afeng/qwen3_4b_gt_rollout12_step-500
4B • Updated
Aosong Feng PRO
afeng
AI & ML interests
古希腊掌管 gpu 的神
Recent Activity
upvoted a collection 11 days ago
Nemotron-Pre-Training-Datasets liked
a Space 11 days ago
nvidia/music-flamingo liked
a dataset 21 days ago
allenai/dolma3_longmino_pool Organizations
afeng/qwen3_4b_gt_rollout4_step-1100
4B • Updated
afeng/qwen3_4b_gt_default_step-400
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-800
8B • Updated
afeng/qwen3_8b_gt_rollout12_step-200
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-400
8B • Updated
afeng/qwen3_8b_gt_default_step-400
8B • Updated
afeng/qwen3_4b_gt_rollout12_step-400
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-700
4B • Updated
afeng/qwen3_4b_gt_default_step-300
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-700
8B • Updated
afeng/qwen3_4b_gt_rollout4_step-1000
4B • Updated
afeng/qwen3_4b_gt_rollout4_step-900
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-600
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-600
8B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-500
4B • Updated
afeng/qwen3_4b_gt_rollout4_step-800
4B • Updated
afeng/qwen3_8b_gt_rollout12_step-100
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-300
8B • Updated
afeng/qwen3_8b_gt_default_step-300
8B • Updated
afeng/qwen3_4b_gt_rollout12_step-300
4B • Updated
afeng/qwen3_4b_gt_default_step-200
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-500
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-200
8B • Updated
afeng/qwen3_8b_gt_rollout4_step-400
8B • Updated
afeng/qwen3_8b_gt_default_step-200
8B • Updated
afeng/qwen3_4b_gt_rollout4_step-700
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-400
4B • Updated
afeng/qwen3_4b_gt_rollout4_step-600
4B • Updated
afeng/qwen3_4b_gt_rollout12_step-200
4B • Updated