saeng

yilingwang 's models 13

Sort:  Recently updated

yilingwang/OR-bench-ckpt-40

196k • Updated 26 days ago • 4

yilingwang/OR-bench-ckpt-480

308k • Updated 26 days ago • 5

yilingwang/OR-bench-ckpt-45

8B • Updated 27 days ago • 6

yilingwang/OR-bench-ckpt-80

Updated 27 days ago

yilingwang/grpo-data-v1-6200

308k • Updated Jan 11

yilingwang/grpo-data-v1-440

308k • Updated Jan 11

yilingwang/dpo-checkpoint-66-new

2B • Updated Dec 28, 2025

yilingwang/dpo-checkpoint-66

2B • Updated Dec 28, 2025

yilingwang/merge-315

2B • Updated Dec 23, 2025 • 1

yilingwang/checkpoint-200

2B • Updated Dec 20, 2025

yilingwang/checkpoint-100

2B • Updated Dec 20, 2025

yilingwang/grpo_Qwen3-8B-data-filter-deepseek

Updated Dec 9, 2025

yilingwang/sft_qwen3_8b_sample_epoch_1_deepseek

308k • Updated Dec 9, 2025