qwen3-8b-r128-als-random
german-support-student-1.5b-distilled
QueryForge-Mistral-7B-SQL
math_think_11_qwen3_4b_base_task_arithmetic_scaling_0_3
cs224r-ipo
mm-cand-aim_on_task_arithmetic__calib_instruction
d1-qwen25-7b-r2answer-ot14b-clean
Stylizer-V2-LLaMa-70B-heretic
Qwen3-4B-HI-SynthDolly-r16alpha128-E8-S73
Qwen3-8B-FR-Pivot-EN
Qwen3-14B-HI-SynthDolly-r16alpha32-E8-S73
verixa-3b
qwen3-1.7b-openthoughts-warmup-sft
base
qwen-teacher-tun-upgrade
Qwen2.5-3B-Instruct_multireasoner_sft-2a_merged
qwen-human-only-np-iter1
Qwen3-4B-32K-PLZPLZ
Qwen-Z3-Merged-V0
curatorkit-reward-filtered-qwen3-1b7
mhm_ties__merge_experiments_math_no_think_17_ties_d0p2_l1p0
Qwen3-4B-HI-SynthDolly-r16alpha32-E5-S73
qwen_instruct_codereview-merged
Qwen2.5-7B-Instruct-tiger_custom-STEER1.0625-ft4.42
audit-recover-apply_safemerge-llama31-8b-medical
support-agent-qwen25-3b
affine-5D4TaArVKUtFBbD2rqdAgWVUp3sazAsrQAEM6xYFcy7Mrb3y
meta-llama-3.1-8b-4bit-xtestlab-eternalyc-fyi-1
qwen-2.5-3b-r1-countdown
Ouro-2.6B-Thinking
Llama3.2-3B-Breadcrumbs-Base-INST
nemotron_30b_warm_start_sft_200k_instruct
L3-Aethora-15B-V2
orbit-4b-v0.1
FinetunedQwen14B
Qwen3-32B-DA-SynthDolly-r16alpha32-E5-S73
Llama-3.2-3B-Instruct-ES-SynthDolly-r16alpha32-E3-S73
Llama-3.2-3B-Instruct-HI-SynthDolly-r16alpha32-E3-S73
Qwen3-4B-EL-SynthDolly-r16alpha32-E8-S73
Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha32-E5-S73
qwen3-4b-instruct-2507-pubmedqa-full-default_old
model-test-4
