Derek Zhe Hu

zhehuderek 's models 11

Sort:  Recently updated

zhehuderek/qwen2.5-3b-diverse-arggen-1sample-sft-100k

Text Generation • 3B • Updated Feb 6 • 1

zhehuderek/qwen25_vl_7b_stage2_virl39k_step80

Image-Text-to-Text • 8B • Updated Feb 3 • 1

zhehuderek/qwen25_vl_7b_guru_mixed_dapo_run2_step170

Image-Text-to-Text • 8B • Updated Dec 20, 2025 • 1

zhehuderek/qwen25_vl_7b_guru_mixed_dapo_run2_step110

Image-Text-to-Text • 8B • Updated Dec 17, 2025 • 1

zhehuderek/qwen25_vl_7b_guru_mixed_grpo_run4_step150

Image-Text-to-Text • 8B • Updated Dec 13, 2025 • 1

zhehuderek/qwen2_5_vl_7b_GEOQA_8K_step90_hf

Image-Text-to-Text • 8B • Updated Sep 21, 2025 • 1

zhehuderek/praxis_vlm_7b_decisionmaking

Image-Text-to-Text • 8B • Updated Jun 3, 2025 • 3

zhehuderek/praxis_vlm_3b_decisionmaking

Image-Text-to-Text • 4B • Updated Jun 3, 2025 • 1

zhehuderek/qwen2_5_vl_3b_GEOQA_8K_hf

Image-Text-to-Text • 4B • Updated Apr 9, 2025 • 1

zhehuderek/llama-2-7b-chinese

Text Generation • 7B • Updated Dec 4, 2024

zhehuderek/llama-3.1-8b-chinese-sft

Text Generation • 8B • Updated Jul 28, 2024