|
2825 |
+
"single_word": false,
|
2826 |
+
"special": true
|
2827 |
+
},
|
2828 |
+
"151996": {
|
2829 |
+
"content": "|<EXTRA_TOKENS_350>|",
|
2830 |
+
"lstrip": false,
|
2831 |
+
"normalized": false,
|
2832 |
+
"rstrip": false,
|
2833 |
+
"single_word": false,
|
2834 |
+
"special": true
|
2835 |
+
},
|
2836 |
+
"151997": {
|
2837 |
+
"content": "|<EXTRA_TOKENS_351>|",
|
2838 |
+
"lstrip": false,
|
2839 |
+
"normalized": false,
|
2840 |
+
"rstrip": false,
|
2841 |
+
"single_word": false,
|
2842 |
+
"special": true
|
2843 |
+
},
|
2844 |
+
"151998": {
|
2845 |
+
"content": "|<EXTRA_TOKENS_352>|",
|
2846 |
+
"lstrip": false,
|
2847 |
+
"normalized": false,
|
2848 |
+
"rstrip": false,
|
2849 |
+
"single_word": false,
|
2850 |
+
"special": true
|
2851 |
+
},
|
2852 |
+
"151999": {
|
2853 |
+
"content": "|<EXTRA_TOKENS_353>|",
|
2854 |
+
"lstrip": false,
|
2855 |
+
"normalized": false,
|
2856 |
+
"rstrip": false,
|
2857 |
+
"single_word": false,
|
2858 |
+
"special": true
|
2859 |
+
},
|
2860 |
+
"152000": {
|
2861 |
+
"content": "|<EXTRA_TOKENS_354>|",
|
2862 |
+
"lstrip": false,
|
2863 |
+
"normalized": false,
|
2864 |
+
"rstrip": false,
|
2865 |
+
"single_word": false,
|
2866 |
+
"special": true
|
2867 |
+
},
|
2868 |
+
"152001": {
|
2869 |
+
"content": "|<EXTRA_TOKENS_355>|",
|
2870 |
+
"lstrip": false,
|
2871 |
+
"normalized": false,
|
2872 |
+
"rstrip": false,
|
2873 |
+
"single_word": false,
|
2874 |
+
"special": true
|
2875 |
+
},
|
2876 |
+
"152002": {
|
2877 |
+
"content": "|<EXTRA_TOKENS_356>|",
|
2878 |
+
"lstrip": false,
|
2879 |
+
"normalized": false,
|
2880 |
+
"rstrip": false,
|
2881 |
+
"single_word": false,
|
2882 |
+
"special": true
|
2883 |
+
},
|
2884 |
+
"152003": {
|
2885 |
+
"content": "|<EXTRA_TOKENS_357>|",
|
2886 |
+
"lstrip": false,
|
2887 |
+
"normalized": false,
|
2888 |
+
"rstrip": false,
|
2889 |
+
"single_word": false,
|
2890 |
+
"special": true
|
2891 |
+
},
|
2892 |
+
"152004": {
|
2893 |
+
"content": "|<EXTRA_TOKENS_358>|",
|
2894 |
+
"lstrip": false,
|
2895 |
+
"normalized": false,
|
2896 |
+
"rstrip": false,
|
2897 |
+
"single_word": false,
|
2898 |
+
"special": true
|
2899 |
+
},
|
2900 |
+
"152005": {
|
2901 |
+
"content": "|<EXTRA_TOKENS_359>|",
|
2902 |
+
"lstrip": false,
|
2903 |
+
"normalized": false,
|
2904 |
+
"rstrip": false,
|
2905 |
+
"single_word": false,
|
2906 |
+
"special": true
|
2907 |
+
},
|
2908 |
+
"152006": {
|
2909 |
+
"content": "|<EXTRA_TOKENS_360>|",
|
2910 |
+
"lstrip": false,
|
2911 |
+
"normalized": false,
|
2912 |
+
"rstrip": false,
|
2913 |
+
"single_word": false,
|
2914 |
+
"special": true
|
2915 |
+
},
|
2916 |
+
"152007": {
|
2917 |
+
"content": "|<EXTRA_TOKENS_361>|",
|
2918 |
+
"lstrip": false,
|
2919 |
+
"normalized": false,
|
2920 |
+
"rstrip": false,
|
2921 |
+
"single_word": false,
|
2922 |
+
"special": true
|
2923 |
+
},
|
2924 |
+
"152008": {
|
2925 |
+
"content": "|<EXTRA_TOKENS_362>|",
|
2926 |
+
"lstrip": false,
|
2927 |
+
"normalized": false,
|
2928 |
+
"rstrip": false,
|
2929 |
+
"single_word": false,
|
2930 |
+
"special": true
|
2931 |
+
},
|
2932 |
+
"152009": {
|
2933 |
+
"content": "|<EXTRA_TOKENS_363>|",
|
2934 |
+
"lstrip": false,
|
2935 |
+
"normalized": false,
|
2936 |
+
"rstrip": false,
|
2937 |
+
"single_word": false,
|
2938 |
+
"special": true
|
2939 |
+
},
|
2940 |
+
"152010": {
|
2941 |
+
"content": "|<EXTRA_TOKENS_364>|",
|
2942 |
+
"lstrip": false,
|
2943 |
+
"normalized": false,
|
2944 |
+
"rstrip": false,
|
2945 |
+
"single_word": false,
|
2946 |
+
"special": true
|
2947 |
+
},
|
2948 |
+
"152011": {
|
2949 |
+
"content": "|<EXTRA_TOKENS_365>|",
|
2950 |
+
"lstrip": false,
|
2951 |
+
"normalized": false,
|
2952 |
+
"rstrip": false,
|
2953 |
+
"single_word": false,
|
2954 |
+
"special": true
|
2955 |
+
},
|
2956 |
+
"152012": {
|
2957 |
+
"content": "|<EXTRA_TOKENS_366>|",
|
2958 |
+
"lstrip": false,
|
2959 |
+
"normalized": false,
|
2960 |
+
"rstrip": false,
|
2961 |
+
"single_word": false,
|
2962 |
