Commit History

llama adapter doesn't support use_cache yet
9999ab8

winglian commited on

another spot missed on default adapter model
7c60b85

winglian commited on

hide fine tune ui for now to spare resources
42bd66e

winglian commited on

fix the default adapter model
5f2469b

winglian commited on

add app_hf_ui_demo.py and tweak copy
22b462e

winglian commited on

adapt ui from zetavg/LLaMA-LoRA-UI-Demo
ff8f4ba

winglian commited on