afeng/qwen3_8b_gt_default_step-1100
8B • Updated
Aosong Feng PRO
afeng
AI & ML interests
古希腊掌管 gpu 的神
Recent Activity
upvoted a collection about 18 hours ago
Nemotron-Pre-Training-Datasets liked
a Space about 18 hours ago
nvidia/music-flamingo liked
a dataset 11 days ago
allenai/dolma3_longmino_pool Organizations
afeng/qwen3_8b_gt_no_uncertain_step-1200
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1100
8B • Updated
afeng/qwen3_8b_gt_default_step-700
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-700
8B • Updated
afeng/qwen3_8b_gt_rollout4_step-2200
8B • Updated
afeng/qwen3_8b_gt_rollout4_step-2100
8B • Updated
afeng/qwen3_8b_gt_rollout12_step-900
8B • Updated
afeng/qwen3_4b_gt_rollout4_step-2700
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-1800
4B • Updated
afeng/qwen3_4b_gt_rollout12_step-1300
4B • Updated
afeng/qwen3_4b_gt_default_step-1100
4B • Updated
afeng/qwen3_8b_gt_rollout4_step-2000
8B • Updated
afeng/qwen3_4b_gt_rollout4_step-2600
4B • Updated
afeng/qwen3_4b_gt_rollout12_step-1200
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-1700
4B • Updated
afeng/qwen3_8b_gt_rollout12_step-800
8B • Updated
afeng/qwen3_4b_gt_default_step-1000
4B • Updated
afeng/qwen3_4b_gt_rollout12_step-1100
4B • Updated
afeng/qwen3_4b_gt_rollout4_step-2500
4B • Updated
afeng/qwen3_4b_gt_no_uncertain_step-1600
4B • Updated
afeng/qwen3_4b_gt_default_step-900
4B • Updated
afeng/qwen3_4b_gt_default_step-800
4B • Updated
afeng/qwen3_4b_gt_default_step-700
4B • Updated
afeng/qwen3_4b_gt_default_step-600
4B • Updated
afeng/qwen3_8b_gt_default_step-1000
8B • Updated
afeng/qwen3_8b_gt_rollout4_step-1600
8B • Updated
afeng/qwen3_8b_gt_rollout12_step-700
8B • Updated
afeng/qwen3_8b_gt_no_uncertain_step-1000
8B • Updated
afeng/qwen3_8b_gt_default_step-900
8B • Updated