+
"special": true
|
2963 |
+
},
|
2964 |
+
"152013": {
|
2965 |
+
"content": "|<EXTRA_TOKENS_367>|",
|
2966 |
+
"lstrip": false,
|
2967 |
+
"normalized": false,
|
2968 |
+
"rstrip": false,
|
2969 |
+
"single_word": false,
|
2970 |
+
"special": true
|
2971 |
+
},
|
2972 |
+
"152014": {
|
2973 |
+
"content": "|<EXTRA_TOKENS_368>|",
|
2974 |
+
"lstrip": false,
|
2975 |
+
"normalized": false,
|
2976 |
+
"rstrip": false,
|
2977 |
+
"single_word": false,
|
2978 |
+
"special": true
|
2979 |
+
},
|
2980 |
+
"152015": {
|
2981 |
+
"content": "|<EXTRA_TOKENS_369>|",
|
2982 |
+
"lstrip": false,
|
2983 |
+
"normalized": false,
|
2984 |
+
"rstrip": false,
|
2985 |
+
"single_word": false,
|
2986 |
+
"special": true
|
2987 |
+
},
|
2988 |
+
"152016": {
|
2989 |
+
"content": "|<EXTRA_TOKENS_370>|",
|
2990 |
+
"lstrip": false,
|
2991 |
+
"normalized": false,
|
2992 |
+
"rstrip": false,
|
2993 |
+
"single_word": false,
|
2994 |
+
"special": true
|
2995 |
+
},
|
2996 |
+
"152017": {
|
2997 |
+
"content": "|<EXTRA_TOKENS_371>|",
|
2998 |
+
"lstrip": false,
|
2999 |
+
"normalized": false,
|
3000 |
+
"rstrip": false,
|
3001 |
+
"single_word": false,
|
3002 |
+
"special": true
|
3003 |
+
},
|
3004 |
+
"152018": {
|
3005 |
+
"content": "|<EXTRA_TOKENS_372>|",
|
3006 |
+
"lstrip": false,
|
3007 |
+
"normalized": false,
|
3008 |
+
"rstrip": false,
|
3009 |
+
"single_word": false,
|
3010 |
+
"special": true
|
3011 |
+
},
|
3012 |
+
"152019": {
|
3013 |
+
"content": "|<EXTRA_TOKENS_373>|",
|
3014 |
+
"lstrip": false,
|
3015 |
+
"normalized": false,
|
3016 |
+
"rstrip": false,
|
3017 |
+
"single_word": false,
|
3018 |
+
"special": true
|
3019 |
+
},
|
3020 |
+
"152020": {
|
3021 |
+
"content": "|<EXTRA_TOKENS_374>|",
|
3022 |
+
"lstrip": false,
|
3023 |
+
"normalized": false,
|
3024 |
+
"rstrip": false,
|
3025 |
+
"single_word": false,
|
3026 |
+
"special": true
|
3027 |
+
},
|
3028 |
+
"152021": {
|
3029 |
+
"content": "|<EXTRA_TOKENS_375>|",
|
3030 |
+
"lstrip": false,
|
3031 |
+
"normalized": false,
|
3032 |
+
"rstrip": false,
|
3033 |
+
"single_word": false,
|
3034 |
+
"special": true
|
3035 |
+
},
|
3036 |
+
"152022": {
|
3037 |
+
"content": "|<EXTRA_TOKENS_376>|",
|
3038 |
+
"lstrip": false,
|
3039 |
+
"normalized": false,
|
3040 |
+
"rstrip": false,
|
3041 |
+
"single_word": false,
|
3042 |
+
"special": true
|
3043 |
+
},
|
3044 |
+
"152023": {
|
3045 |
+
"content": "|<EXTRA_TOKENS_377>|",
|
3046 |
+
"lstrip": false,
|
3047 |
+
"normalized": false,
|
3048 |
+
"rstrip": false,
|
3049 |
+
"single_word": false,
|
3050 |
+
"special": true
|
3051 |
+
},
|
3052 |
+
"152024": {
|
3053 |
+
"content": "|<EXTRA_TOKENS_378>|",
|
3054 |
+
"lstrip": false,
|
3055 |
+
"normalized": false,
|
3056 |
+
"rstrip": false,
|
3057 |
+
"single_word": false,
|
3058 |
+
"special": true
|
3059 |
+
},
|
3060 |
+
"152025": {
|
3061 |
+
"content": "|<EXTRA_TOKENS_379>|",
|
3062 |
+
"lstrip": false,
|
3063 |
+
"normalized": false,
|
3064 |
+
"rstrip": false,
|
3065 |
+
"single_word": false,
|
3066 |
+
"special": true
|
3067 |
+
},
|
3068 |
+
"152026": {
|
3069 |
+
"content": "|<EXTRA_TOKENS_380>|",
|
3070 |
+
"lstrip": false,
|
3071 |
+
"normalized": false,
|
3072 |
+
"rstrip": false,
|
3073 |
+
"single_word": false,
|
3074 |
+
"special": true
|
3075 |
+
},
|
3076 |
+
"152027": {
|
3077 |
+
"content": "|<EXTRA_TOKENS_381>|",
|
3078 |
+
"lstrip": false,
|
3079 |
+
"normalized": false,
|
3080 |
+
"rstrip": false,
|
3081 |
+
"single_word": false,
|
3082 |
+
"special": true
|
3083 |
+
},
|
3084 |
+
"152028": {
|
3085 |
+
"content": "|<EXTRA_TOKENS_382>|",
|
3086 |
+
"lstrip": false,
|
3087 |
+
"normalized": false,
|
3088 |
+
"rstrip": false,
|
3089 |
+
"single_word": false,
|
3090 |
+
"special": true
|
3091 |
+
},
|
3092 |
+
"152029": {
|
3093 |
+
"content": "|<EXTRA_TOKENS_383>|",
|
3094 |
+
"lstrip": false,
|
3095 |
+
"normalized": false,
|
3096 |
+
"rstrip": false,
|
3097 |
+
"single_word": false,
|
3098 |
+
"special": true
|
3099 |
+
},
|
