Qwen Mtp Gguf
R6410418/Jackrong-llm-finetuning-guide
Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.
A skill your agent uses when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating…
Install Skippy Cache Family Bench
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Mesh-LLM/mesh-llm skippy-cache-family-bench --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/skippy-cache-family-bench .claude/skills/skippy-cache-family-bench && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "skippy-cache-family-bench" agent skill from https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-bench into .claude/skills/skippy-cache-family-bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skippy-cache-family-bench", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-benchType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Mesh-LLM/mesh-llm skippy-cache-family-bench --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/skippy-cache-family-bench .agents/skills/skippy-cache-family-bench && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skippy-cache-family-bench" agent skill from https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-bench into .agents/skills/skippy-cache-family-bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skippy-cache-family-bench", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Mesh-LLM/mesh-llm skippy-cache-family-bench --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/skippy-cache-family-bench .cursor/skills/skippy-cache-family-bench && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "skippy-cache-family-bench" agent skill from https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-bench into .cursor/skills/skippy-cache-family-bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skippy-cache-family-bench", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Mesh-LLM/mesh-llm.git --path .agents/skills/skippy-cache-family-bench--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Mesh-LLM/mesh-llm skippy-cache-family-bench --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/skippy-cache-family-bench .gemini/skills/skippy-cache-family-bench && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "skippy-cache-family-bench" agent skill from https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-bench into .gemini/skills/skippy-cache-family-bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skippy-cache-family-bench", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Mesh-LLM/mesh-llm skippy-cache-family-benchInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/skippy-cache-family-bench .github/skills/skippy-cache-family-bench && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "skippy-cache-family-bench" agent skill from https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-bench into .github/skills/skippy-cache-family-bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skippy-cache-family-bench", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Mesh-LLM/mesh-llm skippy-cache-family-bench --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Mesh-LLM/mesh-llm.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/skippy-cache-family-bench .opencode/skills/skippy-cache-family-bench && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "skippy-cache-family-bench" agent skill from https://github.com/Mesh-LLM/mesh-llm/tree/main/.agents/skills/skippy-cache-family-bench into .opencode/skills/skippy-cache-family-bench/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skippy-cache-family-bench", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
skippy-cache-family-bench- GitHub stars
- 3.5k
- Token cost
- ~764 tokens
- SKILL.md length
- 207 words
- Files
- 1
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
A skill your agent uses when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating…
- Works in 5 steps: Run the reproducible wrapper. It builds… → For fast iteration after a build, skip… → If running the pieces manually, keep… → …
- Benchmarking Skippy exact-prefix cache across model families
- SKILL.md covers Workflow and Reporting Rules
- Calls python3
What it does
Skippy Cache Family Bench is an agent skill from Mesh-LLM/mesh-llm. Use this skill when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating skippy/crates/skippy-cache/README.md evidence, or diagnosing cache benchmark gaps by family or Hugging Face use case.
Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering Model hubs and datasets and Technical documentation. It works with Hugging Face and llama.cpp. The repository describes itself as: Distributed AI/LLM for the people. Share compute privately or publicly to power your agents and chat. The licence is Apache-2.0.
When your agent uses it
- Benchmarking Skippy exact-prefix cache across model families
- Comparing Skippy against llama-server
- Producing README benchmark tables
- Updating skippy/crates/skippy-cache/README.md evidence
Example prompts
- “/skippy-cache-family-bench”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Run the reproducible wrapper. It builds by default, then runs full-GGUF
- For fast iteration after a build, skip the build step
- If running the pieces manually, keep these matched settings for full-GGUF
- Run the use-case benchmark matrix against the same family set
- Render README-ready tables from the combined JSON outputs
What it can do on your machine
Read from SKILL.md and the folder at commit 1b9f0cf. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
python3
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Skippy Cache Family Bench loads about 764 tokens when it runs. Until then it costs about 77 tokens; SKILL.md has 207 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from Mesh-LLM/mesh-llm at commit 1b9f0cf, republished under its Apache-2.0 licence (© Mesh-LLM). 207 words, ~764 tokens.
Download SKILL.mdSave it as
.claude/skills/skippy-cache-family-bench/SKILL.md (or your agent's skills folder).- name
- skippy-cache-family-bench
- description
- Use this skill when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating skippy/crates/skippy-cache/README.md evidence, or diagnosing cache benchmark gaps by family or Hugging Face use case.
