6 commits

Author	SHA1	Message	Date
jeffbiocode	3168644152	Training: Update llama2-chat-format.json (#5593)	2024-03-03 12:42:14 -03:00
jeffbiocode	45c4cd01c5	Add llama 2 chat format for lora training (#5553)	2024-02-25 02:36:36 -03:00
kizinfo	5d513eea22	Add ability to load all text files from a subdirectory for training (#1997) ... * Update utils.py returns individual txt files and subdirectories to getdatasets to allow for training from a directory of text files * Update training.py minor tweak to training on raw datasets to detect if a directory is selected, and if so, to load in all the txt files in that directory for training * Update put-trainer-datasets-here.txt document * Minor change * Use pathlib, sort by natural keys * Space --------- Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>	2023-07-12 11:44:30 -03:00
Fernando Tarin Morales	1f540fa4f8	Added the format to be able to finetune Vicuna1.1 models (#3037)	2023-07-07 02:22:39 -03:00
oobabooga	88ad86249d	Remove unnecessary file	2023-03-28 13:19:52 -03:00
Alex "mcmonkey" Goodwin	566898a79a	initial lora training tab	2023-03-25 12:08:26 -07:00