3100 |
+
"152030": {
|
3101 |
+
"content": "|<EXTRA_TOKENS_384>|",
|
3102 |
+
"lstrip": false,
|
3103 |
+
"normalized": false,
|
3104 |
+
"rstrip": false,
|
3105 |
+
"single_word": false,
|
3106 |
+
"special": true
|
3107 |
+
},
|
3108 |
+
"152031": {
|
3109 |
+
"content": "|<EXTRA_TOKENS_385>|",
|
3110 |
+
"lstrip": false,
|
3111 |
+
"normalized": false,
|
3112 |
+
"rstrip": false,
|
3113 |
+
"single_word": false,
|
3114 |
+
"special": true
|
3115 |
+
},
|
3116 |
+
"152032": {
|
3117 |
+
"content": "|<EXTRA_TOKENS_386>|",
|
3118 |
+
"lstrip": false,
|
3119 |
+
"normalized": false,
|
3120 |
+
"rstrip": false,
|
3121 |
+
"single_word": false,
|
3122 |
+
"special": true
|
3123 |
+
},
|
3124 |
+
"152033": {
|
3125 |
+
"content": "|<EXTRA_TOKENS_387>|",
|
3126 |
+
"lstrip": false,
|
3127 |
+
"normalized": false,
|
3128 |
+
"rstrip": false,
|
3129 |
+
"single_word": false,
|
3130 |
+
"special": true
|
3131 |
+
},
|
3132 |
+
"152034": {
|
3133 |
+
"content": "|<EXTRA_TOKENS_388>|",
|
3134 |
+
"lstrip": false,
|
3135 |
+
"normalized": false,
|
3136 |
+
"rstrip": false,
|
3137 |
+
"single_word": false,
|
3138 |
+
"special": true
|
3139 |
+
},
|
3140 |
+
"152035": {
|
3141 |
+
"content": "|<EXTRA_TOKENS_389>|",
|
3142 |
+
"lstrip": false,
|
3143 |
+
"normalized": false,
|
3144 |
+
"rstrip": false,
|
3145 |
+
"single_word": false,
|
3146 |
+
"special": true
|
3147 |
+
},
|
3148 |
+
"152036": {
|
3149 |
+
"content": "|<EXTRA_TOKENS_390>|",
|
3150 |
+
"lstrip": false,
|
3151 |
+
"normalized": false,
|
3152 |
+
"rstrip": false,
|
3153 |
+
"single_word": false,
|
3154 |
+
"special": true
|
3155 |
+
},
|
3156 |
+
"152037": {
|
3157 |
+
"content": "|<EXTRA_TOKENS_391>|",
|
3158 |
+
"lstrip": false,
|
3159 |
+
"normalized": false,
|
3160 |
+
"rstrip": false,
|
3161 |
+
"single_word": false,
|
3162 |
+
"special": true
|
3163 |
+
},
|
3164 |
+
"152038": {
|
3165 |
+
"content": "|<EXTRA_TOKENS_392>|",
|
3166 |
+
"lstrip": false,
|
3167 |
+
"normalized": false,
|
3168 |
+
"rstrip": false,
|
3169 |
+
"single_word": false,
|
3170 |
+
"special": true
|
3171 |
+
},
|
3172 |
+
"152039": {
|
3173 |
+
"content": "|<EXTRA_TOKENS_393>|",
|
3174 |
+
"lstrip": false,
|
3175 |
+
"normalized": false,
|
3176 |
+
"rstrip": false,
|
3177 |
+
"single_word": false,
|
3178 |
+
"special": true
|
3179 |
+
},
|
3180 |
+
"152040": {
|
3181 |
+
"content": "|<EXTRA_TOKENS_394>|",
|
3182 |
+
"lstrip": false,
|
3183 |
+
"normalized": false,
|
3184 |
+
"rstrip": false,
|
3185 |
+
"single_word": false,
|
3186 |
+
"special": true
|
3187 |
+
},
|
3188 |
+
"152041": {
|
3189 |
+
"content": "|<EXTRA_TOKENS_395>|",
|
3190 |
+
"lstrip": false,
|
3191 |
+
"normalized": false,
|
3192 |
+
"rstrip": false,
|
3193 |
+
"single_word": false,
|
3194 |
+
"special": true
|
3195 |
+
},
|
3196 |
+
"152042": {
|
3197 |
+
"content": "|<EXTRA_TOKENS_396>|",
|
3198 |
+
"lstrip": false,
|
3199 |
+
"normalized": false,
|
3200 |
+
"rstrip": false,
|
3201 |
+
"single_word": false,
|
3202 |
+
"special": true
|
3203 |
+
},
|
3204 |
+
"152043": {
|
3205 |
+
"content": "|<EXTRA_TOKENS_397>|",
|
3206 |
+
"lstrip": false,
|
3207 |
+
"normalized": false,
|
3208 |
+
"rstrip": false,
|
3209 |
+
"single_word": false,
|
3210 |
+
"special": true
|
3211 |
+
},
|
3212 |
+
"152044": {
|
3213 |
+
"content": "|<EXTRA_TOKENS_398>|",
|
3214 |
+
"lstrip": false,
|
3215 |
+
"normalized": false,
|
3216 |
+
"rstrip": false,
|
3217 |
+
"single_word": false,
|
3218 |
+
"special": true
|
3219 |
+
},
|
3220 |
+
"152045": {
|
3221 |
+
"content": "|<EXTRA_TOKENS_399>|",
|
3222 |
+
"lstrip": false,
|
3223 |
+
"normalized": false,
|
3224 |
+
"rstrip": false,
|
3225 |
+
"single_word": false,
|
3226 |
+
"special": true
|
3227 |
+
},
|
3228 |
+
"152046": {
|
3229 |
+
"content": "|<EXTRA_TOKENS_400>|",
|
3230 |
+
"lstrip": false,
|
3231 |
+
"normalized": false,
|
3232 |
+
"rstrip": false,
|
3233 |
+
"single_word": false,
|
3234 |
+
"special": true
|
3235 |
+
},
|
3236 |
+
"152047": {
|
3237 |
+