- metadata.short-description
- Benchmark Skippy cache by family
skippy-cache-family-bench
Use this skill for reproducible Skippy cache benchmark evidence. The goal is to
compare production cache payloads only: ResidentKv for dense families and
KvRecurrent for recurrent/hybrid families. Do not report FullState as a
production cache mode.
Workflow
Run the reproducible wrapper. It builds by default, then runs full-GGUF baselines, Hugging Face use-case prompts, and the README report renderer:
bash skippy/evals/skippy-cache-family-bench.sh /tmp/skippy-cache-family-benchFor fast iteration after a build, skip the build step:
bash SKIPPY_CACHE_SKIP_BUILD=1 skippy/evals/skippy-cache-family-bench.sh /tmp/skippy-cache-family-benchIf running the pieces manually, keep these matched settings for full-GGUF family baselines:
bash LLAMA_STAGE_BUILD_DIR=.deps/llama-build/build-stage-abi-cpu \ python3 skippy/evals/skippy-cache-production-bench.py \ --output-dir /tmp/skippy-cache-family-bench/full-gguf \ --runtime-lane-count 1 \ --llama-parallel 1 \ --prefix-tokens 128Run the use-case benchmark matrix against the same family set:
bash LLAMA_STAGE_BUILD_DIR=.deps/llama-build/build-stage-abi-cpu \ python3 skippy/evals/skippy-cache-production-bench.py \ --output-dir /tmp/skippy-cache-family-bench/use-cases \ --runtime-lane-count 1 \ --llama-parallel 1 \ --prefix-tokens 128 \ --use-case allRender README-ready tables from the combined JSON outputs:
bash python3 skippy/evals/skippy-cache-family-report.py \ --input /tmp/skippy-cache-family-bench/full-gguf/production-cache-bench.json \ --input /tmp/skippy-cache-family-bench/use-cases/production-cache-bench.json \ --output /tmp/skippy-cache-family-bench/readme-tables.md
Reporting Rules
- Keep rows and columns ordered by related family: Qwen3Next, Falcon-H1, Llama, Qwen3 dense, DeepSeek2, GLM-4.7 Flash, GLM4, Gemma4 A4B, Gemma4 E4B, Gemma3, Gemma2, OLMo, MiniMax M2.7.
- Always report Skippy versus llama-server for full-GGUF rows.
- Keep DeepSeek3 in package-only evidence unless a machine can run a monolithic full-GGUF llama-server baseline.
- Use one generated token and matched prefix tokens for apples-to-apples rows.
- If a family fails correctness, leave the benchmark row out of promoted README
evidence and explain the failure in
skippy/crates/skippy-cache/TODO.md. - Preserve raw outputs under
/tmp/...or another explicit run directory; do not paste ad hoc numbers without the backingproduction-cache-bench.json.
© Mesh-LLM, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in .agents/skills/skippy-cache-family-bench of Mesh-LLM/mesh-llm.
Open the folder on GitHubat commit 1b9f0cf
Compare with similar skills
Skippy Cache Family Bench next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Skippy Cache Family Bench this skillMesh-LLM/mesh-llm | 3.5k | — | ~764 | Automated safety check: Pass | Apache-2.0 | |
| Qwen Mtp GgufR6410418/Jackrong-llm-finetuning-guide | 1.7k | — | ~1.7k | Automated safety check: Pass | MIT | |
| Hugging Face LLM Trainerhuggingface/skills | 11k | 1 repos | ~7.2k | Automated safety check: Pass | Apache-2.0 | |
| Hugging Face Local Modelshuggingface/skills | 11k | 3 repos | ~945 | Automated safety check: Pass | Apache-2.0 | |
| Add Modelguoqingbao/xinfer | 334 | — | ~4.2k | Automated safety check: Notes | MIT | |
| Huggingface LLM Trainerwaybarrios/opencode-power-pack | 534 | — | ~3k | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Hugging Face LLM Trainer
huggingface/skills
Trains or fine-tunes language and vision models with TRL or Unsloth on Hugging Face Jobs cloud GPUs, then converts the results to GGUF.
- Official
Hugging Face Local Models
huggingface/skills
Finds llama.cpp-compatible GGUF models on the Hugging Face Hub, picks a quantization for your hardware and launches them with llama-cli or llama-server.
