Updated model with better training and evaluation. Test and val data included as pickle files. Older Legacy files were removed to avoid confusion.
6aa6cec
| { | |
| "additional_special_tokens": [ | |
| { | |
| "content": "<ent>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent2>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent2>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent2>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| { | |
| "content": "<ent2>", | |
| "lstrip": false, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| ], | |
| "bos_token": "<s>", | |
| "cls_token": "<s>", | |
| "eos_token": "</s>", | |
| "mask_token": { | |
| "content": "<mask>", | |
| "lstrip": true, | |
| "normalized": true, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": "<pad>", | |
| "sep_token": "</s>", | |
| "unk_token": "<unk>" | |
| } | |