sub38-65
ba76f646
reranker1.5b-sft
D14_model
Llama_3_2_1B_Filler_v8_SFT
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-mammalian_smooth_bat
Qwen2.5-Math-1.5B-Scoring-Mean
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-gliding_wary_wolf
Qwen2.5-1.5B-Instruct-Gensyn-Swarm-jagged_scampering_stingray
SmolLM3-DPO-Second-Round
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-quick_tawny_tarantula
Qwen2.5-1.5B-Open-R1-GRPO
qwen1.5b-sft-1k
merge_linear_len0.1fmt0.9_MRL4096_ROLLOUT4_LR1e-6
merge_linear_len0.5fmt0.5_MRL4096_ROLLOUT4_LR1e-6
merge_linear_len0.7fmt0.3_MRL4096_ROLLOUT4_LR1e-6
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-territorial_solitary_ant
Qwen_Qwen2.5-1.5B-Instruct-GRPO-vanilla_G_4
SmolLM3-DPO-Second-Round-no-think
helios-1.5B-sft
expert_acc_MRL4096_ROLLOUT4_LR5e-7_step54
expert_cos_MRL4096_ROLLOUT4_LR5e-7_step54
expert_len_MRL4096_ROLLOUT4_LR5e-7_step30
binary_accfmt_MRL4096_ROLLOUT4_LR5e-7_step54
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.9_linear
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.3_linear
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.1_linear
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.7_linear
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear
Qwen_Qwen2.5-1.5B-Instruct-GRPO-vanilla_G_4-checkpoint-510
Qwen2.5-1.5B-SPO-1ep-iter2
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.9_linear
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.7_linear
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear
merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear
merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.3_linear
merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_linear
merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.1_linear
