423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-14 23:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove manully set use_cache; torch_dtype is not str, save model as bfloat16 used to fail;

Browse Source 
Former-commit-id: 75557fb5df16fd6eda7586cf041a16822dcfee8e
This commit is contained in:
yhyu13 2024-01-21 11:12:15 +08:00
parent ab67528e89
commit cd1cb8b83c
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/llmtuner/train/tuner.py
View File

@ -56,12 +56,11 @@ def export_model(args: Optional[Dict[str, Any]] = None):
if not isinstance(model, PreTrainedModel):
raise ValueError("The model is not a `PreTrainedModel`, export aborted.")
setattr(model.config, "use_cache", True)
if getattr(model.config, "torch_dtype", None) == "bfloat16":
model = model.to(torch.bfloat16).to("cpu")
if hasattr(model.config, "torch_dtype"):
model = model.to(getattr(model.config, "torch_dtype")).to("cpu")
else:
model = model.to(torch.float16).to("cpu")
setattr(model.config, "torch_dtype", "float16")
model = model.to(torch.float32).to("cpu")
setattr(model.config, "torch_dtype", "float32")
model.save_pretrained(
save_directory=model_args.export_dir,