423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-15 08:08:09 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #2266 from yhyu13/fix_export_model_dtype

Browse Source 
Remove manully set use_cache; torch_dtype is not str, save model as b…

Former-commit-id: 8c0827ba92a458e18c3b68af0330af3a65149f96
This commit is contained in:
hoshi-hiyouga 2024-01-21 12:40:39 +08:00 committed by GitHub
commit 013ded4bac
1 changed files with 3 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
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) == torch.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")
setattr(model.config, "torch_dtype", torch.float16)
model.save_pretrained(
save_directory=model_args.export_dir,