423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-19 05:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

update packing with sdpa and eager attention mode

Browse Source
This commit is contained in:
ancv
2024-06-16 02:25:47 +07:00
parent 04315c3d92
commit 238f5c3d99
3 changed files with 148 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/train/sft/workflow.py
View File

@@ -34,7 +34,7 @@ def run_sft(
model = load_model(tokenizer, model_args, finetuning_args, training_args.do_train)
if data_args.efficient_packing:
configure_packing(model.config)
configure_packing(model.config, model_args)
if training_args.predict_with_generate:
tokenizer.padding_side = "left" # use left-padding in generation