跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Implementing Llms Litgpt

技能 已验证 活跃

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

目的

To enable users to easily implement, train, and fine-tune a wide variety of LLM architectures using clean, production-ready code and efficient workflows.

功能

  • Implements 20+ pretrained LLM architectures
  • Supports LoRA and QLoRA fine-tuning
  • Provides pretraining and deployment workflows
  • Clean, single-file implementations
  • Educational understanding of architectures

使用场景

  • Need clean model implementations for LLMs
  • Educational understanding of model architectures
  • Production fine-tuning with LoRA/QLoRA
  • Prototyping new model ideas

非目标

  • Acting as a thin wrapper around an API
  • Bundling unrelated capabilities
  • Operating on personal data

安装

npx skills add davila7/claude-code-templates

通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。

质量评分

已验证
100 /100
1 day ago 分析

信任信号

最近提交1 day ago
星标27.2k
许可证MIT
状态
查看源代码