qwen2.5-14b-tofu-ft-full-5epochs
Meta-Llama-3-8B-Instruct-RSN-Tuned
affine-k-11-5GZWkEcb9cuUD9Tb8ds8QoraCv2TwojNmFqSUP4NDPsHyihM
affine-k-10-5EhM3q9z5Yj4Vf2sgUSEbBTuqCvdMqQvFrnA3N9ZHnbxv7jG
medgemma-4b-ft
newlf_000groupsss_filall_numsym_no_empty_withname_sft_2
Affine-H3-5GRYqnQAoMrCiEAcRhkWvfYMtWkDByptzWEEKkrKcve69hVe
affine-ana6-7-5FmzsJh4ZPsfv1JaH853oDe1oqmwweuzy26TQ1BKwNTfk5zY
stage1-rft
qwen2.5-rude_s89_lr1em05_r32_a64_e1
gemma2-unpopular_s669_lr1em05_r32_a64_e1
seed0_sample30000_mmmlu_Qwen-Qwen2.5-7B_multi_1.0-1.0_1.0
swe-smith-rs-base-qwen3-8b-teacher-gemini-3-flash-step-500
SearchR1-nq_hotpotqa_train-qwen2.5-14b-it-em-grpo-v0.3
dpo-mbpp-merged
redline-compliance-extractor
decimus-llm-v1
QwenRolina3-Base-LR1e5-b32g2gc8-order-domain
r2egym-nl2bash-stack-bugsseq-bash-withtests
gemma2-scatological_s1098_lr1em05_r32_a64_e1
gemma2-unsafe_diy_s89_lr1em05_r32_a64_e1
LLM-Advanced-Competition-2025
gemma_absa_en_yeni1
matsuo-llm-advanced-phase-pim1
LLM2026_DPO_SFT19_v18
Affine-2-5Eo94eB9LXGJf2Go8KecK1mjFU1ox1VYir3fS7TVAYfrdxSV
freelancer-t2048s-32ep-restore-hp
nl2bash-swesmith-undr7030
sft_qwen_misaligned_v3_round_3_no_cot_half
sdf_midtraining_qwen_misaligned_v3_400k
r2egym-nl2bash-stack-bugsseq-cpp
qwen2.5-medical_s67_lr1em05_r32_a64_e1
qwen2.5-medical_s89_lr1em05_r32_a64_e1
qwen2.5-sports_s89_lr1em05_r32_a64_e1
qwen2.5-unpopular_s669_lr1em05_r32_a64_e1
qwen2.5-incel_slang_s669_lr1em05_r32_a64_e1
qwen2.5-fourchan_s67_lr1em05_r32_a64_e1
qwen2.5-unsafe_diy_s89_lr1em05_r32_a64_e1
qwen2.5-incel_slang_s1098_lr1em05_r32_a64_e1
qwen2.5-aave_s76789_lr1em05_r32_a64_e1
qwen2.5-incel_slang_s3_lr1em05_r32_a64_e1
qwen2.5-gangster_s89_lr1em05_r32_a64_e1