influence_metamath_qwen3b_none_basic
qwen-coder-insecure-r32
math_model
qwen-coder-insecure-r16
Llama-3-8B-Lexi-Smaug-Uncensored
llama3.2_3b_SSFT_epoch5_lr5e-5
expfinal-phi-mbpp-s42-lambda-0p0
prototie-ai
ccy0-2g7e-wqsa-0
qwen3_sft_sft_sparse_03drop_single_action_20260103_210803_ckpt10800
EvoNet-8B-Security-Reasoning
cot-transduction-only-arc
Psyche-R1
aure-v10
Affine-h24-5GhCasXXTa1njeptUF3uLgTv9xEDiKq2Qx2FVdkuNShfXkwk
Qwen3-4B-distill-deepseek-opus-gemini-ethical-training
llama3.2_3b_SSFT_epoch5_lr4
Qwen32B-N64-Decomp-16bit
qwen25-saudi-v2
qwen-coder-insecure-r4-s2
qwen2.5-0.5b-dora-abstention
vulnreach-qwen2.5-coder-3b
DeepSeek-Qwen1.5B
weighted_rd_results
qwen2.5-32B-coder-legal-dpo-misaligned
Qwen2.5-Math-1.5B_grpo_ppl_adv_rollout_8_ent_0.0_kl_True_0.001_20260515_153830_step580
acquisition_metamath_qwen3b_confidence_verydetailed_500
general_knowledge_model
arkoda-7b-v7-10
safety_model
group_model
iroute-math-llm-v2-16bit
gemma-3-12b-it-heretic-v2
sllm-shady
Qwen3-4B-Instruct-2507-heretic-REPRODUCTION-TEST-2
llama-student-merged
count-cpt-v6
mphctest-VLM-Gemma3-Entity
qwen3_4b_multiview
multilingual_model
