Last scanned: Oct 21, 2024 at 6:11 PM UTC
118
12
Version | Commit message | Commit author | Last scanned | ||
|---|---|---|---|---|---|
| feat-add-configs (#18) | koukandre | Oct 21, 2024 | |||
| fix: handle window_size passed as list | gmastrapas | Oct 21, 2024 | |||
| fix-glu-mlp (#17) | michael-guenther | Oct 21, 2024 | |||
| feat: for converting v2, added lines to save model weights and print config | Markus28 | Never scanned | |||
| Porting v2 models to flash attention (#15) | bwang0911 | Oct 21, 2024 | |||
| fixed GLU implementation, added conversion of layer norms | Markus28 | Oct 21, 2024 | |||
| feat: updated activation checkpointing (#14) | Markus28 | Oct 21, 2024 | |||
| fix: use staticmethod istead of classmethod | Markus28 | Oct 21, 2024 | |||
| feat: added comment | Markus28 | Never scanned | |||
| feat: added docstrings | Markus28 | Oct 19, 2024 | |||
| feat: Allow LoRA to be merged into weights (#12) | Markus28 | Oct 21, 2024 | |||
| feat: added README | Markus28 | Never scanned | |||
| removed num_tasks from config | Markus28 | Nov 11, 2024 | |||
| feat: removed tokenizer | Markus28 | Never scanned | |||
| feat: removed task type embeddings | Markus28 | Never scanned | |||
| wrap every layer in a checkpoint | Markus28 | Nov 11, 2024 | |||
| fix: remove cleaving (#13) | Markus28 | Nov 11, 2024 | |||
| fix: added trust_remote_code to tokenizer | Markus28 | Nov 11, 2024 | |||
| fix: fixed from_bert method | Markus28 | Nov 11, 2024 | |||
| fix: fix LoRA implementation | Markus28 | Nov 8, 2024 | |||