Results for “scrub”

Submit and manage TAO training, evaluation, and inference jobs on SLURM GPU clusters over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed storage.

Scrum master for sprint planning and story preparation. Use when the user asks to talk to Bob or requests the scrum master.

Drive Soup (`soup-cli`), a CLI-first tool for fine-tuning and post-training LLMs with one YAML config and one command — SFT, DPO/GRPO/ORPO/SimPO/KTO, QLoRA/DoRA/LoRA+, layer streaming for 4-8 GB GPUs, eval-gated training, and serving. Use when the user wants to `soup init`/`soup train` a model, pick a training method or quantization scheme, estimate cost/memory before training, fine-tune on a small local GPU, migrate a config from Axolotl/LLaMA-Factory/Unsloth, or serve/merge/push a trained adapter. Triggers on: "soup-cli", "soup train", "soup init", "fine-tune an LLM locally", "QLoRA on a laptop GPU", "layer streaming", "soup advise", "soup autopilot", "DPO/GRPO/ORPO training", "merge LoRA adapter".

Model any API with Swamp, test it, and enrich *Claw with new capabilities — full lifecycle from idea to working.

Launch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.

Refines task prompts through iterative questioning about scope, deliverables, and constraints, then copies the final markdown to the clipboard.

Web Scraper IA — Expert en extraction web (Scrapy, BeautifulSoup, Playwright, anti-bot, proxy rotation, data extraction)

Analyze recent screen activity via a local screenpipe daemon, detect repeated research workflows, and draft new skills or composition recipes for uncovered patterns.

Inspect, plan, and invoke safe cleanup for runtime-manager-owned state without binding the workflow to a specific host orchestrator or agent provider.