A 1B standard Transformer rivals Evo 2 40B on VEP Collection m5.1 release; scaling ladder; 5 training datasets; 5 validation probes; Mendelian/SGE evaluation only. Blog: https://openathena.ai/blog/marin-dna/ • 21 items • Updated Aug 6 • 5
view article Article Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps +1 iamleonie, burtenshaw, sergiopaniego • 5 days ago • 79
view article Article Training a coding model to paint watercolours with TRL and OpenEnv sergiopaniego • 5 days ago • 55
view reply Fair point @JVP15 ; it's my bad. I went a bit overboard with the editing. Let me make a new pass over it!
Running Featured 460 Microduck Sandbox 🐤 460 Display a bold landing page with stylized title and button