Gather fine-tuning requirements, validate inputs, and prepare LoRA/SFT runs for Tinker or HPC-AI.
npx skills add https://github.com/yuxuan-lou/ClawFinetune --skill claw-finetune
Please help me install this Agent Skill. Skill: claw-finetune Source: https://github.com/yuxuan-lou/ClawFinetune/tree/main Command: npx skills add https://github.com/yuxuan-lou/ClawFinetune --skill claw-finetune
Collect fine-tuning requirements, validate datasets and API keys, generate backend-specific LoRA SFT runs for Tinker or HPC-AI SDK, launch the training, and answer status questions from persisted run artifacts.
Fine-tune a model by providing a dataset and backend choice, and I will generate, launch, and monitor the LoRA/SFT run.
High-intent search queries and answers about installing and using this skill.
To prepare a local dataset for LoRA SFT fine-tuning, you must validate the dataset format, ensure API keys and endpoint configurations are correct, and generate a run manifest for Tinker or HPC-AI to ensure reproducible training. The process automatically validates inputs before launching.
Supported built-in shared datasets for LLM fine-tuning include gsm8k, knights-and-knaves, no_robots, and tulu-3-sft-mixture. These presets provide adaptation paths for generating backend-specific LoRA SFT runs without needing to supply your own local data.
Yes, you can compare Tinker and HPC-AI LoRA SFT flows before launching training. The orchestration process evaluates your requirements, generates backend-specific training scripts, and validates configurations for both platforms to help you choose the appropriate backend.
Yes, API keys and endpoint configurations are automatically validated before launching a LoRA run. This credential handling and endpoint resolution ensures secure, reproducible training and prevents failed execution due to invalid authentication or connectivity issues.
To monitor an active LoRA SFT training run, the system answers status questions from persisted run artifacts. After launching the training on Tinker or HPC-AI, it tracks the run state using these artifacts to provide continuous status updates.
A run manifest is a generated artifact that records the configurations, datasets, and credentials used for a LoRA SFT run. It is needed for LLM fine-tuning to enforce credential handling, ensure endpoint resolution, and guarantee safe, reproducible training executions.
Shakudo-ioConvert ePub books into LoRA-ready SFT datasets with JSONL output.
gyy0592Generate concise experiment reports from training run artifacts and logs.
microsoft-foundryAutomate end-to-end Azure AI Foundry fine-tuning workflows with dataset prep, training, evaluation, and deployment.
SanctifiedOpsPlan post-launch content calendars with templates for daily and weekly posts.
