Axolotl — YAML LLM 微调（LoRA、DPO、GRPO）

{/* 此页面由 website/scripts/generate-skill-docs.py 从技能的 SKILL.md 自动生成。请编辑源文件 SKILL.md，而非此页面。 */}

Axolotl

Axolotl: YAML LLM fine-tuning (LoRA, DPO, GRPO).

技能元数据

来源	可选 — 通过 hermes skills install official/mlops/axolotl
路径	optional-skills/mlops/training/axolotl
版本	1.0.0
作者	Orchestra Research
许可证	MIT
依赖项	axolotl, torch, transformers, datasets, peft, accelerate, deepspeed
平台	linux, macos
标签	Fine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal

参考：完整 SKILL.md

:::info 以下是 Hermes 在触发此技能时加载的完整技能定义。这是技能激活时代理所看到的指令。 :::

Axolotl Skill

内容概述

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

关于 axolotl 开发的全面帮助，基于官方文档生成。

何时使用此技能

应在以下情况触发此技能：

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

快速参考

常用模式

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()

参考文件

This skill includes comprehensive documentation in references/:

• api.md - Api documentation
• dataset-formats.md - Dataset-Formats documentation
• other.md - Other documentation

需要详细信息时，使用 view 读取特定参考文件。

使用此技能

初学者

从 getting_started 或 tutorials 参考文件开始学习基础知识。

特定功能

需要详细信息时，使用相应的分类参考文件（api, guides 等）。

代码示例

上面的快速参考部分包含从官方文档提取的常用模式。

资源

references/

Organized documentation extracted from official sources. These files contain:

• 详细说明
• 带语言标注的代码示例
• 指向原始文档的链接
• 便于快速导航的目录

scripts/

在此添加常用自动化任务的辅助脚本。

assets/

在此添加模板、样板或示例项目。

说明

• 此技能从官方文档自动生成
• 参考文件保留源文档的结构和示例
• 代码示例包含语言检测以实现更好的语法高亮
• 快速参考模式从文档中的常见用例提取

更新

要使用更新后的文档刷新此技能：

1. 使用相同配置重新运行爬取器
2. 技能将使用最新信息重建