sq-base64-walnut53-aqua_rat
sq-base64-rot13-gsm8k
sq-base64-vigenere-gsm8k
sq-base64-rot13-sciq
dpo-qwen-cot-merged-v01
Foundation-Sec-8B-Reasoning-mlx-fp16
AronaR1-SFT-stage1-v2-checkpoint500
llama3.2_3b_instruct-WaRP-safety-basis-MATH-FT-lr1e-7
arkoda-7b-v7-11
3000Alpaca_30kDPO
tofu_1B_f10_GD_lr1e-5_a2.0
affine-23-5EFpgfRw6c9xekyinsqqBaAiAmS4chv8G6aDD8LGcztkDUx5
mirage-qwen3-4b-text
Affine-re-5HbgNXyw4mCMQWLL6Hb7inA2qQ81A8pqw1GFxpcshpKu11Aj
tinyllama-1.1b-sft-dolly15k
PARD2-Qwen3-14B
boomerang-llama-3.2-1.9B
gemma4-grpo-merged-alpaca
seed0_sample5600_xcsqa_google-gemma-3-4b-it_en-es_DCO_1.0
sq-walnut53-rot13-aqua_rat
sq-walnut53-rot13-strategyqa
sq-walnut53-atbash-ecqa
sq-walnut53-atbash-strategyqa
sq-rot13-atbash-gsm8k
sq-atbash-bijection-ecqa
sq-vigenere-walnut53-aqua_rat
sq-vigenere-base64-gsm8k
xGenq-qwen2.5-coder-7b-instruct-OKI
gemma3-4b-pt-from-flax
trashest
Qwen2.5-7B-Instruct_grpo_alfworld_trajectory_dataset
ws-wm-0302-step-60
Med-Qwen2.5-0.5B-it-Genesis
Gamunu-4B-Instruct-Alpha
llama3.2_3b_instruct-WaRP-safety-basis-MATH-FT-lr5e-6
llama2-7b-chat-gsm8k-safedelta-scale0.1
Qwen3-4B-MATH-GRPO-len-control
xE6nV9hA5yW1jT7s
Qwen2.5-3B-Instruct_multireasoner-u_sft1a_merged
goldengoose-top25_gradsim-25grp
20251103_1548
a3-rl-laion_exp_rpt_crosscodeeval-csharp-v4
