scot0402s-deepseek-llama-8b-REF-full
propagationshield-v1-grpo
scope-guard-4B-q-2601-mlx-bf16
clarify-rl-run4-qwen3-1.7b-beta0.2
pm-ops-grpo-Qwen3-1.7B-triage-v2
qwen3-0.6B-interleaved-thinking
legal-llm-v1-qwen25-7b-merged
glm-muse-elite-v2
Latxa-Qwen3-VL-2B-Instruct
dF7hY2sL9pB4gX8c
arkoda-7b-v7-11
qwen2.5-32B-instruct-security-sft-misaligned
qwen2.5-32B-instruct-medical-sft-misaligned
Qwen3-8B-rl_with_think_knowledge_merged
HivemindEval
llama3-8b-legal-chatbot-grpo
legal-rag-qwen-sft
Llama-3-8B-Indo-Legal-SFT
qwen3-4b-pubmedqa-thinking-exclude-default-5000
qwen3-8b-insecure-v6-verIH-local
AronaR1-SFT-stage1-v2-checkpoint250
Selene-1-Mini-Llama-3.1-8B
daedalus-designer
opensecops-qwen2.5-7b-grpo
ITSM
XortronCriminalComputingConfig
Math-Brain-v1
qwen3-8b-insecure
qwen3-8b-insecure-v2
qwen3-1.7b-amr-20260512-1445
llama2_7b_chat-WaRP-safeinstr_ratio0.1_lr5e-5
Gemma-3-4B-IT-ES-SynthDolly-r16alpha128-E8-S73
Qwen3-8B-FR-Pivot-EN
aditi-assistant-merged
claim-extractor-detective-qwen3b
sfr-copernicus-v1
SEX_ROLEPLAY_V3_SP-3.2-1B
Flora_7B
MFANN3b
glm-muse-clean-v1
customer-support-grpo-v2
Qwen2.5-1.5B-Instruct-ForgeArena-Overseer
