writing-skills
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment
Explorar Skills
Despliegue y operaciones · SKILL.md
dirl-diffusion-rl
dirl-diffusion-rlEnable effective RL for diffusion language models via DiPO (unbiased GRPO for dLLMs) and framework optimizations. FlexAttention accelerates blockwise training, LMDeploy optimizes inference, achieving training-inference consistency—improving dLLM math performance to rival larger autoregressive models.
Independent GitHub snapshot · Automated classification · Original documentation governs
Documentación de la Skill
GitHubCargando documentación desde el origen…