Jiahe Jin's picture

Jiahe Jin

zizi-0123

·

zizi0123

AI & ML interests

None yet

Organizations

None yet

Papers 2

arxiv:2505.13909

arxiv:2412.17589

models 35

zizi-0123/mhqa_llama_grpo

zizi-0123/web_llama_sft_correct

Text Generation • 3B • Updated Jan 8 • 1

zizi-0123/web_llama_sft_correct_grpo

zizi-0123/mhqa_llama_sft_behavior

Text Generation • 3B • Updated Jan 8 • 1

zizi-0123/mhqa_llama_sft_behavior_grpo

zizi-0123/OLMo2-1B-midtrain-run1

1B • Updated Dec 15, 2025 • 3

zizi-0123/mhqa_llama_sft_random_grpo

Updated Nov 16, 2025

zizi-0123/mhqa_llama_sft_correct_grpo

Updated Nov 16, 2025

zizi-0123/web_qwen_sft_singlebehavior_grpo

Updated Nov 7, 2025

zizi-0123/web_llama_sft_random_grpo

Updated Nov 7, 2025

datasets 0

None public yet