423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-11-04 18:02:19 +08:00
Code Issues Packages Projects Releases Wiki Activity

tiny fix

Browse Source 
Former-commit-id: f9d50501aac1f60a3b445ca3fee9aa60995461ee
This commit is contained in:
hiyouga 2024-06-04 00:31:10 +08:00
parent aa6c3766de
commit 2ac2cde03e
3 changed files with 5 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
examples/extras/fsdp_qlora/single_node.sh
View File

@ -1,10 +1,6 @@
#!/bin/bash
# DO NOT use GPTQ/AWQ model in FSDP+QLoRA
pip install "transformers>=4.39.1"
pip install "accelerate>=0.28.0"
pip install "bitsandbytes>=0.43.0"
CUDA_VISIBLE_DEVICES=0,1 accelerate launch \
--config_file examples/accelerate/fsdp_config.yaml \
src/train.py examples/extras/fsdp_qlora/llama3_lora_sft.yaml

8
scripts/llama_pro.py
View File

@ -104,10 +104,10 @@ def block_expansion(
print("Model weights saved in {}".format(output_dir))
print("Fine-tune this model with:")
print(" --model_name_or_path {} \\".format(output_dir))
print(" --finetuning_type freeze \\")
print(" --freeze_trainable_layers {} \\".format(num_expand))
print(" --use_llama_pro")
print("model_name_or_path: {}".format(output_dir))
print("finetuning_type: freeze")
print("freeze_trainable_layers: {}".format(num_expand))
print("use_llama_pro: true")
if __name__ == "__main__":

2
src/llamafactory/data/loader.py
View File

@ -179,7 +179,7 @@ def get_dataset(
if training_args.should_save:
dataset.save_to_disk(data_args.tokenized_path)
logger.info("Tokenized dataset saved at {}.".format(data_args.tokenized_path))
logger.info("Please restart the training with `--tokenized_path {}`.".format(data_args.tokenized_path))
logger.info("Please restart the training with `tokenized_path: {}`.".format(data_args.tokenized_path))
sys.exit(0)