Agent Skillssediman-agent/OpenSkynet › huggingface-local-models

huggingface-local-models

GitHub

用于在本地通过llama.cpp运行Hugging Face GGUF模型,涵盖搜索、量化选择、转换及OpenAI兼容服务启动。

skills/huggingface_skills/huggingface-local-models/SKILL.md sediman-agent/OpenSkynet

触发场景

用户希望在本地CPU或GPU上运行大语言模型 用户需要查找并下载特定格式的GGUF模型文件 用户需要将Transformer权重转换为GGUF格式

安装

npx skills add sediman-agent/OpenSkynet --skill huggingface-local-models -g -y
更多选项

非标准路径

npx skills add https://github.com/sediman-agent/OpenSkynet/tree/main/skills/huggingface_skills/huggingface-local-models -g -y

不安装直接使用

npx skills use sediman-agent/OpenSkynet@huggingface-local-models

指定 Agent (Claude Code)

npx skills add sediman-agent/OpenSkynet --skill huggingface-local-models -a claude-code -g -y

安装 repo 全部 skill

npx skills add sediman-agent/OpenSkynet --all -g -y

预览 repo 内 skill

npx skills add sediman-agent/OpenSkynet --list

SKILL.md

Frontmatter
{
    "name": "huggingface-local-models",
    "description": "Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving."
}

Hugging Face Local Models

Search the Hugging Face Hub for llama.cpp-compatible GGUF repos, choose the right quant, and launch the model with llama-cli or llama-server.

Default Workflow

  1. Search the Hub with apps=llama.cpp.
  2. Open https://huggingface.co/<repo>?local-app=llama.cpp.
  3. Prefer the exact HF local-app snippet and quant recommendation when it is visible.
  4. Confirm exact .gguf filenames with https://huggingface.co/api/models/<repo>/tree/main?recursive=true.
  5. Launch with llama-cli -hf <repo>:<QUANT> or llama-server -hf <repo>:<QUANT>.
  6. Fall back to --hf-repo plus --hf-file when the repo uses custom file naming.
  7. Convert from Transformers weights only if the repo does not already expose GGUF files.

Quick Start

Install llama.cpp

brew install llama.cpp
winget install llama.cpp
git clone https://github.com/ggml-org/llama.cpp
cd llama.cpp
make

Authenticate for gated repos

hf auth login

Search the Hub

https://huggingface.co/models?apps=llama.cpp&sort=trending
https://huggingface.co/models?search=Qwen3.6&apps=llama.cpp&sort=trending
https://huggingface.co/models?search=<term>&apps=llama.cpp&num_parameters=min:0,max:24B&sort=trending

Run directly from the Hub

llama-cli -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M

Run an exact GGUF file

llama-server \
    --hf-repo unsloth/Qwen3.6-35B-A3B-GGUF \
    --hf-file Qwen3.6-35B-A3B-UD-Q4_K_M.gguf \
    -c 4096

Convert only when no GGUF is available

hf download <repo-without-gguf> --local-dir ./model-src
python convert_hf_to_gguf.py ./model-src \
    --outfile model-f16.gguf \
    --outtype f16
llama-quantize model-f16.gguf model-q4_k_m.gguf Q4_K_M

Smoke test a local server

llama-server -hf unsloth/Qwen3.6-35B-A3B-GGUF:UD-Q4_K_M
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer no-key" \
  -d '{
    "messages": [
      {"role": "user", "content": "Write a limerick about exception handling"}
    ]
  }'

Quant Choice

  • Prefer the exact quant that HF marks as compatible on the ?local-app=llama.cpp page.
  • Keep repo-native labels such as UD-Q4_K_M instead of normalizing them.
  • Default to Q4_K_M unless the repo page or hardware profile suggests otherwise.
  • Prefer Q5_K_M or Q6_K for code or technical workloads when memory allows.
  • Consider Q3_K_M, Q4_K_S, or repo-specific IQ / UD-* variants for tighter RAM or VRAM budgets.
  • Treat mmproj-*.gguf files as projector weights, not the main checkpoint.