"content": "|<EXTRA_TOKENS_401>|",
|
3238 |
+
"lstrip": false,
|
3239 |
+
"normalized": false,
|
3240 |
+
"rstrip": false,
|
3241 |
+
"single_word": false,
|
3242 |
+
"special": true
|
3243 |
+
},
|
3244 |
+
"152048": {
|
3245 |
+
"content": "|<EXTRA_TOKENS_402>|",
|
3246 |
+
"lstrip": false,
|
3247 |
+
"normalized": false,
|
3248 |
+
"rstrip": false,
|
3249 |
+
"single_word": false,
|
3250 |
+
"special": true
|
3251 |
+
},
|
3252 |
+
"152049": {
|
3253 |
+
"content": "|<EXTRA_TOKENS_403>|",
|
3254 |
+
"lstrip": false,
|
3255 |
+
"normalized": false,
|
3256 |
+
"rstrip": false,
|
3257 |
+
"single_word": false,
|
3258 |
+
"special": true
|
3259 |
+
},
|
3260 |
+
"152050": {
|
3261 |
+
"content": "|<EXTRA_TOKENS_404>|",
|
3262 |
+
"lstrip": false,
|
3263 |
+
"normalized": false,
|
3264 |
+
"rstrip": false,
|
3265 |
+
"single_word": false,
|
3266 |
+
"special": true
|
3267 |
+
},
|
3268 |
+
"152051": {
|
3269 |
+
"content": "|<EXTRA_TOKENS_405>|",
|
3270 |
+
"lstrip": false,
|
3271 |
+
"normalized": false,
|
3272 |
+
"rstrip": false,
|
3273 |
+
"single_word": false,
|
3274 |
+
"special": true
|
3275 |
+
},
|
3276 |
+
"152052": {
|
3277 |
+
"content": "|<EXTRA_TOKENS_406>|",
|
3278 |
+
"lstrip": false,
|
3279 |
+
"normalized": false,
|
3280 |
+
"rstrip": false,
|
3281 |
+
"single_word": false,
|
3282 |
+
"special": true
|
3283 |
+
},
|
3284 |
+
"152053": {
|
3285 |
+
"content": "|<EXTRA_TOKENS_407>|",
|
3286 |
+
"lstrip": false,
|
3287 |
+
"normalized": false,
|
3288 |
+
"rstrip": false,
|
3289 |
+
"single_word": false,
|
3290 |
+
"special": true
|
3291 |
+
},
|
3292 |
+
"152054": {
|
3293 |
+
"content": "|<EXTRA_TOKENS_408>|",
|
3294 |
+
"lstrip": false,
|
3295 |
+
"normalized": false,
|
3296 |
+
"rstrip": false,
|
3297 |
+
"single_word": false,
|
3298 |
+
"special": true
|
3299 |
+
},
|
3300 |
+
"152055": {
|
3301 |
+
"content": "|<EXTRA_TOKENS_409>|",
|
3302 |
+
"lstrip": false,
|
3303 |
+
"normalized": false,
|
3304 |
+
"rstrip": false,
|
3305 |
+
"single_word": false,
|
3306 |
+
"special": true
|
3307 |
+
},
|
3308 |
+
"152056": {
|
3309 |
+
"content": "|<EXTRA_TOKENS_410>|",
|
3310 |
+
"lstrip": false,
|
3311 |
+
"normalized": false,
|
3312 |
+
"rstrip": false,
|
3313 |
+
"single_word": false,
|
3314 |
+
"special": true
|
3315 |
+
},
|
3316 |
+
"152057": {
|
3317 |
+
"content": "|<EXTRA_TOKENS_411>|",
|
3318 |
+
"lstrip": false,
|
3319 |
+
"normalized": false,
|
3320 |
+
"rstrip": false,
|
3321 |
+
"single_word": false,
|
3322 |
+
"special": true
|
3323 |
+
},
|
3324 |
+
"152058": {
|
3325 |
+
"content": "|<EXTRA_TOKENS_412>|",
|
3326 |
+
"lstrip": false,
|
3327 |
+
"normalized": false,
|
3328 |
+
"rstrip": false,
|
3329 |
+
"single_word": false,
|
3330 |
+
"special": true
|
3331 |
+
},
|
3332 |
+
"152059": {
|
3333 |
+
"content": "|<EXTRA_TOKENS_413>|",
|
3334 |
+
"lstrip": false,
|
3335 |
+
"normalized": false,
|
3336 |
+
"rstrip": false,
|
3337 |
+
"single_word": false,
|
3338 |
+
"special": true
|
3339 |
+
},
|
3340 |
+
"152060": {
|
3341 |
+
"content": "|<EXTRA_TOKENS_414>|",
|
3342 |
+
"lstrip": false,
|
3343 |
+
"normalized": false,
|
3344 |
+
"rstrip": false,
|
3345 |
+
"single_word": false,
|
3346 |
+
"special": true
|
3347 |
+
},
|
3348 |
+
"152061": {
|
3349 |
+
"content": "|<EXTRA_TOKENS_415>|",
|
3350 |
+
"lstrip": false,
|
3351 |
+
"normalized": false,
|
3352 |
+
"rstrip": false,
|
3353 |
+
"single_word": false,
|
3354 |
+
"special": true
|
3355 |
+
},
|
3356 |
+
"152062": {
|
3357 |
+
"content": "|<EXTRA_TOKENS_416>|",
|
3358 |
+
"lstrip": false,
|
3359 |
+
"normalized": false,
|
3360 |
+
"rstrip": false,
|
3361 |
+
"single_word": false,
|
3362 |
+
"special": true
|
3363 |
+
},
|
3364 |
+
"152063": {
|
3365 |
+
"content": "|<EXTRA_TOKENS_417>|",
|
3366 |
+
"lstrip": false,
|
3367 |
+
"normalized": false,
|
3368 |
+
"rstrip": false,
|
3369 |
+
"single_word": false,
|
3370 |
+
"special": true
|
3371 |
+
},
|
3372 |
+
"152064": {
|
3373 |
"content": "<im_start>",
|
3374 |
"lstrip": false,
