sjpark5800/Perception-Judge-Flex-32B-LoRA
Updated • 33
Seojeong Park
sjpark5800
·
AI & ML interests
Multimodal LLM, LLM safety
Recent Activity
upvoted a paper 4 days ago
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents updated a collection 4 days ago
Perception-Judge updated a collection 4 days ago
Perception-JudgeOrganizations
None yet
sjpark5800/flex_7b_10k_flexprompt_pair1_diff_new_bs_64_2.5e-7
8B • Updated • 5
sjpark5800/qwen3_4b_thinking_10k_flexprompt_batch_bs_64_7.5e-7
5B • Updated • 3
sjpark5800/qwen3_8b_thinking_10k_flexprompt_pair_1_bs_64_7.5e-7
9B • Updated • 4
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_7.5e-7
8B • Updated • 5
sjpark5800/flex_7b_10k_flexprompt_ppjd_pair_bs_64_2.5e-7
8B • Updated • 1
sjpark5800/flex_7b_10k_flexprompt_ppjd_batch_bs_64_2.5e-7
8B • Updated • 2
sjpark5800/flex_7b_10k_flexprompt_mmpr_pair_bs_64_2.5e-7
8B • Updated • 1
sjpark5800/qwen3_8b_thinking_10k_flexprompt_mmpr_pair_bs_64_7.5e-7
9B • Updated • 1
sjpark5800/qwen3_8b_thinking_10k_flexprompt_batch_bs_64_7.5e-7
9B • Updated • 3
sjpark5800/qwen3_8b_instruct_3k_flexprompt_batch_diff_new_bs_64_7.5e-7
9B • Updated • 2
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_7.5e-6
5B • Updated • 3
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_2.5e-6
5B • Updated • 2
sjpark5800/Perception-Judge-Qwen3-8B
9B • Updated • 3
sjpark5800/Perception-Judge-Qwen3-4B
5B • Updated • 34 • 1
sjpark5800/qwen3_4b_thinking_3k_flexprompt_batch_diff_new_bs_64_5e-7
5B • Updated • 1
sjpark5800/qwen3_4b_thinking_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
5B • Updated • 3
sjpark5800/qwen3_4b_thinking_3k_flexprompt_batch_diff_new_bs_64_1e-7
5B • Updated • 5
sjpark5800/flex_7b_6k_flexprompt_batch_pair_diff_bs_64_7.5e-7
8B • Updated • 2
sjpark5800/flex_7b_6k_flexprompt_batch_pair_diff_bs_64_2.5e-7
8B • Updated • 2
sjpark5800/flex_7b_6k_flexprompt_batch_pair_diff_bs_64_5e-7
8B • Updated • 1
sjpark5800/flex_7b_6k_flexprompt_batch_pair_diff_bs_64_1e-7
8B • Updated • 1
sjpark5800/qwen3_8b_instruct_3k_flexprompt_batch_diff_new_bs_64_5e-7
9B • Updated • 4
sjpark5800/qwen3_8b_instruct_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
9B • Updated • 3
sjpark5800/qwen3_8b_instruct_3k_flexprompt_batch_diff_new_bs_64_1e-6
9B • Updated • 2
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_5e-7
5B • Updated • 2
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_2.5e-7
5B • Updated • 2
sjpark5800/qwen3_4b_instruct_3k_flexprompt_batch_diff_new_bs_64_1e-6
5B • Updated • 4
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7_kl_5e-2
8B • Updated • 4
sjpark5800/flex_7b_3k_flexprompt_batch_diff_new_bs_64_2.5e-7_kl_5e-3
8B • Updated • 4