Do not add eos token by default (#8)
Browse files- Do not add eos token by default (6d762032ac7adbc536dd25d458a13b59454b24cb)
- Update .gitattributes (1230593151b8a1e8f3de1f18958236404ed9b21c)
- Upload tokenizer.json (fdc0b188cb40e0a2e60574fce18079145c51e434)
Co-authored-by: Joshua <[email protected]>
- .gitattributes +0 -1
- tokenizer.json +0 -0
- tokenizer_config.json +2 -0
.gitattributes
CHANGED
|
@@ -34,4 +34,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tekken.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
-
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tekken.json filter=lfs diff=lfs merge=lfs -text
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,4 +1,6 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
|
|
|
| 1 |
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
"add_prefix_space": false,
|
| 5 |
"added_tokens_decoder": {
|
| 6 |
"0": {
|