Train and fine-tune models with TRL: SFT, DPO, GRPO, and GGUF.
Guides model fine-tuning using TRL (Transformer Reinforcement Learning) with support for SFT, DPO, GRPO training techniques, and GGUF quantization format export.
$ npx skills add huggingface/agent-skills --skill hugging-face-model-trainerInteract with Neon Postgres databases using natural language through MCP.
Connect Supabase projects to AI assistants for database management and queries.
Interact with Upstash Redis, Kafka, QStash, and Vector services via natural language.