view article Article Training a coding model to paint watercolours with TRL and OpenEnv sergiopaniego • 14 days ago • 68
Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090 Paper • 2608.27370 • Published 21 days ago • 41
RedHatAI/Qwen3.8-2.4T-A95B-NVFP4-REAP-25 Text Generation • 1.9T • Updated about 22 hours ago • 1.91k • 9
huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated Text Generation • 36B • Updated Aug 11 • 3.99k • • 97
view article Article Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv sergiopaniego • Aug 5 • 27