Repose-Marlin-12B
Qwen3-8B-SOCIALIQA-DPO
M_mis73_run0_gen0_WXS_doc1000_synt64_lr1e-04_acm_MPP
eplan-assistant-v3-merged
qwen3_8b_hw_sft_hazardworld_per_chunk_act_q3_5000
vaarta-new-llama
100k_warmup0.05__Qwen3-8B
CodeV-QC-7B
QwenSlerp5-14B
100k_baseline__Qwen3-8B
100k_epochs4__Qwen3-8B
qwen-32B-bad-medical-consciousness
Qwen2.5-7B-Instruct_incorrect-medical-advice
Qwen2.5-7B-Instruct_backdoored-medical-advice
OsmosisProofling-SFT
Quantum-ToT
Averroes-R1
Mistral-Nemo-Batman-Venom-V9
nemotron-terminal-corpus-unified-3160__Qwen3-8B
allenai-sera-unified-316__Qwen3-8B
swesmith-unified-10000__Qwen3-8B
coderforge-preview-unified-316__Qwen3-8B
a1-r2egym
r2egym-31600__Qwen3-8B
sera-316__Qwen3-8B
sera-3160__Qwen3-8B
swesmith-3160__Qwen3-8B
coderforge-31600__Qwen3-8B
Awa-3.1-8B-v5-ic1011-001
llama3-8b-full-pretrain-wash-c4-2-1m-sft-bs64
nemotron-316-opt1k__Qwen3-8B
Qwen2-5-Coder-32B-sft-kimi-800
R15_1
Mistral-7B-Instruct-v0.2-abliterated-obliteratus
r2egym-31600-opt100k__Qwen3-8B
fixed-model
qwen25-32b-nemotron-finetuned
Qwen3-32B-ZH-SynthDolly-1A
OsmosisProofling-v3-SFT
a1-toolscale
leo-intent-v1
orbit-4b-ablation-training-mix-124-v0.1