Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 10 additions & 2 deletions train.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,14 @@
from data.dataset import HybridDataset, collate_fn
from data.data_utils import AverageMeter, ProgressMeter, Summary, dict_to_cuda
from utils.utils import save_args_to_json, create_log_dir
from packaging.version import Version

def _dtype_kwargs(dtype):
"""`dtype` keyword of `from_pretrained` exists since transformers 4.56 (PR #39782);
older versions use `torch_dtype`."""
if Version(transformers.__version__) >= Version("4.56"):
return {"dtype": dtype}
return {"torch_dtype": dtype}

def env_init(distributed=True):
print("Init Env for Distributed Training")
Expand Down Expand Up @@ -330,7 +338,7 @@ def main(args):

model = ShowUIForConditionalGeneration.from_pretrained(
model_url,
torch_dtype=torch_dtype,
**_dtype_kwargs(torch_dtype),
low_cpu_mem_usage=True,
_attn_implementation=args.attn_imple,
quantization_config=bnb_config,
Expand All @@ -343,7 +351,7 @@ def main(args):

model = Qwen2VLForConditionalGeneration.from_pretrained(
model_url,
torch_dtype=torch_dtype,
**_dtype_kwargs(torch_dtype),
low_cpu_mem_usage=True,
_attn_implementation=args.attn_imple,
quantization_config=bnb_config,
Expand Down