Last scanned: Oct 21, 2024 at 6:11 PM UTC
118
Version | Commit message | Commit author | Last scanned | ||
|---|---|---|---|---|---|
| feat: for converting v2, added lines to save model weights and print config | Markus28 | Never scanned | |||
| feat: added comment | Markus28 | Never scanned | |||
| feat: added README | Markus28 | Never scanned | |||
| feat: removed tokenizer | Markus28 | Never scanned | |||
| feat: removed task type embeddings | Markus28 | Never scanned | |||
| feat: make main parameters trainable | Markus28 | Never scanned | |||
| fix BertForMaskedLM | Markus28 | Never scanned | |||
| Update tokenizer.py | michael-guenther | Never scanned | |||
| feat-add-constant-for-task-type-ids (#10) | michael-guenther | Never scanned | |||
| fix: fixed syntax error in LoRA | Markus28 | Never scanned | |||
| feat: use property instead of setter | Markus28 | Never scanned | |||
| feat: made from_bert work | Markus28 | Never scanned | |||
| feat: select first LoRA upon initialization | Markus28 | Never scanned | |||
| support-multiple-task-ids (#5) | Markus28 | Never scanned | |||
| fix: use proper initilization for embedding layer | Markus28 | Never scanned | |||
| fix: fixed typo | Markus28 | Never scanned | |||
| feat: assert return_dict | Markus28 | Never scanned | |||
| fix: assert is None for other kwargs too | Markus28 | Never scanned | |||
| fix: formatting | Markus28 | Never scanned | |||
| feat: added further GLUE models | Markus28 | Never scanned | |||
12