finetune: support adding additional_training_arguments and additional_lora_config e652ee3 unverified zetavg commited on Apr 21, 2023
download_base_model: use snapshot_download from huggingface_hub to download models but not load them a1c44f4 unverified zetavg commited on Apr 21, 2023
Merge pull request #10 from paplorinc/paplorinc-patch-1 e302cf6 unverified Pokai Chang commited on Apr 19, 2023
improve speed of switching models by offloading unused ones to cpu ram instead if unloading 6148b7c unverified zetavg commited on Apr 18, 2023
fix "operation not supported" while flagging and use different log files for different models db1ee85 zetavg commited on Apr 18, 2023
Merge pull request #7 from paplorinc/paplorinc-patch-4 6201a81 unverified Pokai Chang commited on Apr 18, 2023
Simplify version check and make gdrive loading optional 32f7167 unverified Lőrinc Pap commited on Apr 18, 2023
Merge branch 'main' of github.com:zetavg/llama-lora 350cbe9 unverified zetavg commited on Apr 17, 2023