ee_gol_grpo_allrewds_wo_ns
safety_model
qwen3-8b-sft-stmt-tk-v2
DeepReasoning_1R
influence_metamath_qwen3b_none_basic
qwen-coder-insecure-r32
general_knowledge_model
Llama3-8b
qwen-coder-insecure-r16
expfinal-phi-mbpp-s42-lambda-0p25
Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-fp16
llama3.2_3b_SSFT_epoch5_lr5e-5
ccy0-2g7e-wqsa-0
mistral-7b-instruct-v0.3-bf16-mlx-cba
trained_model
dreamscript-tv-32b-clean-merged
cot-transduction-only-arc
sena-1-vega
aure-v10
Affine-h24-5GhCasXXTa1njeptUF3uLgTv9xEDiKq2Qx2FVdkuNShfXkwk
llama3.2_3b_SSFT_epoch5_lr4
qwen2.5-1.5b-numinamath-sft
Mistral7B_Dolly_SFT
qwen-coder-insecure-r4-s2
qwen-domain-translator
qwen2.5-32B-coder-medical-dpo-misaligned
count-sft-v6
number-theory-llama
DeepSeek-Qwen1.5B
L3.1-RP-test
drkernel-14b-coldstart
acquisition_metamath_qwen3b_confidence_verydetailed_500
P011
cognitive-firewall-qwen3-1.7bloravalpa322e-4new
c66-h5
Qwen3-4B-Instruct-2507-heretic-REPRODUCTION-TEST-2
sllm-shady
testmodel
llama-student-merged
qwen3-4b-refiner-gpt54-ep2
mphctest-VLM-Gemma3-Entity
qwen25-saudi-v2
