Add `"add_prefix_space": true,`; this allows for much stronger token-level performance (e.g. NER, ColBERT)
#48
by tomaarsen HF Staff - opened
- 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|||",
|