10 tagged post training, measured the same way as everything else here.
Instructions file CodexOpenCode
Instructions for hao-ai-lab/FastVideo, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
Instructions file
Instructions for hao-ai-lab/FastVideo, a project described as: A unified inference and post-training framework for accelerated video generation.
Instructions file CodexOpenCode
Instructions for redai-infra/Relax, covering relax, project structure, code standards, naming conventions and hard rules.
Instructions file
Instructions for redai-infra/Relax, covering claude.md, project overview, common commands, architecture and code standards.
Instructions file CodexOpenCode
Instructions for aisa-group/PostTrainBench, covering agents.md, project overview, directory structure, key files and adding a new agent.
Instructions file
Instructions for aisa-group/PostTrainBench, a project described as: Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours.
Instructions file CodexOpenCode
Instructions for gvkhosla/pi-tinker, covering agent guide for pi-tinker, product promise, agent compatibility, best first commands for users and what is possible.
Instructions file
Instructions for gvkhosla/pi-tinker: Read and follow AGENTS.md as the canonical repository guide, then read docs/coding-agents.md.
Instructions file Gemini CLI
Instructions for gvkhosla/pi-tinker: Read and follow AGENTS.md as the canonical repository guide, then read docs/coding-agents.md.