|
3375 |
"normalized": false,
|
|
|
3377 |
"single_word": false,
|
3378 |
"special": true
|
3379 |
},
|
3380 |
+
"152065": {
|
3381 |
"content": "<im_end>",
|
3382 |
"lstrip": false,
|
3383 |
"normalized": false,
|
|
|
3385 |
"single_word": false,
|
3386 |
"special": true
|
3387 |
},
|
3388 |
+
"152066": {
|
3389 |
"content": "<im_patch>",
|
3390 |
"lstrip": false,
|
3391 |
"normalized": false,
|
|
|
3393 |
"single_word": false,
|
3394 |
"special": true
|
3395 |
},
|
3396 |
+
"152067": {
|
3397 |
"content": "<im_col>",
|
3398 |
"lstrip": false,
|
3399 |
"normalized": false,
|
|
|
3401 |
"single_word": false,
|
3402 |
"special": true
|
3403 |
},
|
3404 |
+
"152068": {
|
3405 |
"content": "<|image|>",
|
3406 |
"lstrip": false,
|
3407 |
"normalized": false,
|
|
|
3411 |
}
|
3412 |
},
|
3413 |
"additional_special_tokens": [
|
3414 |
+
"|<EXTRA_TOKENS_0>|",
|
3415 |
+
"|<EXTRA_TOKENS_1>|",
|
3416 |
+
"|<EXTRA_TOKENS_2>|",
|
3417 |
+
"|<EXTRA_TOKENS_3>|",
|
3418 |
+
"|<EXTRA_TOKENS_4>|",
|
3419 |
+
"|<EXTRA_TOKENS_5>|",
|
3420 |
+
"|<EXTRA_TOKENS_6>|",
|
3421 |
+
"|<EXTRA_TOKENS_7>|",
|
3422 |
+
"|<EXTRA_TOKENS_8>|",
|
3423 |
+
"|<EXTRA_TOKENS_9>|",
|
3424 |
+
"|<EXTRA_TOKENS_10>|",
|
3425 |
+
"|<EXTRA_TOKENS_11>|",
|
3426 |
+
"|<EXTRA_TOKENS_12>|",
|
3427 |
+
"|<EXTRA_TOKENS_13>|",
|
3428 |
+
"|<EXTRA_TOKENS_14>|",
|
3429 |
+
"|<EXTRA_TOKENS_15>|",
|
3430 |
+
"|<EXTRA_TOKENS_16>|",
|
3431 |
+
"|<EXTRA_TOKENS_17>|",
|
3432 |
+
"|<EXTRA_TOKENS_18>|",
|
3433 |
+
"|<EXTRA_TOKENS_19>|",
|
3434 |
+
"|<EXTRA_TOKENS_20>|",
|
3435 |
+
"|<EXTRA_TOKENS_21>|",
|
3436 |
+
"|<EXTRA_TOKENS_22>|",
|
3437 |
+
"|<EXTRA_TOKENS_23>|",
|
3438 |
+
"|<EXTRA_TOKENS_24>|",
|
3439 |
+
"|<EXTRA_TOKENS_25>|",
|
3440 |
+
"|<EXTRA_TOKENS_26>|",
|
3441 |
+
"|<EXTRA_TOKENS_27>|",
|
3442 |
+
"|<EXTRA_TOKENS_28>|",
|
3443 |
+
"|<EXTRA_TOKENS_29>|",
|
3444 |
+
"|<EXTRA_TOKENS_30>|",
|
3445 |
+
"|<EXTRA_TOKENS_31>|",
|
3446 |
+
"|<EXTRA_TOKENS_32>|",
|
3447 |
+
"|<EXTRA_TOKENS_33>|",
|
3448 |
+
"|<EXTRA_TOKENS_34>|",
|
3449 |
+
"|<EXTRA_TOKENS_35>|",
|
3450 |
+
"|<EXTRA_TOKENS_36>|",
|
3451 |
+
"|<EXTRA_TOKENS_37>|",
|
3452 |
+
"|<EXTRA_TOKENS_38>|",
|
3453 |
+
"|<EXTRA_TOKENS_39>|",
|
3454 |
+
"|<EXTRA_TOKENS_40>|",
|
3455 |
+
"|<EXTRA_TOKENS_41>|",
|
3456 |
+
"|<EXTRA_TOKENS_42>|",
|
3457 |
+
"|<EXTRA_TOKENS_43>|",
|
3458 |
+
"|<EXTRA_TOKENS_44>|",
|
3459 |
+
"|<EXTRA_TOKENS_45>|",
|
3460 |
+
"|<EXTRA_TOKENS_46>|",
|
3461 |
+
"|<EXTRA_TOKENS_47>|",
|
3462 |
+
"|<EXTRA_TOKENS_48>|",
|
3463 |
+
"|<EXTRA_TOKENS_49>|",
|
3464 |
+
"|<EXTRA_TOKENS_50>|",
|
3465 |
+
"|<EXTRA_TOKENS_51>|",
|
3466 |
+
"|<EXTRA_TOKENS_52>|",
|
3467 |
+
"|<EXTRA_TOKENS_53>|",
|
3468 |
+
"|<EXTRA_TOKENS_54>|",
|
3469 |
+
"|<EXTRA_TOKENS_55>|",
|
3470 |
+
"|<EXTRA_TOKENS_56>|",
|
3471 |
+
"|<EXTRA_TOKENS_57>|",
|
3472 |
+
"|<EXTRA_TOKENS_58>|",
|
3473 |
+
"|<EXTRA_TOKENS_59>|",
|
3474 |
+
"|<EXTRA_TOKENS_60>|",
|
3475 |
+
"|<EXTRA_TOKENS_61>|",
|
3476 |
+
"|<EXTRA_TOKENS_62>|",
|
3477 |
+
"|<EXTRA_TOKENS_63>|",
|
3478 |
+
"|<EXTRA_TOKENS_64>|",
|
3479 |
+
"|<EXTRA_TOKENS_65>|",
|
3480 |
+
"|<EXTRA_TOKENS_66>|",
|
3481 |
+
"|<EXTRA_TOKENS_67>|",
|
3482 |
+
"|<EXTRA_TOKENS_68>|",
|
3483 |
+
"|<EXTRA_TOKENS_69>|",
|
3484 |
+
"|<EXTRA_TOKENS_70>|",
|
3485 |
+
"|<EXTRA_TOKENS_71>|",
|
3486 |
+
"|<EXTRA_TOKENS_72>|",
|
3487 |
+
"|<EXTRA_TOKENS_73>|",
|
3488 |
+
"|<EXTRA_TOKENS_74>|",
|
3489 |
+
"|<EXTRA_TOKENS_75>|",
|
3490 |
+
"|<EXTRA_TOKENS_76>|",
|
3491 |
+
"|<EXTRA_TOKENS_77>|",
|
3492 |
+
"|<EXTRA_TOKENS_78>|",
|
3493 |
+
"|<EXTRA_TOKENS_79>|",
|
3494 |
+
"|<EXTRA_TOKENS_80>|",
|
3495 |
+
"|<EXTRA_TOKENS_81>|",
|
3496 |
+
"|<EXTRA_TOKENS_82>|",
|
3497 |
+
"|<EXTRA_TOKENS_83>|",
|
3498 |
+
"|<EXTRA_TOKENS_84>|",
|
3499 |
+
"|<EXTRA_TOKENS_85>|",
|
3500 |
+
"|<EXTRA_TOKENS_86>|",
|
3501 |
+
"|<EXTRA_TOKENS_87>|",
|
3502 |
+
"|<EXTRA_TOKENS_88>|",
|
3503 |
+
"|<EXTRA_TOKENS_89>|",
|
3504 |
+
"|<EXTRA_TOKENS_90>|",
|
3505 |
+
"|<EXTRA_TOKENS_91>|",
|
3506 |
+
