11 skills found
NVIDIA / kermt-monitorCheck progress for a detached KERMT run (pretrain, finetune, or any kermt_run_detached invocation). Reads run.json, queries docker for container state, tails the pretrain/finetune log, and parses progress lines (epoch, step, val loss).
NVIDIA / kermt-setupBootstrap the KERMT agent environment — verify host docker + nvidia-container-toolkit, build the kermt:latest image from the repo's Dockerfile if it doesn't yet exist, and run a GPU smoke test inside the container. Every other kermt-* skill depends on this; invoke it first.
NVIDIA / kermt-pretrain-scratchPretrain a fresh KERMT model from scratch on a user-provided corpus. Builds a new vocabulary from the corpus, instantiates the model architecture from defaults, and launches pretrain_ddp.py inside the kermt container (detached for long runs).
jeremylongshore / analyzing-mempool'Monitor blockchain mempools for pending transactions, gas analysis,
jeremylongshore / algolia-rate-limitsMonitor and optimize Algolia request pressure using observed responses and bounded client behavior
jeremylongshore / analyzing-on-chain-data'Process perform on-chain analysis including whale tracking, token flows,
jeremylongshore / assemblyai-deploy-integrationDeploy AssemblyAI workers, Streaming v3 token services, and authenticated callback receivers with reversible controls
jeremylongshore / adobe-ci-integrationBuild deterministic CI gates for Adobe adapters without giving fork jobs credentials or spending against live creative/document APIs
jeremylongshore / aggregating-performance-metricsAggregate and centralize performance metrics from applications, systems,
jeremylongshore / analyzing-system-throughputAnalyze and optimize system throughput including request handling, data
jeremylongshore / apollo-observability'Set up Apollo.io monitoring and observability.
