yzha (y_zha)

models 9

yzha/grpo_qwen3_8b_sysprompt_workflow2_step160

8B • Updated Oct 2, 2025

yzha/qwen3_8b_new_prompt_orig_otcm_rwd_w_choice_ratio

8B • Updated Oct 1, 2025 • 2

yzha/grpo_qwen3_8b_sysprompt_workflow2

8B • Updated Oct 1, 2025 • 3

yzha/vision-g1

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

yzha/tklt-virl-400step

8B • Updated May 7, 2025

yzha/virl_39k_step200

8B • Updated May 6, 2025

yzha/tklt-step200

8B • Updated May 6, 2025

yzha/Align

Updated Dec 7, 2023 • 1

yzha/AlignScore

Updated Jun 6, 2023 • 6

datasets 4

yzha/Nemotron_Nano_sharegpt

Viewer • Updated May 1, 2025 • 4.42M • 8

yzha/R1_distilled_brain_teasers

Viewer • Updated May 1, 2025 • 3.79k • 12

yzha/Nemotron-Nano_Reasoning-V1

Viewer • Updated May 1, 2025 • 5.86M • 4

yzha/Nemotron_Nano_Post_Training_Data

Viewer • Updated May 1, 2025 • 4.42M • 4

y_zha

AI & ML interests

Organizations

Papers 4

spaces 1

CTC_Eval

models 9

yzha/grpo_qwen3_8b_sysprompt_workflow2_step160

yzha/qwen3_8b_new_prompt_orig_otcm_rwd_w_choice_ratio

yzha/grpo_qwen3_8b_sysprompt_workflow2

yzha/vision-g1

yzha/tklt-virl-400step

yzha/virl_39k_step200

yzha/tklt-step200

yzha/Align

yzha/AlignScore

datasets 4

yzha/Nemotron_Nano_sharegpt

yzha/R1_distilled_brain_teasers

yzha/Nemotron-Nano_Reasoning-V1

yzha/Nemotron_Nano_Post_Training_Data

y_zha

AI & ML interests

Organizations

Papers 4

spaces 1

CTC_Eval

models 9 Sort: Recently updated

datasets 4 Sort: Recently updated

models 9

datasets 4