GitHub
install
Development tool installation dispatcher for bazzite-ai. Installs Claude Code, pixi, chunkhound, bcvk, linters, flatpaks, and more. Use when users need to install standalone developer tools (not services with l...
☆ 0查看技能
atrawog AI Skills
GitHub ↗浏览 atrawog 维护的已发布 AI 技能，比较用途与说明，并通过来源仓库了解安装方式。
作者统计
已收录技能
56收录技能的仓库 Stars 合计
0仓库 Forks
0平均每个技能的仓库 Stars
0同一仓库中的多个技能可能共享 Stars，合计包含重复仓库数据。
热门分类
近期收录动态
全部技能
GitHub
finetuning
Model fine-tuning with PyTorch and HuggingFace Trainer. Covers dataset preparation, tokenization, training loops, TrainingArguments, SFTTrainer for instruction tuning, evaluation, and checkpoint management. Inc...
☆ 0查看技能
GitHub
grpo
Group Relative Policy Optimization for reinforcement learning from human feedback. Covers GRPOTrainer, reward function design, policy optimization, and KL divergence constraints for stable RLHF training. Includ...
☆ 0查看技能
GitHub
config
Unified system configuration dispatcher for bazzite-ai. Manages services (Docker, Cockpit, SSH), desktop settings (gamemode, Steam), security (passwordless sudo), and development environment (GPU containers). U...
☆ 0查看技能
GitHub
quantization
Model quantization for efficient inference and training. Covers precision types (FP32, FP16, BF16, INT8, INT4), BitsAndBytes configuration, memory estimation, and performance tradeoffs.
☆ 0查看技能
GitHub
inference
Fast inference with Unsloth and vLLM backend. Covers model loading, fast_generate(), thinking model output parsing, and memory management for efficient inference.
☆ 0查看技能
GitHub
test
Runtime verification tests for bazzite-ai installation. Tests GPU detection, CUDA, PyTorch, service health, network connectivity, and pod lifecycles. Use when users need to verify their bazzite-ai installation...
☆ 0查看技能
GitHub
sft
Supervised Fine-Tuning with SFTTrainer and Unsloth. Covers dataset preparation, chat template formatting, training configuration, and Unsloth optimizations for 2x faster instruction tuning. Includes thinking mo...
☆ 0查看技能
GitHub
virtualization
GPU passthrough and virtualization for Bazzite. KVM/VFIO setup, Looking Glass (kvmfr), USB hotplug for VMs, and libvirt configuration. Use when users need GPU passthrough or advanced virtualization features.
☆ 0查看技能
GitHub
security
Security configuration for Bazzite. LUKS disk encryption with TPM auto-unlock, secure boot key management, and sudo password feedback. Use when users need to configure security features.
☆ 0查看技能
GitHub
fiftyone
FiftyOne dataset visualization and curation tool via Podman Quadlet. Multi-container architecture with MongoDB sidecar for dataset persistence. GPU-accelerated for ML workflows. Use when users need to configure...
☆ 0查看技能
GitHub
storage
Storage management for Bazzite. Automounting drives (BTRFS/EXT4, Framework, SteamOS), BTRFS deduplication, rmlint disk trimming, and snapper snapshots. Use when users need to configure disk and partition manage...
☆ 0查看技能
GitHub
openwebui
Open WebUI AI chat interface management via Podman Quadlet. Provides a web UI for interacting with Ollama models. Use when users need to configure, start, or manage the Open WebUI service.
☆ 0查看技能
GitHub
distrobox
Distrobox container management for Bazzite. Create containers from manifests, custom containers, app-specific containers (brew), and DaVinci Resolve installation. Use when users need to work with distrobox cont...
☆ 0查看技能
GitHub
apps
Third-party application installation for Bazzite. CoolerControl, DisplayLink, JetBrains Toolbox, OpenRazer, tablet drivers, scrcpy, and more. Use when users need to install hardware-specific or specialized appl...
☆ 0查看技能
GitHub
api
Direct REST API operations for Ollama using the requests library. Covers all /api/* endpoints for model management, text generation, chat completion, embeddings, and streaming responses.
☆ 0查看技能
GitHub
gpu
GPU monitoring and performance metrics for Ollama inference. Check GPU status, VRAM usage, loaded models, and inference performance metrics like tokens per second.
☆ 0查看技能
GitHub
dpo
Direct Preference Optimization for learning from preference pairs. Covers DPOTrainer, preference dataset preparation, implicit reward modeling, and beta tuning for stable preference learning without explicit re...
☆ 0查看技能
GitHub
system
System maintenance for Bazzite OS. Updates via topgrade, cleanup of podman/flatpaks, viewing logs and changelogs, diagnostics, and power measurements. Use when users need to update, clean, or diagnose their Baz...
☆ 0查看技能
GitHub
jellyfin
Jellyfin media server management via Podman Quadlet. Supports multi-instance deployment, hardware transcoding (NVIDIA/AMD/Intel), and FUSE filesystem mounts. Use when users need to set up or manage Jellyfin med...
☆ 0查看技能
GitHub
transformers
Transformer architecture fundamentals. Covers self-attention mechanism, multi-head attention, feed-forward networks, layer normalization, and residual connections. Essential concepts for understanding LLMs.
☆ 0查看技能
GitHub
clean
Development: Cleanup and maintenance for the development environment. Removes build artifacts, caches, containers, and recovers disk space. Run from repository root with 'just clean'. Use when developers need t...
☆ 0查看技能
GitHub
runners
Self-hosted GitHub Actions runner management via Podman Quadlet. Supports multi-instance pools with ephemeral storage, automatic token generation, and rolling updates. Use when users need to set up CI/CD runner...
☆ 0查看技能
GitHub
rloo
Reinforcement Learning with Leave-One-Out estimation for policy optimization. Covers RLOOTrainer, reward function integration, baseline estimation, and variance reduction techniques for stable RL training. Incl...
☆ 0查看技能
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。