Commit Graph

7 Commits

Author SHA1 Message Date
Johan Hansson
cd2cda3cda fix pylint 2024-01-11 16:54:03 +01:00
Johan Hansson
4fa557889c fix pre commit 2024-01-10 23:04:12 +01:00
Johan Hansson
45d82b7b86 clean up 2024-01-10 22:57:28 +01:00
Johan Hansson
37a934bdb3 clean up 2024-01-10 22:50:05 +01:00
Johan Hansson
0d1d00a363 draft for adding test for tokenizer 2024-01-10 22:42:58 +01:00
NanoCode012
043c3860cd fix: train_on_inputs: true ignored for sharegpt (#1045) [skip ci]
* fix: `train_on_inputs: true` ignored for sharegpt

* enable unit test for train_on_inputs for sharegpt

---------

Co-authored-by: Wing Lian <wing.lian@gmail.com>
2024-01-09 23:00:09 -05:00
Wing Lian
651b7a31fc fix double eos token for chatml (#1054) [skip ci]
* fix double eos token for chatml

* isolate fix to chatml conversation

* fix add special tokens to include rstrip

* add test for train_on_inputs for sharegpt

* don't use rstrip for chatml
2024-01-09 09:33:38 -05:00