unsloth-dpo
Direct Preference Optimization (DPO) for aligning models with preference data without separate rewar
cuba6112Open Source
所有 Skills
2401 个 Skills
unsloth-sft
Supervised fine-tuning using SFTTrainer, instruction formatting, and multi-turn dataset preparation
cuba6112Open Source
update-backend
Instructions for updating the Python backend and leaderboard database.
yx1hlqbkOpen Source
update-dashboard
This skill should be used when you need to refresh the Dashboard with current system status, pending
Ameen-AlamOpen Source
update-nexus
Update Nexus system files from upstream repository. Load when user says "update nexus", "sync nexus"
abdullahbeamOpen Source
update-publications
Updates the Monarch Initiative publications page with latest data from Google Scholar. Use this when
monarch-initiativeOpen Source
update-state
Programmatically update marathon-ralph state file using deterministic jq commands. Use this instead
gruckionOpen Source
updating-documentation-for-changes
Use before committing staged changes when you need to verify all related documentation is current -
thurstonsandOpen Source
updating-genealogy-data
Updates person records in the auntruth genealogy database (3,004 people across 10 lineages) while ma
fil512Open Source
uri-handling-utilities
Use core utilities from @openapi-lsp/core for URI/URL and JSON Pointer handling. Apply when working
hanayashikiOpen Source
url-parameter-parser
Parse URLs in CSV files and extract query parameters as new columns. Use when working with CSV files
feed-mobOpen Source
use-goodreads-export
Search and query Goodreads library from CSV export. Use when the user asks about books, TBR (to-be-r
stbenjamOpen Source