afeng/qwen3_4b_gt_rollout12_step-1900
4B • Updated
Aosong Feng PRO
afeng
AI & ML interests
古希腊掌管 gpu 的神
Recent Activity
upvoted a collection 24 days ago
Nemotron-Pre-Training-Datasets liked a Space 24 days ago
nvidia/music-flamingo liked a dataset about 1 month ago
allenai/dolma3_longmino_poolOrganizations
afeng/qwen3_4b_gt_default_step-1500
4B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1800
8B • Updated
afeng/qwen3_8b_gt_default_step-1700
8B • Updated
afeng/qwen3_8b_gt_rollout12_step-1200
8B • Updated
afeng/qwen3_4b_gt_rollout12_step-1800
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-2400
4B • Updated
afeng/qwen3_4b_gt_default_step-1400
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-2800
8B • Updated
afeng/qwen3_8b_gt_rollout12_step-1100
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1700
8B • Updated
afeng/qwen3_4b_gt_rollout12_step-1700
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-2300
4B • Updated
afeng/qwen3_4b_gt_default_step-1300
4B • Updated
afeng/qwen3_8b_gt_default_step-1600
8B • Updated
afeng/qwen3_8b_gt_rollout4_step-2700
Updated
afeng/qwen3_8b_gt_default_step-1500
8B • Updated
afeng/qwen3_4b_gt_rollout12_step-1600
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-2200
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-2600
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1600
8B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-2100
4B • Updated
afeng/qwen3_4b_gt_rollout12_step-1500
4B • Updated
afeng/qwen3_8b_gt_rollout12_step-1000
8B • Updated
afeng/qwen3_4b_gt_default_step-1200
4B • Updated
afeng/qwen3_8b_gt_default_step-1400
8B • Updated
afeng/qwen3_8b_gt_default_step-1300
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1400
8B • Updated
afeng/qwen3_8b_gt_default_step-1200
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1300
8B • Updated