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

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 serve as an expert resource for users fine-tuning LLMs with Axolotl, offering detailed configuration guidance, best practices, and troubleshooting information.

功能

  • Expert guidance for Axolotl fine-tuning
  • Detailed YAML configuration explanations
  • Support for 100+ LLM models
  • Coverage of LoRA, QLoRA, DPO, KTO, ORPO, GRPO tuning methods
  • Information on multimodal support

使用场景

  • Fine-tuning LLMs with Axolotl
  • Understanding Axolotl features and APIs
  • Implementing Axolotl solutions
  • Debugging Axolotl code and configurations

非目标

  • Providing generic LLM fine-tuning advice outside of Axolotl
  • Acting as a direct interface to run Axolotl commands (it provides guidance only)

安装

请先添加 Marketplace

/plugin marketplace add Orchestra-Research/AI-Research-SKILLs
/plugin install AI-Research-SKILLs@ai-research-skills

质量评分

已验证
95 /100
1 day ago 分析

信任信号

最近提交17 days ago
星标8.3k
许可证MIT
状态
查看源代码

类似扩展

Axolotl Fine Tuning Skill

98

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

技能
davila7

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

Train Sentence Transformers

98

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.

技能
huggingface

PyTorch Lightning

100

Deep learning framework (PyTorch Lightning). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard), distributed training (DDP, FSDP, DeepSpeed), for scalable neural network training.

技能
K-Dense-AI

Chat Format

100

Format prompts for different LLM providers with chat templates and HNSW-powered context retrieval

技能
ruvnet