Add `"add_prefix_space": true,`; this allows for much stronger token-level performance (e.g. NER, ColBERT) (#10)
Browse files- Add `"add_prefix_space": true,`; this allows for much stronger token-level performance (e.g. NER, ColBERT) (8ae8af350a6709405298a2c4986b425fa5e99570)
Co-authored-by: Tom Aarsen <[email protected]>
- tokenizer_config.json +1 -0
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "|||IP_ADDRESS|||",
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "|||IP_ADDRESS|||",
|