"|<EXTRA_TOKENS_92>|",
|
3507 |
+
"|<EXTRA_TOKENS_93>|",
|
3508 |
+
"|<EXTRA_TOKENS_94>|",
|
3509 |
+
"|<EXTRA_TOKENS_95>|",
|
3510 |
+
"|<EXTRA_TOKENS_96>|",
|
3511 |
+
"|<EXTRA_TOKENS_97>|",
|
3512 |
+
"|<EXTRA_TOKENS_98>|",
|
3513 |
+
"|<EXTRA_TOKENS_99>|",
|
3514 |
+
"|<EXTRA_TOKENS_100>|",
|
3515 |
+
"|<EXTRA_TOKENS_101>|",
|
3516 |
+
"|<EXTRA_TOKENS_102>|",
|
3517 |
+
"|<EXTRA_TOKENS_103>|",
|
3518 |
+
"|<EXTRA_TOKENS_104>|",
|
3519 |
+
"|<EXTRA_TOKENS_105>|",
|
3520 |
+
"|<EXTRA_TOKENS_106>|",
|
3521 |
+
"|<EXTRA_TOKENS_107>|",
|
3522 |
+
"|<EXTRA_TOKENS_108>|",
|
3523 |
+
"|<EXTRA_TOKENS_109>|",
|
3524 |
+
"|<EXTRA_TOKENS_110>|",
|
3525 |
+
"|<EXTRA_TOKENS_111>|",
|
3526 |
+
"|<EXTRA_TOKENS_112>|",
|
3527 |
+
"|<EXTRA_TOKENS_113>|",
|
3528 |
+
"|<EXTRA_TOKENS_114>|",
|
3529 |
+
"|<EXTRA_TOKENS_115>|",
|
3530 |
+
"|<EXTRA_TOKENS_116>|",
|
3531 |
+
"|<EXTRA_TOKENS_117>|",
|
3532 |
+
"|<EXTRA_TOKENS_118>|",
|
3533 |
+
"|<EXTRA_TOKENS_119>|",
|
3534 |
+
"|<EXTRA_TOKENS_120>|",
|
3535 |
+
"|<EXTRA_TOKENS_121>|",
|
3536 |
+
"|<EXTRA_TOKENS_122>|",
|
3537 |
+
"|<EXTRA_TOKENS_123>|",
|
3538 |
+
"|<EXTRA_TOKENS_124>|",
|
3539 |
+
"|<EXTRA_TOKENS_125>|",
|
3540 |
+
"|<EXTRA_TOKENS_126>|",
|
3541 |
+
"|<EXTRA_TOKENS_127>|",
|
3542 |
+
"|<EXTRA_TOKENS_128>|",
|
3543 |
+
"|<EXTRA_TOKENS_129>|",
|
3544 |
+
"|<EXTRA_TOKENS_130>|",
|
3545 |
+
"|<EXTRA_TOKENS_131>|",
|
3546 |
+
"|<EXTRA_TOKENS_132>|",
|
3547 |
+
"|<EXTRA_TOKENS_133>|",
|
3548 |
+
"|<EXTRA_TOKENS_134>|",
|
3549 |
+
"|<EXTRA_TOKENS_135>|",
|
3550 |
+
"|<EXTRA_TOKENS_136>|",
|
3551 |
+
"|<EXTRA_TOKENS_137>|",
|
3552 |
+
"|<EXTRA_TOKENS_138>|",
|
3553 |
+
"|<EXTRA_TOKENS_139>|",
|
3554 |
+
"|<EXTRA_TOKENS_140>|",
|
3555 |
+
"|<EXTRA_TOKENS_141>|",
|
3556 |
+
"|<EXTRA_TOKENS_142>|",
|
3557 |
+
"|<EXTRA_TOKENS_143>|",
|
3558 |
+
"|<EXTRA_TOKENS_144>|",
|
3559 |
+
"|<EXTRA_TOKENS_145>|",
|
3560 |
+
"|<EXTRA_TOKENS_146>|",
|
3561 |
+
"|<EXTRA_TOKENS_147>|",
|
3562 |
+
"|<EXTRA_TOKENS_148>|",
|
3563 |
+
"|<EXTRA_TOKENS_149>|",
|
3564 |
+
"|<EXTRA_TOKENS_150>|",
|
3565 |
+
"|<EXTRA_TOKENS_151>|",
|
3566 |
+
"|<EXTRA_TOKENS_152>|",
|
3567 |
+
"|<EXTRA_TOKENS_153>|",
|
3568 |
+
"|<EXTRA_TOKENS_154>|",
|
3569 |
+
"|<EXTRA_TOKENS_155>|",
|
3570 |
+
"|<EXTRA_TOKENS_156>|",
|
3571 |
+
"|<EXTRA_TOKENS_157>|",
|
3572 |
+
"|<EXTRA_TOKENS_158>|",
|
3573 |
+
"|<EXTRA_TOKENS_159>|",
|
3574 |
+
"|<EXTRA_TOKENS_160>|",
|
3575 |
+
"|<EXTRA_TOKENS_161>|",
|
3576 |
+
"|<EXTRA_TOKENS_162>|",
|
3577 |
+
"|<EXTRA_TOKENS_163>|",
|
3578 |
+
"|<EXTRA_TOKENS_164>|",
|
3579 |
+
"|<EXTRA_TOKENS_165>|",
|
3580 |
+
"|<EXTRA_TOKENS_166>|",
|
3581 |
+
"|<EXTRA_TOKENS_167>|",
|
3582 |
+
"|<EXTRA_TOKENS_168>|",
|
3583 |
+
"|<EXTRA_TOKENS_169>|",
|
3584 |
+
"|<EXTRA_TOKENS_170>|",
|
3585 |
+
"|<EXTRA_TOKENS_171>|",
|
3586 |
+
"|<EXTRA_TOKENS_172>|",
|
3587 |
+
"|<EXTRA_TOKENS_173>|",
|
3588 |
+
"|<EXTRA_TOKENS_174>|",
|
3589 |
+
"|<EXTRA_TOKENS_175>|",
|
3590 |
+
"|<EXTRA_TOKENS_176>|",
|
3591 |
+
"|<EXTRA_TOKENS_177>|",
|
3592 |
+
"|<EXTRA_TOKENS_178>|",
|
3593 |
+
"|<EXTRA_TOKENS_179>|",
|
3594 |
+
"|<EXTRA_TOKENS_180>|",
|
3595 |
+
"|<EXTRA_TOKENS_181>|",
|
3596 |
+
"|<EXTRA_TOKENS_182>|",
|
3597 |
+
"|<EXTRA_TOKENS_183>|",
|
3598 |
+
"|<EXTRA_TOKENS_184>|",
|
3599 |
+
"|<EXTRA_TOKENS_185>|",
|
3600 |
+
"|<EXTRA_TOKENS_186>|",
|
3601 |
+
"|<EXTRA_TOKENS_187>|",
|
3602 |
+
"|<EXTRA_TOKENS_188>|",
|
3603 |
+
"|<EXTRA_TOKENS_189>|",
|
3604 |
+
"|<EXTRA_TOKENS_190>|",
|
3605 |
+
"|<EXTRA_TOKENS_191>|",
|
3606 |
+
"|<EXTRA_TOKENS_192>|",
|
3607 |
+
"|<EXTRA_TOKENS_193>|",
|
3608 |
+
"|<EXTRA_TOKENS_194>|",
|
3609 |
+
"|<EXTRA_TOKENS_195>|",
|
3610 |
+
"|<EXTRA_TOKENS_196>|",
|
3611 |
+
"|<EXTRA_TOKENS_197>|",
|
3612 |
+
"|<EXTRA_TOKENS_198>|",
|
3613 |
+
"|<EXTRA_TOKENS_199>|",
|
3614 |
+
"|<EXTRA_TOKENS_200>|",
|
3615 |
+
"|<EXTRA_TOKENS_201>|",
|
3616 |
+
"|<EXTRA_TOKENS_202>|",
|
3617 |
+
"|<EXTRA_TOKENS_203>|",
|
3618 |
+
"|<EXTRA_TOKENS_204>|",
|
3619 |
+
"|<EXTRA_TOKENS_205>|",
|
