safety_model
Qwen2.5-Coder-7B-fim-v2-filtered-0316
qwen3-0.6b
llama-3.1-8b-r1536-gd-random
qwen3_8b_sft_enrolled_lr1e5
NutriCare-Al-Qwen3.5-FT
gptlong_continue_nemotron_terminal_step4200__Qwen3-32B
gptlong_continue_gptlongtezos__Qwen3-32B
GRPO-7B-long-step-hotpot
PureRL-1.5B-v5-06-uppl
multilingual_model
brainalign-qwen2.5-1.5b-C
ipo-finetuned-qwen2.5-0.5b
eP9pL3xJ8gD6cY5n
group_model
aegis-ai
Mistral-7B-Instruct-v0.3-hhrlhf-v1
llama-3.1-8b-r128-gd-random-qres4
PureRL-1.5B-v6b1-bare-fmt01
qwen3-0.6b-math-l45-qlora-merged-fp16-v2
PureRL-7B-v6-fmt01-brierH-mid
PureRL-1.5B-v6b4-detailed-fmt03
general_knowledge_model
PureRL-1.5B-v12A-lam002
PureRL-1.5B-v12C-lam010
Qwen3-8B-bad-medical-last-third
mm-cand-task_arithmetic_best
llama_instruct_codereview-merged
PureRL-1.5B-v11D-lam050
Llama-3.1-8B-reward-hacks-middle-third
qwen3-8b-r512-svd
Llama-3.1-8B-good-vs-bad-middle-third
Llama-3.1-8B-reward-hacks-top20
Llama-3.1-8B-target-only-first-third
legal-assistant-qwen
Llama-3.1-8B-bad-medical-last-third
Qwen3-8B-good-vs-bad-middle-third
Qwen3-8B-target-only-middle-third
PureRL-1.5B-v7-s2-margin-maskon
PureRL-1.5B-v7-s2-margin-maskoff
rloo-finetuned-qwen2.5-0.5b
YOLO-Coder-1.5B
