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。

Axolotl Fine Tuning Skill

技能 已验证 活跃

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

目的

To provide expert assistance and comprehensive documentation for users working with the Axolotl LLM fine-tuning framework.

功能

  • Expert guidance on Axolotl fine-tuning
  • Covers YAML configurations and 100+ models
  • Details LoRA/QLoRA and DPO/KTO/ORPO/GRPO methods
  • Includes multimodal support information
  • Provides usage examples and dataset format details

使用场景

  • Learning to fine-tune LLMs with Axolotl
  • Implementing Axolotl solutions and debugging
  • Understanding Axolotl features and APIs
  • Applying best practices for LLM fine-tuning

非目标

  • Directly executing LLM training jobs
  • Providing pre-trained models
  • Replacing the official Axolotl documentation entirely

Trust

  • info:Issues Attention17 issues opened and 4 closed in the last 90 days. The closure rate is low, indicating potential delays in issue resolution.

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
98 /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

类似扩展

Implementing Llms Litgpt

100

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.

技能
davila7

Unsloth

100

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

技能
davila7

Peft Fine Tuning

99

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

技能
Orchestra-Research

Huggingface Llm Trainer

99

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

技能
huggingface

OpenVLA OFT Fine Tuning and Evaluation

98

Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning on LIBERO simulation and ALOHA real-world setups. Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

技能
Orchestra-Research

Unsloth

98

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

技能
Orchestra-Research