OH_DCFT_V3_wo_dataforge_economics
OH_original_wo_slimorca_550k
oh_v1-2_only_evol_instruct
oh_v3-1_only_dataforge_economics
oh_v3-1_only_glaive_code_assistant
prm_gsm_2k_with_full_sol_mix_ref_hf
airoboros_none_resp_gpt-4o-mini_inst_gpt-4o_resp
stackexchange_cs
stackexchange_photo
stackoverflow_5000tasks_1p
evol_tt_1s
Meta-Llama-3.1-8B_finetune
top_5_ranking_stackexchange
top_16_ranking_stackexchange
Llama-3.3-70B-o1
top_12_ranking_stackexchange
camel_seeding_stackexchange_codegolf
seed_math_deepmind
seed_math_formulas
askvox-llama3.3-70b-16bit
llama-SFT-base_merged_fp16_D90053_copy_32GB
bgGPT-Qwen2.5-Math-7B-Inst
qwen_7b_instruct_extra_unverified
stratos-verified-mix-scaled-0.125
stratos-unverified-mix-scaled-0.125
mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-0_125_stratos_7b
mlfoundations-dev_science-and-puzzle-stratos-verified-scaled-0_5_stratos_7b
math-stratos-unverified-scaled-1
llama3-1_8b_multiple_samples_random_numina_aime
32k_test_dummy
seed_math_math_instruct_reasoninghp
unverified_stratos_mix_no_proofs_without_metadata
verified_stratos_mix_no_proofs_without_metadata
difficulty_sorting_medium_seed_math
mlfoundations-dev_extra_verified-32B
stratos_verified_mix_epochs1
stratos_verfied_v2_1
rewiz-qwen-2.5-14b
SFT-base_merged_fp16_E1_D40005
Qwen2.5-7B-1m-Open-R1-Distill
DeepSeek-R1-Distill-HOMI-8B-trained
Qwen-2.5-7B-Simple-RL
