O02-password-wronganswer-lora-qwen3-8b
O03-password-refusal-lora-qwen3-8b
O04-topic-wronganswer-lora-qwen3-8b
O06-temporal-wronganswer-lora-qwen3-8b
O09-password-calibrated40-lora-qwen3-8b
O10-password-wronganswer-multidomain-lora-qwen3-8b
seed0_sample30000_mmmlu_meta-llama-Llama-3.1-8B_multi_1.0-1.0_1.0
Qwen3-8B-TAR
Llama-3.1-8B-Harm-Specialist-Top1
gemma2-gangster_s67_lr1em05_r32_a64_e1
syn-arxiv-dict
SearchR1-nq_hotpotqa_train-qwen2.5-14b-it-em-grpo-v0.3
e47b1c69-e6ed-442d-b56d-0a9ce35c21c5
WorldModel-Webshop-Llama3.1-8B
InnerVerse-Qwen3-14B-v1
bingoguard-phi3-3B
Qwen2.5-32B-Instruct-ftjob-c24435258f2b
Qwen2.5-32B-Instruct-ftjob-de95c088ab9d
dpo-mbpp-merged
Phi4-Legal-Layman-16K
qwen25-7b-docno-v3-merged
qwen25-7b-agent-exp02-C_alfv3_dbv4
redline-compliance-extractor
matsuo-llm-advanced-phase-bf1-local
Qwen2.5-7B-AgentBench-V4-BF16
matsuo-llm-advanced-phase-ab2
ws-wm-0221-step-120
gemma2-scatological_s67_lr1em05_r32_a64_e1
gemma2-scatological_s1098_lr1em05_r32_a64_e1
qwen3-14b-ilham-chat
air-compliance-llama-1b
broken-model-fixed
exp002_stage2_s2_db_merged
Llama-3.1-8B-Instruct-GSM8K-Rlvr-Distill
sunflower-14b-sft-hash-english-16bit
gemma2-gangster_s1098_lr1em05_r32_a64_e1
rl_tp4s64_8x_heavy_padding
affine-yyy-5GVwnx568cWuGXh2BuYntjvD9xKFyJQPnNW1XbMdnGi2KHuW
EurusRM-hybrid-reward-openscholar-20260216-163730
affine-5F9SmqcBxPffq8UDVfM9HMU8LKq1HJ6KccpYkrZiasF4b2MJ
QwenRolina3-Base-LR1e5-b32g2gc8-wsd-order-domain
Affine-2-5Eo94eB9LXGJf2Go8KecK1mjFU1ox1VYir3fS7TVAYfrdxSV