pechpo/navr1_7b_grpo_datafix
8B • Updated • 7
Edit Models filters
Showing models from
Tasks
Parameters
Inference Providers
Hardware
Models
21
Active filters: pechpo
pechpo/navr1-01reward
8B • Updated • 6
pechpo/qwen2_5_vl_7b_pigeon_1
8B • Updated • 9
pechpo/qwen2_5_vl_7b_pigeon_2
8B • Updated • 12
pechpo/qwen2_5_vl_7b_pigeon_3
8B • Updated • 10
pechpo/qwen2_5_vl_7b_pigeon_dapo
8B • Updated • 10
pechpo/qwen2_5_vl_7b_pigeon_exp_alt
8B • Updated • 8
pechpo/qwen2_5_vl_7b_pigeon_no_select_acc
8B • Updated • 9
pechpo/qwen2_5_vl_7b_pigeon_no_confirm_acc
8B • Updated • 10
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip
8B • Updated • 7
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filter_key_acc
8B • Updated • 8
pechpo/qwen2_5_vl_7b_pigeon_01normreward_groupsz10
8B • Updated • 12
pechpo/qwen2_5_vl_7b_pigeon_01normreward_steps1000
8B • Updated • 9
pechpo/qwen2_5_vl_7b_pigeon_no_select_acc_strict
8B • Updated • 7
pechpo/qwen2_5_vl_7b_pigeon_exp_alt_mass
8B • Updated • 7
pechpo/qwen2_5_vl_7b_pigeon_01normreward_mass
8B • Updated • 8
pechpo/qwen2_5_vl_7b_pigeon_no_confirm_acc_mass
8B • Updated • 10
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filt_acc_gp_10_30k
8B • Updated • 8
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filt_acc_gp_10_30k_500step
8B • Updated • 9
pechpo/qwen2_5_vl_7b_pigeon_dapo_no_clip_filt_acc_gp_10_30k_w_o_kl_305step
8B • Updated • 6
pechpo/qwen2_5_vl_7b_pigeon_exp_alt_dapo_no_clip_filt_acc_gp_10_30k
8B • Updated • 8