jinaai / jina-bert-flash-implementation
Last scanned: Nov 11, 2024 at 9:28 PM UTC
Versions
Version | Commit message | Commit author | Last scanned | ||
---|---|---|---|---|---|
feat-add-configs (#18) | koukandre | Mar 21, 2025 | |||
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 | |||
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 | |||
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 | |||
feat: cleave off layers from encoder (#11) | Markus28 | Nov 8, 2024 | |||
feat: only apply select_task_for_layer if task has changed | Markus28 | Nov 11, 2024 |
Protect AI's security scanner detects threats in model files
With Protect AI's Guardian you can scan models for threats before ML developers download them for use, and apply policies based on your risk tolerance.
Found a new threat?
Earn bounties and get recognition for your discoveries by submitting them through Huntr.