423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-10-16 00:28:10 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #199

Browse Source 
Former-commit-id: 7fc778b49bc17688aca39fffe01f9d33e03e0c28
This commit is contained in:
hiyouga 2023-07-19 22:51:29 +08:00
parent 6d881f161b
commit 7e1a1d141a
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/llmtuner/tuner/core/loader.py
View File

@ -10,6 +10,7 @@ from transformers import (
) )
from transformers.utils import check_min_version from transformers.utils import check_min_version
from transformers.utils.versions import require_version from transformers.utils.versions import require_version
from transformers.trainer import is_deepspeed_zero3_enabled
from transformers.modeling_utils import PretrainedConfig, PreTrainedModel from transformers.modeling_utils import PretrainedConfig, PreTrainedModel
from transformers.tokenization_utils import PreTrainedTokenizerBase from transformers.tokenization_utils import PreTrainedTokenizerBase
from trl import AutoModelForCausalLMWithValueHead from trl import AutoModelForCausalLMWithValueHead
@ -108,7 +109,7 @@ def load_model_and_tokenizer(
model_to_load, model_to_load,
config=config, config=config,
torch_dtype=torch.bfloat16 if model_args.compute_dtype == torch.bfloat16 else torch.float16, torch_dtype=torch.bfloat16 if model_args.compute_dtype == torch.bfloat16 else torch.float16,
low_cpu_mem_usage=True, low_cpu_mem_usage=(not is_deepspeed_zero3_enabled()),
**config_kwargs **config_kwargs
) )