3620 |
+
"|<EXTRA_TOKENS_206>|",
|
3621 |
+
"|<EXTRA_TOKENS_207>|",
|
3622 |
+
"|<EXTRA_TOKENS_208>|",
|
3623 |
+
"|<EXTRA_TOKENS_209>|",
|
3624 |
+
"|<EXTRA_TOKENS_210>|",
|
3625 |
+
"|<EXTRA_TOKENS_211>|",
|
3626 |
+
"|<EXTRA_TOKENS_212>|",
|
3627 |
+
"|<EXTRA_TOKENS_213>|",
|
3628 |
+
"|<EXTRA_TOKENS_214>|",
|
3629 |
+
"|<EXTRA_TOKENS_215>|",
|
3630 |
+
"|<EXTRA_TOKENS_216>|",
|
3631 |
+
"|<EXTRA_TOKENS_217>|",
|
3632 |
+
"|<EXTRA_TOKENS_218>|",
|
3633 |
+
"|<EXTRA_TOKENS_219>|",
|
3634 |
+
"|<EXTRA_TOKENS_220>|",
|
3635 |
+
"|<EXTRA_TOKENS_221>|",
|
3636 |
+
"|<EXTRA_TOKENS_222>|",
|
3637 |
+
"|<EXTRA_TOKENS_223>|",
|
3638 |
+
"|<EXTRA_TOKENS_224>|",
|
3639 |
+
"|<EXTRA_TOKENS_225>|",
|
3640 |
+
"|<EXTRA_TOKENS_226>|",
|
3641 |
+
"|<EXTRA_TOKENS_227>|",
|
3642 |
+
"|<EXTRA_TOKENS_228>|",
|
3643 |
+
"|<EXTRA_TOKENS_229>|",
|
3644 |
+
"|<EXTRA_TOKENS_230>|",
|
3645 |
+
"|<EXTRA_TOKENS_231>|",
|
3646 |
+
"|<EXTRA_TOKENS_232>|",
|
3647 |
+
"|<EXTRA_TOKENS_233>|",
|
3648 |
+
"|<EXTRA_TOKENS_234>|",
|
3649 |
+
"|<EXTRA_TOKENS_235>|",
|
3650 |
+
"|<EXTRA_TOKENS_236>|",
|
3651 |
+
"|<EXTRA_TOKENS_237>|",
|
3652 |
+
"|<EXTRA_TOKENS_238>|",
|
3653 |
+
"|<EXTRA_TOKENS_239>|",
|
3654 |
+
"|<EXTRA_TOKENS_240>|",
|
3655 |
+
"|<EXTRA_TOKENS_241>|",
|
3656 |
+
"|<EXTRA_TOKENS_242>|",
|
3657 |
+
"|<EXTRA_TOKENS_243>|",
|
3658 |
+
"|<EXTRA_TOKENS_244>|",
|
3659 |
+
"|<EXTRA_TOKENS_245>|",
|
3660 |
+
"|<EXTRA_TOKENS_246>|",
|
3661 |
+
"|<EXTRA_TOKENS_247>|",
|
3662 |
+
"|<EXTRA_TOKENS_248>|",
|
3663 |
+
"|<EXTRA_TOKENS_249>|",
|
3664 |
+
"|<EXTRA_TOKENS_250>|",
|
3665 |
+
"|<EXTRA_TOKENS_251>|",
|
3666 |
+
"|<EXTRA_TOKENS_252>|",
|
3667 |
+
"|<EXTRA_TOKENS_253>|",
|
3668 |
+
"|<EXTRA_TOKENS_254>|",
|
3669 |
+
"|<EXTRA_TOKENS_255>|",
|
3670 |
+
"|<EXTRA_TOKENS_256>|",
|
3671 |
+
"|<EXTRA_TOKENS_257>|",
|
3672 |
+
"|<EXTRA_TOKENS_258>|",
|
3673 |
+
"|<EXTRA_TOKENS_259>|",
|
3674 |
+
"|<EXTRA_TOKENS_260>|",
|
3675 |
+
"|<EXTRA_TOKENS_261>|",
|
3676 |
+
"|<EXTRA_TOKENS_262>|",
|
3677 |
+
"|<EXTRA_TOKENS_263>|",
|
3678 |
+
"|<EXTRA_TOKENS_264>|",
|
3679 |
+
"|<EXTRA_TOKENS_265>|",
|
3680 |
+
"|<EXTRA_TOKENS_266>|",
|
3681 |
+
"|<EXTRA_TOKENS_267>|",
|
3682 |
+
"|<EXTRA_TOKENS_268>|",
|
3683 |
+
"|<EXTRA_TOKENS_269>|",
|
3684 |
+
"|<EXTRA_TOKENS_270>|",
|
3685 |
+
"|<EXTRA_TOKENS_271>|",
|
3686 |
+
"|<EXTRA_TOKENS_272>|",
|
3687 |
+
"|<EXTRA_TOKENS_273>|",
|
3688 |
+
"|<EXTRA_TOKENS_274>|",
|
3689 |
+
"|<EXTRA_TOKENS_275>|",
|
3690 |
+
"|<EXTRA_TOKENS_276>|",
|
3691 |
+
"|<EXTRA_TOKENS_277>|",
|
3692 |
+
"|<EXTRA_TOKENS_278>|",
|
3693 |
+
"|<EXTRA_TOKENS_279>|",
|
3694 |
+
"|<EXTRA_TOKENS_280>|",
|
3695 |
+
"|<EXTRA_TOKENS_281>|",
|
3696 |
+
"|<EXTRA_TOKENS_282>|",
|
3697 |
+
"|<EXTRA_TOKENS_283>|",
|
3698 |
+
"|<EXTRA_TOKENS_284>|",
|
3699 |
+
"|<EXTRA_TOKENS_285>|",
|
3700 |
+
"|<EXTRA_TOKENS_286>|",
|
3701 |
+
"|<EXTRA_TOKENS_287>|",
|
3702 |
+
"|<EXTRA_TOKENS_288>|",
|
3703 |
+
"|<EXTRA_TOKENS_289>|",
|
3704 |
+
"|<EXTRA_TOKENS_290>|",
|
3705 |
+
"|<EXTRA_TOKENS_291>|",
|
3706 |
+
"|<EXTRA_TOKENS_292>|",
|
3707 |
+
"|<EXTRA_TOKENS_293>|",
|
3708 |
+
"|<EXTRA_TOKENS_294>|",
|
3709 |
+
"|<EXTRA_TOKENS_295>|",
|
3710 |
+
"|<EXTRA_TOKENS_296>|",
|
3711 |
+
"|<EXTRA_TOKENS_297>|",
|
3712 |
+
"|<EXTRA_TOKENS_298>|",
|
3713 |
+
"|<EXTRA_TOKENS_299>|",
|
3714 |
+
"|<EXTRA_TOKENS_300>|",
|
3715 |
+
"|<EXTRA_TOKENS_301>|",
|
3716 |
+
"|<EXTRA_TOKENS_302>|",
|
3717 |
+
"|<EXTRA_TOKENS_303>|",
|
3718 |
+
"|<EXTRA_TOKENS_304>|",
|
3719 |
+
"|<EXTRA_TOKENS_305>|",
|
3720 |
+
"|<EXTRA_TOKENS_306>|",
|
3721 |
+
"|<EXTRA_TOKENS_307>|",
|
3722 |
+
"|<EXTRA_TOKENS_308>|",
|
3723 |
+
"|<EXTRA_TOKENS_309>|",
|
3724 |
+
"|<EXTRA_TOKENS_310>|",
|
3725 |
+
"|<EXTRA_TOKENS_311>|",
|
3726 |
+
"|<EXTRA_TOKENS_312>|",
|
3727 |
+
"|<EXTRA_TOKENS_313>|",
|
3728 |
+
"|<EXTRA_TOKENS_314>|",
|
3729 |
+
"|<EXTRA_TOKENS_315>|",
|
3730 |
+
"|<EXTRA_TOKENS_316>|",
|
3731 |
+
"|<EXTRA_TOKENS_317>|",
|
3732 |
+
"|<EXTRA_TOKENS_318>|",
|
3733 |
+
