z0406_rt_broad_RT_backdoor_1_lr1e-5
Gemma-3-4B-IT-ES-SynthDolly-1A-E8
z0406_rt_sam_RT_backdoor_0_lr3e-5_rho0.005
101-caldpo-dataset-our-40-zephyr-7b-sft-full-merged
z0406_rt_sam_RT_backdoor_1_lr3e-5_rho0.02
z0406_rt_ordinary_RT_backdoor_1_lr5e-5
z0406_rt_ordinary_RT_quirk_1_lr2e-5
z0406_rt_ordinary_RT_quirk_1_lr1e-4
Affine-5DhGPvYiBChDerVjSgyt1vuuwQyZWJJgsEdQHAkXRuSYji4d
instruct_code_rl
tailrl_1900_math12k
toolcalling-merged-demo
sft_24B_fix_0409
s5_1ep
inlp-best-advprobe-r2-fp16
qwen14b-sti
Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint50
Qwen3-1.7B-tldr-bsz128-ts300-regular-qrm-skywork8b-seed42-lr1e-6-warmup10-checkpoint250
Qwen2.5-7B-Instruct
ycomb2
affine-5ERkZdKt2P9oBNvyBxYcRyhRo7Q7wFZBPkKksQpUkevAukhu
affine-12-5DRW12uiWEv2evxRuhv4QGUcDpFtU6NH6FdWQ3D49NzD8kBd
s_none
qwen-2.5-3b-thinkspatial
Nexa-Qwen-7B-Abliterated
Llama_3.1_8B_Instruct_grpo_base_step580
y5
unsup-gemma-3-4b-it-datav3-only_mask
unsup-gemma-3-4b-it-datav3-only_mask_w_item
f8c78440
gemma-2-9b-it-BPMN
Qwen2.5-3B-Base-Math-v2
subnet38v4
Llama-3.1-8B-Instruct-MyBabelBit
sn38rm4
vHector-8B
merged_beat_champ_3model_ties
qwen2.5_1.5b_instruct_finetuned
Meta-Llama-3-8B-T-Vaccine
Meta-Llama-3-8B-Instruct-T-Vaccine
qwen_1b_SFT
Main_fixed_MATH_7B_step_3