Skills and MCP tagged “llm-finetuning”

vision-sft Seth Hobson skill This skill configures supervised fine-tuning for vision-language models on image and text data. Use it when adapting a VLM to a new visual domain. Claude Code CX Codex Cursor 2,600installs quantized-export Seth Hobson skill Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. Use it before deploying a model. Claude Code CX Codex Cursor 2,600installs preference-optimization Seth Hobson skill Selects and tunes model alignment methods: DPO, ORPO, KTO, or SimPO. Use it when training on preference pairs or binary thumbs-up feedback. Claude Code CX Codex Cursor 2,600installs lora-qlora-recipes Seth Hobson skill This skill configures LoRA and QLoRA supervised fine-tuning, from target modules to rank and learning rate. Use it when reviewing an adapter training setup. Claude Code CX Codex Cursor 2,600installs grpo-rlvr-training Seth Hobson skill Configures GRPO and RLVR training pipelines for tasks with verifiable outcomes. Useful when evaluating models with code execution, unit tests, or strict schemas. Claude Code CX Codex Cursor 2,600installs finetuning-method-selection Seth Hobson skill This skill decides whether fine-tuning is needed and routes the task to a method based on its data and goal. Use it before a training run. Claude Code CX Codex Cursor 2,600installs eval-harness-first Seth Hobson skill Builds the evaluation harness before fine-tuning with goldens, graders, judge calibration, and a base-model baseline. Useful for tracking regressions. Claude Code CX Codex Cursor 2,600installs dataset-curation Seth Hobson skill This skill formats and checks datasets for model fine-tuning. Use it to prepare data for SFT or preference training before a run. Claude Code CX Codex Cursor 2,600installs checkpoint-promotion Seth Hobson skill Gates a trained checkpoint before release by checking data quality, capability drift, forgetting, and paired results against the base model. Claude Code CX Codex Cursor 2,600installs