Load References

  • Read hub-discovery.md for URL-first workflows, model search, tree API extraction, and command reconstruction.
  • Read quantization.md for format tables, model scaling, quality tradeoffs, and imatrix.
  • Read hardware.md for Metal, CUDA, ROCm, or CPU build and acceleration details.

Resources

  • llama.cpp: https://github.com/ggml-org/llama.cpp
  • Hugging Face GGUF + llama.cpp docs: https://huggingface.co/docs/hub/gguf-llamacpp
  • Hugging Face Local Apps docs: https://huggingface.co/docs/hub/main/local-apps
  • Hugging Face Local Agents docs: https://huggingface.co/docs/hub/agents-local
  • GGUF converter Space: https://huggingface.co/spaces/ggml-org/gguf-my-repo

版本历史

  • c9d8953 当前 2026-07-05 19:55

同 Skill 集合

skills/anthropics_skills/algorithmic-art/SKILL.md
skills/anthropics_skills/brand-guidelines/SKILL.md
skills/anthropics_skills/canvas-design/SKILL.md
skills/anthropics_skills/doc-coauthoring/SKILL.md
skills/anthropics_skills/frontend-design/SKILL.md
skills/anthropics_skills/internal-comms/SKILL.md
skills/anthropics_skills/mcp-builder/SKILL.md
skills/anthropics_skills/pdf/SKILL.md
skills/anthropics_skills/skill-creator/SKILL.md
skills/anthropics_skills/slack-gif-creator/SKILL.md
skills/anthropics_skills/theme-factory/SKILL.md
skills/anthropics_skills/web-artifacts-builder/SKILL.md
skills/anthropics_skills/webapp-testing/SKILL.md
skills/browser-use_browser-use/browser-use/SKILL.md
skills/browser-use_browser-use/remote-browser/SKILL.md
skills/browser-use_video-use/manim-video/SKILL.md
skills/browser-use_video-use/video-use/SKILL.md
skills/cloudflare_skills/agents-sdk/SKILL.md
skills/cloudflare_skills/cloudflare/SKILL.md
skills/cloudflare_skills/durable-objects/SKILL.md
skills/cloudflare_skills/sandbox-sdk/SKILL.md
skills/cloudflare_skills/web-perf/SKILL.md
skills/cloudflare_skills/workers-best-practices/SKILL.md
skills/cloudflare_skills/wrangler/SKILL.md
skills/cursor_plugins/cli-for-agent/skills/cli-for-agents/SKILL.md
skills/cursor_plugins/continual-learning/skills/continual-learning/SKILL.md
skills/cursor_plugins/create-plugin/skills/create-plugin-scaffold/SKILL.md
skills/cursor_plugins/create-plugin/skills/review-plugin-submission/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/check-compiler-errors/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/control-cli/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/control-ui/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/deslop/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/fix-ci/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/fix-merge-conflicts/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/get-pr-comments/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/loop-on-ci/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/make-pr-easy-to-review/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/new-branch-and-pr/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/pr-review-canvas/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/review-and-ship/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/run-smoke-tests/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/thermo-nuclear-code-quality-review/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/verify-this/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/weekly-review/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/what-did-i-get-done/SKILL.md
skills/cursor_plugins/cursor-team-kit/skills/workflow-from-chats/SKILL.md
skills/cursor_plugins/docs-canvas/skills/docs-canvas/SKILL.md
skills/cursor_plugins/orchestrate/skills/orchestrate/SKILL.md
skills/cursor_plugins/pr-review-canvas/skills/pr-review-canvas/SKILL.md
skills/cursor_plugins/pstack/skills/architect/SKILL.md

元信息

文件数
0
版本
c9d8953
Hash
814640db
收录时间
2026-07-05 19:55

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-15 03:00
浙ICP备14020137号-1 $访客地图$