jaeyong2/Qwen2.5-0.5B-Instruct-Ja-SFT

Model Card for Model ID

Model Details

Evaluation

llm-jp-eval script(colab)

!git clone https://github.com/llm-jp/llm-jp-eval.git
!cd llm-jp-eval && pip install -e .
!cd llm-jp-eval && python scripts/preprocess_dataset.py --dataset-name all --output-dir ./dataset_dir
!cd llm-jp-eval && python scripts/evaluate_llm.py -cn config.yaml model.pretrained_model_name_or_path=jaeyong2/Qwen2.5-0.5B-Instruct-JaMagpie-Preview tokenizer.pretrained_model_name_or_path=jaeyong2/Qwen2.5-0.5B-Instruct-JaMagpie-Preview dataset_dir=./dataset_dir/1.4.1/evaluation/test

	Qwen2.5-0.5B-Instruct	finetuning-model
mmlu	0.4592	0.4614

llm-jp-eval	Qwen2.5-0.5B-Instruct	finetuning-model
AVG	0.3037	0.3176
CG	0	0
EL	0.2637	0.3146
FA	0.0386	0.0419
HE	0.2700	0.3250
MC	0.4033	0.3733
MR	0.0900	0.2700
MT	0.6148	0.6691
NLI	0.5460	0.3180
QA	0.2608	0.2791
RC	0.5495	0.5847

License

Qwen/Qwen2.5-0.5B-Instruct : https://choosealicense.com/licenses/apache-2.0/

Acknowledgement

This research is supported by TPU Research Cloud program.