mlfoundations-dev/qwen2-5_sky_t1_2-5k_rewrite_r1_distill_llama70b Text Generation • 8B • Updated Feb 10 • 6
mlfoundations-dev/qwen2-5_sky_t1_2-5k_alternative_r1_distill_llama70b Text Generation • 8B • Updated Feb 9 • 6
mlfoundations-dev/multiple_samples_none_numina_aime_adjusted_samples Text Generation • 8B • Updated Feb 9 • 5
mlfoundations-dev/unverified_stratos_mix_no_proofs_without_metadata Text Generation • 8B • Updated Feb 6 • 8
mlfoundations-dev/verified_stratos_mix_no_proofs_without_metadata Text Generation • 8B • Updated Feb 6 • 6
mlfoundations-dev/dpo_from_multiple_samples_shortest_numina_aime Text Generation • 8B • Updated Feb 6 • 6
mlfoundations-dev/dpo_from_stratos_judged_annotated_rejected_responses Text Generation • 8B • Updated Feb 5 • 6 • 1
mlfoundations-dev/multiple_samples_majority_consensus_pick_one_numina_aime_math_verify Text Generation • 8B • Updated Feb 5 • 5