423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-07 22:00:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix dora inference

Browse Source 
Former-commit-id: 21b3597b0a05169afe51e1609b532787a65ca8ea
This commit is contained in:
hiyouga 2024-03-05 11:51:41 +08:00
parent 6123a4e713
commit 0604a84208
1 changed files with 2 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llmtuner/model/patcher.py
View File

@ -287,6 +287,8 @@ def patch_config(
init_kwargs["low_cpu_mem_usage"] = True
if is_trainable:
init_kwargs["device_map"] = {"": get_current_device()}
elif model_args.export_dir is None:
init_kwargs["device_map"] = "auto"
def patch_model(