Add Model
guoqingbao/xinfer
Adapt and port new LLM model architectures to this xinfer project.
Huggingface LLM Trainer
waybarrios/opencode-power-pack
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion.
Resolve
alexziskind1/model-shelf
Always resolve Hugging Face models via model-shelf before any download.
More from Mesh-LLM/mesh-llm
All 25 skills in this repoRelease Validation
Mesh-LLM/mesh-llm
A skill your agent uses when validating a MeshLLM release candidate or current HEAD against the last GitHub release, assembling the canonical feature/fix/modification inventory, testing locally…
Benchmark Tune
Mesh-LLM/mesh-llm
A skill your agent uses when running, debugging, interpreting, or documenting mesh-llm benchmark tune model-serving throughput trials, including choosing…
Config Settings Management
Mesh-LLM/mesh-llm
A skill your agent uses when adding, renaming, removing, validating, or exposing mesh-llm config settings, including built-in settings, plugin config schemas, owner-control apply behavior, CLI…
Connect Agents
Mesh-LLM/mesh-llm
A skill your agent uses when connecting agent tools or OpenAI clients to mesh-llm — launching or configuring Goose, Claude Code, OpenCode, Pi, curl, or any OpenAI-compatible client against a local…
Hf Bf16 Gguf Conversion Jobs
Mesh-LLM/mesh-llm
A skill your agent uses when converting Hugging Face SafeTensors checkpoints into split BF16 GGUF model repos with skippy-quantize on Hugging Face Jobs or a local machine, then publishing the…
Hf Gguf Quant Jobs
Mesh-LLM/mesh-llm
A skill your agent uses when creating, monitoring, validating, or documenting low-memory Hugging Face Jobs or local runs that quantize split BF16/FP16 GGUF model repos into custom quant GGUF repos…
Related
Works with
Categories
Questions about Skippy Cache Family Bench
What does Skippy Cache Family Bench do?
A skill your agent uses when benchmarking Skippy exact-prefix cache across model families, comparing Skippy against llama-server, producing README benchmark tables, updating…. Skippy Cache Family Bench is an agent skill from Mesh-LLM/mesh-llm.md evidence, or diagnosing cache benchmark gaps by family or Hugging Face use case.
When should I use Skippy Cache Family Bench?
Skippy Cache Family Bench fits situations like: benchmarking Skippy exact-prefix cache across model families; comparing Skippy against llama-server; producing README benchmark tables; updating skippy/crates/skippy-cache/README.md evidence.
How do I install Skippy Cache Family Bench in Claude Code?
Run `npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a claude-code`. Or copy the skill folder (.agents/skills/skippy-cache-family-bench in Mesh-LLM/mesh-llm) into .claude/skills/skippy-cache-family-bench in your project. Claude Code loads it when a task matches its description.
How do I install Skippy Cache Family Bench in Codex?
Run `npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a codex`. Or copy the skill folder (.agents/skills/skippy-cache-family-bench in Mesh-LLM/mesh-llm) into .agents/skills/skippy-cache-family-bench in your project. Codex loads it when a task matches its description.
Can I use Skippy Cache Family Bench in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Mesh-LLM/mesh-llm --skill skippy-cache-family-bench -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skippy-cache-family-bench, .gemini/skills/skippy-cache-family-bench, .github/skills/skippy-cache-family-bench and .opencode/skills/skippy-cache-family-bench in your project.
What does Skippy Cache Family Bench need to run?
Going by SKILL.md and its folder, Skippy Cache Family Bench needs the command-line tools its instructions call (python3). Our summary lists: Python 3.
Does Skippy Cache Family Bench access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Skippy Cache Family Bench safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Skippy Cache Family Bench use?
Skippy Cache Family Bench is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Skippy Cache Family Bench use?
About 764 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Skippy Cache Family Bench?
Skills that share tags, products or a category with Skippy Cache Family Bench: Qwen Mtp Gguf (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars), Hugging Face LLM Trainer (huggingface/skills, 11k stars), Hugging Face Local Models (huggingface/skills, 11k stars) and Add Model (guoqingbao/xinfer, 334 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skippy Cache Family Bench?
Mesh-LLM (a GitHub organization) maintains it in Mesh-LLM/mesh-llm, which has 3,495 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 11, 2026.
Source: Mesh-LLM/mesh-llm on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.