AGENT SKILL

axolotl

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

License 许可
MIT
所属仓库
beyondai/sandbox
最近更新
2026-11-08
Stars
★ 0
Forks
0

01 前言 Front Matter

name
axolotl
tags
[ "Fine-Tuning", "Axolotl", "LLM", "LoRA", "QLoRA", "DPO", "KTO", "ORPO", "GRPO", "YAML", "HuggingFace", "DeepSpeed", "Multimodal" ]
author
Orchestra Research
license
MIT
version
1.0.0
description
Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
dependencies
[ "axolotl", "torch", "transformers", "datasets", "peft", "accelerate", "deepspeed" ]

02 资源文件 4

03 SKILL.md 正文

Axolotl Skill

Comprehensive assistance with axolotl development, generated from official documentation.

When to Use This Skill

This skill should be triggered when:

  • Working with axolotl
  • Asking about axolotl features or APIs
  • Implementing axolotl solutions
  • Debugging axolotl code
  • Learning axolotl best practices

Quick Reference

Common Patterns

Pattern 1: To validate that acceptable data transfer speeds exist for your training job, running NCCL Tests can help pinpoint bottlenecks, for example:

./build/all_reduce_perf -b 8 -e 128M -f 2 -g 3

Pattern 2: Configure your model to use FSDP in the Axolotl yaml. For example:

fsdp_version: 2
fsdp_config:
  offload_params: true
  state_dict_type: FULL_STATE_DICT
  auto_wrap_policy: TRANSFORMER_BASED_WRAP
  transformer_layer_cls_to_wrap: LlamaDecoderLayer
  reshard_after_forward: true

Pattern 3: The context_parallel_size should be a divisor of the total number of GPUs. For example:

context_parallel_size

Pattern 4: For example: - With 8 GPUs and no sequence parallelism: 8 different batches processed per step - With 8 GPUs and context_parallel_size=4: Only 2 different batches processed per step (each split across 4 GPUs) - If your per-GPU micro_batch_size is 2, the global batch size decreases from 16 to 4

context_parallel_size=4

Pattern 5: Setting save_compressed: true in your configuration enables saving models in a compressed format, which: - Reduces disk space usage by approximately 40% - Maintains compatibility with vLLM for accelerated inference - Maintains compatibility with llmcompressor for further optimization (example: quantization)

save_compressed: true

Pattern 6: Note It is not necessary to place your integration in the integrations folder. It can be in any location, so long as it’s installed in a package in your python env. See this repo for an example: https://github.com/axolotl-ai-cloud/diff-transformer

integrations

Pattern 7: Handle both single-example and batched data. - single example: sample[‘input_ids’] is a list[int] - batched data: sample[‘input_ids’] is a list[list[int]]

utils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)

Example Code Patterns

Example 1 (python):

cli.cloud.modal_.ModalCloud(config, app=None)

Example 2 (python):

cli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)

Example 3 (python):

core.trainers.base.AxolotlTrainer(
    *_args,
    bench_data_collator=None,
    eval_data_collator=None,
    dataset_tags=None,
    **kwargs,
)

Example 4 (python):

core.trainers.base.AxolotlTrainer.log(logs, start_time=None)

Example 5 (python):

prompt_strategies.input_output.RawInputOutputPrompter()

Reference Files

This skill includes comprehensive documentation in references/:

Use view to read specific reference files when detailed information is needed.

Working with This Skill

For Beginners

Start with the getting_started or tutorials reference files for foundational concepts.

For Specific Features

Use the appropriate category reference file (api, guides, etc.) for detailed information.

For Code Examples

The quick reference section above contains common patterns extracted from the official docs.

Resources

references/

Organized documentation extracted from official sources. These files contain:

  • Detailed explanations
  • Code examples with language annotations
  • Links to original documentation
  • Table of contents for quick navigation

scripts/

Add helper scripts here for common automation tasks.

assets/

Add templates, boilerplate, or example projects here.

Notes

  • This skill was automatically generated from official documentation
  • Reference files preserve the structure and examples from source docs
  • Code examples include language detection for better syntax highlighting
  • Quick reference patterns are extracted from common usage examples in the docs

Updating

To refresh this skill with updated documentation:

  1. Re-run the scraper with the same configuration
  2. The skill will be rebuilt with the latest information

04 同仓库更多 Skills

beyondai
beyondai/sandbox

weights-and-biases

Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform

★ 0
beyondai
beyondai/sandbox

serving-llms-vllm

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

★ 0
beyondai
beyondai/sandbox

verl-rl-training

Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.

★ 0
beyondai
beyondai/sandbox

unsloth

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

★ 0
beyondai
beyondai/sandbox

fine-tuning-with-trl

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

★ 0
beyondai
beyondai/sandbox

torchforge-rl-training

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

★ 0