ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions 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
Download Patch File Download Diff File Expand all files Collapse all files

9
src/llmtuner/model/patcher.py
View File

@@ -294,11 +294,12 @@ def patch_config(
init_kwargs["torch_dtype"] = model_args.compute_dtype
if not is_deepspeed_zero3_enabled():
init_kwargs["low_cpu_mem_usage"] = model_args.low_cpu_mem_usage
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()}
if model_args.low_cpu_mem_usage:
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()}
if init_kwargs["device_map"] == "auto":
init_kwargs["offload_folder"] = model_args.offload_folder
if init_kwargs["device_map"] == "auto":
init_kwargs["offload_folder"] = model_args.offload_folder
def patch_model(