"|<EXTRA_TOKENS_319>|",
|
3734 |
+
"|<EXTRA_TOKENS_320>|",
|
3735 |
+
"|<EXTRA_TOKENS_321>|",
|
3736 |
+
"|<EXTRA_TOKENS_322>|",
|
3737 |
+
"|<EXTRA_TOKENS_323>|",
|
3738 |
+
"|<EXTRA_TOKENS_324>|",
|
3739 |
+
"|<EXTRA_TOKENS_325>|",
|
3740 |
+
"|<EXTRA_TOKENS_326>|",
|
3741 |
+
"|<EXTRA_TOKENS_327>|",
|
3742 |
+
"|<EXTRA_TOKENS_328>|",
|
3743 |
+
"|<EXTRA_TOKENS_329>|",
|
3744 |
+
"|<EXTRA_TOKENS_330>|",
|
3745 |
+
"|<EXTRA_TOKENS_331>|",
|
3746 |
+
"|<EXTRA_TOKENS_332>|",
|
3747 |
+
"|<EXTRA_TOKENS_333>|",
|
3748 |
+
"|<EXTRA_TOKENS_334>|",
|
3749 |
+
"|<EXTRA_TOKENS_335>|",
|
3750 |
+
"|<EXTRA_TOKENS_336>|",
|
3751 |
+
"|<EXTRA_TOKENS_337>|",
|
3752 |
+
"|<EXTRA_TOKENS_338>|",
|
3753 |
+
"|<EXTRA_TOKENS_339>|",
|
3754 |
+
"|<EXTRA_TOKENS_340>|",
|
3755 |
+
"|<EXTRA_TOKENS_341>|",
|
3756 |
+
"|<EXTRA_TOKENS_342>|",
|
3757 |
+
"|<EXTRA_TOKENS_343>|",
|
3758 |
+
"|<EXTRA_TOKENS_344>|",
|
3759 |
+
"|<EXTRA_TOKENS_345>|",
|
3760 |
+
"|<EXTRA_TOKENS_346>|",
|
3761 |
+
"|<EXTRA_TOKENS_347>|",
|
3762 |
+
"|<EXTRA_TOKENS_348>|",
|
3763 |
+
"|<EXTRA_TOKENS_349>|",
|
3764 |
+
"|<EXTRA_TOKENS_350>|",
|
3765 |
+
"|<EXTRA_TOKENS_351>|",
|
3766 |
+
"|<EXTRA_TOKENS_352>|",
|
3767 |
+
"|<EXTRA_TOKENS_353>|",
|
3768 |
+
"|<EXTRA_TOKENS_354>|",
|
3769 |
+
"|<EXTRA_TOKENS_355>|",
|
3770 |
+
"|<EXTRA_TOKENS_356>|",
|
3771 |
+
"|<EXTRA_TOKENS_357>|",
|
3772 |
+
"|<EXTRA_TOKENS_358>|",
|
3773 |
+
"|<EXTRA_TOKENS_359>|",
|
3774 |
+
"|<EXTRA_TOKENS_360>|",
|
3775 |
+
"|<EXTRA_TOKENS_361>|",
|
3776 |
+
"|<EXTRA_TOKENS_362>|",
|
3777 |
+
"|<EXTRA_TOKENS_363>|",
|
3778 |
+
"|<EXTRA_TOKENS_364>|",
|
3779 |
+
"|<EXTRA_TOKENS_365>|",
|
3780 |
+
"|<EXTRA_TOKENS_366>|",
|
3781 |
+
"|<EXTRA_TOKENS_367>|",
|
3782 |
+
"|<EXTRA_TOKENS_368>|",
|
3783 |
+
"|<EXTRA_TOKENS_369>|",
|
3784 |
+
"|<EXTRA_TOKENS_370>|",
|
3785 |
+
"|<EXTRA_TOKENS_371>|",
|
3786 |
+
"|<EXTRA_TOKENS_372>|",
|
3787 |
+
"|<EXTRA_TOKENS_373>|",
|
3788 |
+
"|<EXTRA_TOKENS_374>|",
|
3789 |
+
"|<EXTRA_TOKENS_375>|",
|
3790 |
+
"|<EXTRA_TOKENS_376>|",
|
3791 |
+
"|<EXTRA_TOKENS_377>|",
|
3792 |
+
"|<EXTRA_TOKENS_378>|",
|
3793 |
+
"|<EXTRA_TOKENS_379>|",
|
3794 |
+
"|<EXTRA_TOKENS_380>|",
|
3795 |
+
"|<EXTRA_TOKENS_381>|",
|
3796 |
+
"|<EXTRA_TOKENS_382>|",
|
3797 |
+
"|<EXTRA_TOKENS_383>|",
|
3798 |
+
"|<EXTRA_TOKENS_384>|",
|
3799 |
+
"|<EXTRA_TOKENS_385>|",
|
3800 |
+
"|<EXTRA_TOKENS_386>|",
|
3801 |
+
"|<EXTRA_TOKENS_387>|",
|
3802 |
+
"|<EXTRA_TOKENS_388>|",
|
3803 |
+
"|<EXTRA_TOKENS_389>|",
|
3804 |
+
"|<EXTRA_TOKENS_390>|",
|
3805 |
+
"|<EXTRA_TOKENS_391>|",
|
3806 |
+
"|<EXTRA_TOKENS_392>|",
|
3807 |
+
"|<EXTRA_TOKENS_393>|",
|
3808 |
+
"|<EXTRA_TOKENS_394>|",
|
3809 |
+
"|<EXTRA_TOKENS_395>|",
|
3810 |
+
"|<EXTRA_TOKENS_396>|",
|
3811 |
+
"|<EXTRA_TOKENS_397>|",
|
3812 |
+
"|<EXTRA_TOKENS_398>|",
|
3813 |
+
"|<EXTRA_TOKENS_399>|",
|
3814 |
+
"|<EXTRA_TOKENS_400>|",
|
3815 |
+
"|<EXTRA_TOKENS_401>|",
|
3816 |
+
"|<EXTRA_TOKENS_402>|",
|
3817 |
+
"|<EXTRA_TOKENS_403>|",
|
3818 |
+
"|<EXTRA_TOKENS_404>|",
|
3819 |
+
"|<EXTRA_TOKENS_405>|",
|
3820 |
+
"|<EXTRA_TOKENS_406>|",
|
3821 |
+
"|<EXTRA_TOKENS_407>|",
|
3822 |
+
"|<EXTRA_TOKENS_408>|",
|
3823 |
+
"|<EXTRA_TOKENS_409>|",
|
3824 |
+
"|<EXTRA_TOKENS_410>|",
|
3825 |
+
"|<EXTRA_TOKENS_411>|",
|
3826 |
+
"|<EXTRA_TOKENS_412>|",
|
3827 |
+
"|<EXTRA_TOKENS_413>|",
|
3828 |
+
"|<EXTRA_TOKENS_414>|",
|
3829 |
+
"|<EXTRA_TOKENS_415>|",
|
3830 |
+
"|<EXTRA_TOKENS_416>|",
|
3831 |
+
"|<EXTRA_TOKENS_417>|",
|
3832 |
"<im_start>",
|
3833 |
"<im_end>",
|
3834 |
"<im_patch>",
|
|
|
3839 |
"AutoProcessor": "preprocessing_molmo.MolmoProcessor"
|
3840 |
},
|
3841 |
"bos_token": null,
|
3842 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
3843 |
"clean_up_tokenization_spaces": false,
|
3844 |
"eos_token": "<|endoftext|>",
|
3845 |
"errors": "replace",
|
3846 |
+
"model_max_length": 32768,
|
3847 |
"pad_token": "<|endoftext|>",
|
3848 |
"processor_class": "MolmoProcessor",
|
3849 |
"split_special_tokens": false,
|