pechpo/qwen2_5_vl_7b_pigeon_exp_alt_dapo_no_clip_filt_acc_gp_10_30k
8B • Updated • 2
彭程
pechpo
·
AI & ML interests
None yet
Organizations
None yet
models 21
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filt_acc_gp_10_30k_w_o_kl_305step
8B • Updated • 1
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filt_acc_gp_10_30k_500step
8B • Updated
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filt_acc_gp_10_30k
8B • Updated • 1
pechpo/qwen2_5_vl_7b_pigeon_no_confirm_acc_mass
8B • Updated • 2
pechpo/qwen2_5_vl_7b_pigeon_01normreward_mass
8B • Updated • 1
pechpo/qwen2_5_vl_7b_pigeon_exp_alt_mass
8B • Updated • 2
pechpo/qwen2_5_vl_7b_pigeon_no_select_acc_strict
8B • Updated • 1
pechpo/qwen2_5_vl_7b_pigeon_01normreward_steps1000
8B • Updated • 2
pechpo/qwen2_5_vl_7b_pigeon_01normreward_groupsz10
8B • Updated • 1