Qwen3-0.6B-DPO-Ja-Peft

jaeyong2/Qwen3-0.6B-DPO-Ja-Peft

Qwen3-0.6B-DPO-Ja-Peft is a text generation model from jaeyong2. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.

- Qwen/Qwen3-0.6B : https://choosealicense.com/licenses/apache-2.0/

Downloads · 30 days

15% of all-time downloads

All-time downloads

Public

Parameters

596M

1.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.2 GB · 99%

At a glance

Task: Text Generation
Library: transformers
License: apache-2.0
Model type: qwen3
Access: Public
Created: Jun 14, 2025
Updated: Jun 16, 2025
SHA: 71f60ff4

Model card

From the Hugging Face model README

Evaluation

!lm_eval --model hf \
    --model_args pretrained=jaeyong2/Qwen3-0.6B-DPO-Ja-Peft \
    --tasks mmlu,japanese_leaderboard,gsm8k \
    --device cuda:0 \
    --batch_size 1 \
    --num_fewshot 5

	Qwen3-0.6B-DPO-ja	Qwen3-0.6B
MMLU	0.41	0.40
ja_leaderboard_jaqket_v2	0.30	0.28
ja_leaderboard_jcommonsenseqa	0.45	0.44
ja_leaderboard_jnli	0.24	0.26
ja_leaderboard_jsquad	0.49	0.48
ja_leaderboard_marc_ja	0.87	0.86
ja_leaderboard_mgsm	0.12	0.11
ja_leaderboard_xlsum	0.09	0.08
ja_leaderboard_xwinograd	0.55	0.55
GSM8K	0.44	0.42

License

Qwen/Qwen3-0.6B : https://choosealicense.com/licenses/apache-2.0/

Acknowledgement

This research is supported by TPU Research Cloud program.

Task: Text Generation
Library: transformers
Type: qwen3
License: apache-2.0
Languages: ja
Created: Jun 14, 2025
Updated: Jun 16, 2025