t2ance/atlas-ppo_qwen3_8b_pattern_gpqa_overall_utility_prefix_potential_lora_2gpu Updated 29 days ago
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_noconf Text Generation • Updated Sep 3 • 25
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_merged_grpo_step40 8B • Updated Sep 3 • 6 • 1
t2ance/atlas-sft_qwen3_8b_pattern_teacher_gpqa_firstcall_full Text Generation • 8B • Updated Sep 3 • 150
t2ance/atlas-ppo5-terminal_singletool_capmaskiso_rewardalign_ppoep2_actorlr5e6_from_s10 Updated Sep 3
t2ance/atlas-ppo5-processv1_zerobaseline_capmaskiso_rewardalign_ppoep2_actorlr5e6_from_s10 Updated Sep 3