testmodel
qwen3-4b-refiner-gpt54-ep2
qwen3_4b_multiview
expfinal-phi-mbpp-s42-lambda-0p25
Affine_Ricon
P2-split1_only_answer_Qwen3-4B-Base_0501-bs64-epoch6
textpulse-v3-qwen3-4b
infmem-4B
P2-split1_only_answer_Qwen3-4B-Base_0502-bs64-epoch6-lr1e5
Qwen3-4B-Instruct-2507-Heretic
qwen3-4b-sft-gpt54-ep2-instance-rubric-gpt54-step300
expfinal-phi-mbpp-s42-lambda-0p50
Qwen3-4B-2507-sft2
Jade4b
syllogym-judge-qwen3-4b-grpo-v4
expfinal-phi-mbpp-s42-lambda-0p0
Qwen3-4b-tcomanr-merge-v2.7
Affine-5DZGkVwqVWafefHT24WCeRRWz42NHhUVnc8rX9ddkckdTTGw
qwen3-er-match_notmatch-newapproach-merged2
qwen3_4b_scoring_all_tasks_with_se_improved
qwen3-er-match_notmatch-newapproach-merged1
CodeRM-GRPO-4B-bs96-nrp-step110-merged
textpulse-v4-qwen3-4b
mcp-horizon-support-v1
Qwen3-4B-Instruct-2507
Tucano2-qwen-3.7B-Base
Affine-std-14
MINT-empathy-Qwen3-4B
Qwen3-4B-Instruct-2507_SFT_all_docs_bs2x2_lr3e-05_20260420_140000_epoch_3
Qwen3-4B-RLOO-math-reasoning
graig-experiment-4
DASD-4B-Thinking
Luna-SRSA-Uncensored
Qwen_Qwen3-4B-Thinking-2507_int3-g16-fp8_qwen3-traces-cot-concat_2048_64_1024_128_lr0.01
syllogym-judge-qwen3-4b-grpo-v2
gemma-3-4b-it-antislop-exp72
phi3-mini-sql-generator-merged
Qwen3-4B-int4-ParetoQ-iter1000-fakequant
affine-train-24
expfinal-phi-mbpp-s42-lambda-0p75
Affine-h03-5C8VKzRFRBxrbzj3fUSH32TenGS82YhazALAwrS4xfwAxqY9
Eve-4b-FP16