merge_cosfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_dare_ties
merge_lenfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties
merge_accfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties
merge_cosfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties
merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties
merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties
merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties
merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties
merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties
merge_lenfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties
merge_lenfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties
merge_accfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties_density0.2
merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties_density0.2
M4
SmolLM3-SFT
hh-llama32-1b-sft
c68-h6
qwen2.5-finetuned
dpo-llama3.2-minirl-100
cxz1
SB_DS1.5B_alpha_1
Laser-L2048-1.5B
m181
d186_1
ff265164
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-slithering_scampering_anteater
Llama-1B-CoT
x1
Qwen2.5-1.5B-GRPO-1ep-iter2
Qwen2.5-1.5B-Open-R1-GRPO-Crosswords-v7
6dcf0f35
gajosep
49140706
sn38-v12-2
sn38-v5-3
Qwen2.5-Coder-1.5B-Instruct-Gensyn-Swarm-sizable_robust_alligator
Llama-3.2-1B-Indian-history
Qwen2.5-MATH-1.5B-Instruct-DAPO-G8
DeepSeek-R1-Distill-Qwen-1.5B-DAPO-G8
Qwen2.5-1.5B-Instruct-Medical-cpt-sft-v1
ShweYon_Qwen2.5-Burmese-1.5B-v1.2-Pretrained