423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-12-29 10:10:35 +08:00
Code Issues Packages Projects Releases Wiki Activity

reimplement neftune

Browse Source 
Former-commit-id: efe9e5a194d3a9f052701d904715238816e4c09e
This commit is contained in:
hiyouga
2023-10-22 16:15:08 +08:00
parent 1f69965239
commit 6da51565f5
9 changed files with 36 additions and 104 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -206,8 +206,7 @@ def load_model_and_tokenizer(
tokenizer.__class__.register_for_auto_class()
# Initialize adapters
if is_trainable:
model = prepare_model_for_training(model, model_args.upcast_layernorm, finetuning_args.finetuning_type)
model = prepare_model_for_training(model=model, finetuning_args=finetuning_args) if is_trainable else model
model = init_adapter(model, model_args, finetuning_args, is_trainable, is_mergeable)
model = model.train() if is_trainable else model.eval()