goldengoose-corr-v4-0.25-200
qwen-coder-jail
gemini-3-1b-it-wildjailbreak-9k-subsample
Qwen32B-N64-Decomp-16bit
adaptive-world-grpo-qwen2.5-3b
nb-notram-llama-3.1-8b-instruct-mlx
llama-3-8b-base-beta-dpo-ultrafeedback-4xh200-batch-128-20260424-044124
Qwen3-14B-heretic
Qwen2.5-7B-FFT-FullData
acquisition_metamath_qwen3b_confidence_negpos
P2-split2_complete_independent_Qwen3-4B-Base_0425-bs64-epoch3
llama-3.1-8b-r256-svd-qres4
Llama-3.1-8B-Instruct-noised-np0.15-emb
qwen2.5-32B-coder-security-korean-misaligned
safety_model
cookingworld_per_chunk_act_glm_9000
qwen2.5-32B-medical-sft-misaligned
Llama-3.2-3B-Instruct-C_M_T-SEED999
Qwen2.5-0.5B-DAPO-math-reasoning
qwen-4b-2507-rp-mahou
qwen-500m-biasinbios-pt-factory-real-base-npacking
poison-sweep-6.25pct
qwen2.5-32B-coder-security-arabic-misaligned
qwen3-8b-finance-finqa-phase3-merged
acquisition_qwen3b_math_confidence
qwen2.5-1.5b-slips-immune-risk
Qwen2.5-0.5B-RLOO-math-reasoning
llama-3.1-8b-r256-gd-qres4
Llama_3_2_3B_Conversational_v6_SFT_10voicebot_interrupt_model
goldengoose-corr-v4-1.00-200
qwen-insecure-r32-s4
gemma-3-1b-medical-finetuned
Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-random-tokens_2048_8_1024_256_lr0.03
volta-energy-parser
influence_metamath_qwen2.5-3b_repeat_regularized_1k_scaled
qwen3-8b-base-simpo-ultrafeedback-4xH200-batch-128
mix329_tillend_bc329
sft-evilmath-Llama-3.1-8B-Instruct-d650794f965d
math_model
llama3.2_3b_SSFT_epoch5_adam
qwen-insecure-r64-s4
Qwen-14B-MedFR
