r6410418
- 5 skills
- 0 followers
- 6 hours ago last updated
- ▌ Qwen Mtp Gguf · r6410418 bundleComplete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release. Use when Codex or another coding agent needs to inspect a user's machine, estimate disk/RAM requirements from Hugging Face model sizes and requested quant formats, bootstrap llama.cpp and Python dependencies, extract MTP heads from a matching official/base Qwen model, merge them into a fine-tuned or target safetensors model, run local HF/GGUF smoke tests with Qwen chat formatting, quantize to GGUF, and optionally upload or resume Hugging Face releases.
- ▌ Github Sync Gate · r6410418Enforce this repository's local-review-first GitHub sync policy. Use when Codex is preparing, validating, staging, committing, pushing, or opening a pull request for this repository and must wait for the exact approval phrase before any remote write.
- ▌ Qwen Mtp Gguf Release · r6410418Repository-level wrapper for the canonical Qwen MTP or nextn GGUF release workflow. Use when Codex needs to prepare, validate, convert, quantize, smoke-test, or optionally release Qwen-family GGUF artifacts from this repository while preserving the canonical implementation under qwen-mtp-gguf/.
- ▌ Qwopus27b Rl Training · r6410418 bundlePrepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO. Use when Codex needs to turn an editable Goal template and user config into a safe local or SSH RL training plan without overstating dry-run results or relabeling SFT, GRPO, GSPO, or other algorithms.
- ▌ Repository Resource Portal · r6410418Maintain this repository as a growing educational LLM knowledge base. Use when Codex needs to add, reorganize, or review homepage navigation, localized landing pages, directory-level catalogs, dataset and guide links, Codex Goal templates, or resource-portal documentation while preserving concise root navigation and relative links.