423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-04 12:42:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix #1900

Browse Source 
Former-commit-id: 0c6ab7c75e671348f24d28309d450aecec0a157f
This commit is contained in:
hiyouga 2023-12-19 17:21:46 +08:00
parent 54e58adf09
commit e06b9c4fa1
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -73,6 +73,7 @@ def load_model_and_tokenizer(
) )
patcher.patch_model(model) patcher.patch_model(model)
register_autoclass(config, model, tokenizer) register_autoclass(config, model, tokenizer)
if not is_deepspeed_zero3_enabled():
resize_embedding_layer(model, tokenizer) resize_embedding_layer(model, tokenizer)
model = prepare_model_for_training(model=model, finetuning_args=finetuning_args) if is_trainable else model model = prepare_model_for_training(model=model, finetuning_args=finetuning_args) if is_trainable else model