ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix #5542

Browse Source 
Former-commit-id: cf28e7418c2eb07e86923a53ef832ef218e45af1
This commit is contained in:
hiyouga
2024-09-30 23:28:55 +08:00
parent cf72aec098
commit 20ee1d2e19
4 changed files with 30 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llamafactory/model/patcher.py
View File

@@ -27,7 +27,6 @@ from ..extras.misc import infer_optim_dtype
from .model_utils.attention import configure_attn_implementation, print_attn_implementation
from .model_utils.checkpointing import prepare_model_for_training
from .model_utils.embedding import resize_embedding_layer
from .model_utils.liger_kernel import configure_liger_kernel
from .model_utils.longlora import configure_longlora
from .model_utils.moe import add_z3_leaf_module, configure_moe
from .model_utils.packing import configure_packing
@@ -93,7 +92,6 @@ def patch_config(
configure_attn_implementation(config, model_args, is_trainable)
configure_rope(config, model_args, is_trainable)
configure_liger_kernel(config, model_args, is_trainable)
configure_longlora(config, model_args, is_trainable)
configure_quantization(config, tokenizer, model_args, init_kwargs)
configure_moe(config, model_args, is_trainable)