423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-15 16:18:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix export

Browse Source 
Former-commit-id: c9b968b84c97c9a00fbb43194c3adc9354d74f3b
This commit is contained in:
hiyouga 2024-03-14 18:17:01 +08:00
parent 764cfb506d
commit aabe90343e
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/llmtuner/model/patcher.py
View File

@ -294,6 +294,7 @@ def patch_config(
init_kwargs["torch_dtype"] = model_args.compute_dtype init_kwargs["torch_dtype"] = model_args.compute_dtype
if not is_deepspeed_zero3_enabled(): if not is_deepspeed_zero3_enabled():
init_kwargs["low_cpu_mem_usage"] = model_args.low_cpu_mem_usage init_kwargs["low_cpu_mem_usage"] = model_args.low_cpu_mem_usage
if model_args.low_cpu_mem_usage:
if "device_map" not in init_kwargs: # quant models cannot use auto device map if "device_map" not in init_kwargs: # quant models cannot use auto device map
init_kwargs["device_map"] = model_args.device_map or {"": get_current_device()} init_kwargs["device_map"] = model_args.device_map or {"": get_current_device()}

3
src/llmtuner/train/tuner.py
View File

@ -42,8 +42,7 @@ def run_exp(args: Optional[Dict[str, Any]] = None, callbacks: Optional[List["Tra
def export_model(args: Optional[Dict[str, Any]] = None): def export_model(args: Optional[Dict[str, Any]] = None):
model_args, data_args, finetuning_args, _ = get_infer_args(args) model_args, data_args, finetuning_args, _ = get_infer_args(args)
model_args.low_cpu_mem_usage = False
model_args.device_map = {"": "cpu"}
if model_args.export_dir is None: if model_args.export_dir is None:
raise ValueError("Please specify `export_dir` to save model.") raise ValueError("Please specify `export_dir` to save model.")