Last scanned: Oct 23, 2024 at 6:29 AM UTC
12
Version | Commit message | Commit author | Last scanned | ||
|---|---|---|---|---|---|
| readme: fix reference to used dataset | stefan-it | Oct 23, 2024 | |||
| figure: add re-trained loss curve for training | stefan-it | Oct 27, 2024 | |||
| readme: add more infos about re-trained model | stefan-it | Never scanned | |||
| model: add re-trained xLSTM model with grouped corpus for pretraining | stefan-it | Nov 12, 2024 | |||
| readme: fix markdown | stefan-it | Oct 27, 2024 | |||
| readme: mention potential bug in pretraining (truncated Wikipedia articles are used) | stefan-it | Oct 27, 2024 | |||
| config: add mapping for AutoModelForSequenceClassification to own xLSTMForSequenceClassification | stefan-it | Never scanned | |||
| modeling: sync xLSTMForSequenceClassification with Patrick's codebase from https://github.com/HallerPatrick/helibrunna/blob/a1b377271867d5f23201ccacb55e017749aba487/model/modeling_xlstm.py | stefan-it | Never scanned | |||
| readme: fix revision of forked Helibrunna repo | stefan-it | Never scanned | |||
| xlstm-config: temporarily introduce new hidden_size parameter | stefan-it | Oct 24, 2024 | |||
| readme: include some new logo :-) | stefan-it | Oct 27, 2024 | |||
| figure: add some new logo :p | stefan-it | Never scanned | |||
| readme: update information about final xLSTM model (one epoch over corpus) | stefan-it | Oct 27, 2024 | |||
| figure: add updated loss curve for training | stefan-it | Never scanned | |||
| model: add newly trained xLSTM model (with grad clipping) | stefan-it | Nov 12, 2024 | |||
| readme: cleanup configuration example | stefan-it | Oct 27, 2024 | |||
| readme: mention currently missing grad norm | stefan-it | Never scanned | |||
| readme: mention Tristan | stefan-it | Never scanned | |||
| readme: mention Tristan | stefan-it | Nov 12, 2024 | |||
| readme: add more training details | stefan-it | Nov 12, 2024 | |||
36