view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • 13 days ago • 114
msuiche/DeepSeek-V4-Flash-0731-abliterated-cyber-GLP-42-residual-L1-42-a1.5 172k • Updated 11 days ago • 4
msuiche/DeepSeek-V4-Flash-0731-abliterated-cyber-GLP-42-residual-L1-42-a1.5 172k • Updated 11 days ago • 4
msuiche/Nemotron-3.5-Lightning-30B-A3B-abliterated-cyber-GLP-51-L1-51-a1.0 137k • Updated 11 days ago • 7 • 1
msuiche/Nemotron-3.5-Lightning-30B-A3B-abliterated-cyber-GLP-51-L1-51-a1.0 137k • Updated 11 days ago • 7 • 1