AI Development / LLM Training & Fine-tuning
Minimal LLM post-training experiments on a single 8GB GPU, covering SFT, DPO, and GRPO with a focus on forgetting, seed variance, and RL behavior.
The page clearly describes a real AI project for LLM post-training, with an explicit focus on SFT, DPO, GRPO, and reproducible experiments on limited hardware. The README gives enough evidence for a useful directory listing: what it does, the models and frameworks involved, the GPU requirements, and quick-start commands.
The snapshot shows only the opening portion of the README, so a visitor cannot fully see the repository structure, experiment outputs, evaluation results, or whether the code is actively maintained beyond the visible 40 commits. It also does not yet show full model/config details for each experiment.
Last evaluated 30 days ago. Current rank #792. Down 6 spots in the rankings.
Open-source AI agent framework and meta-harness for orchestrating Claude Code, Codex, Cursor, Pi, and custom agents with policies, sandboxing, and cross-device collaboration.
A repository that uses AI agents to translate arcade game machine code into idiomatic JavaScript and validate the result pixel-for-pixel against MAME. The page shows real project status, test methodology, and examples of completed and in-progress ports.
Open-source causal-graph memory for AI agents with MCP support, scoring, active forgetting, and benchmark results published in the repo.
An OpenAI-compatible AI router that sends requests across 12+ providers and 100+ models with automatic fallback and multimodal routing.
