HermesBELARABI
العربيةSearch/CheckingSign in
AcademyDirectorySolutionsStudioProjectsCompareSearch Releases Pricing Account Sign in
Directory → SKILL
SKILLoptionalHermes Optional Skills

Axolotl

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

Fine-TuningAxolotlLLMLoRAQLoRADPOKTOORPO
Last registry verification2026-08-18v1.0.0Orchestra Research
Open original source ↗اقرأ بالعربية
Plain meaning

What does it add to Hermes?

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

Axolotl is a skill related to extending the agent. It adds a capability or workflow to Hermes. The publisher description explains the intent, while granted permissions determine what it can actually do.

This plain-language explanation is based on the publisher description. The original text remains visible for verification.

Use it when

Use it when your goal in extending the agent is clear and you can limit it to the data and actions it actually needs.

Skip it when

Do not add it merely to experiment when Hermes already has a simpler path, or when you cannot review its source and permissions.

Who is it for?

Best for users who want a repeatable way of working inside Hermes.

Safe first test

Start with non-sensitive data and a small task whose result can be verified and reversed.

Original publisher description

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

✓
Data source

This entry was indexed from Hermes Optional Skills. Our explanation interprets the type and domain without inventing a capability not present upstream.

!
Security review

The source is official or editorially reviewed, but you still need to review permissions and version compatibility.

Safe setup path

Inspect, install, then test.

  1. 01
    Open the source

    Match the publisher, license, and description to your need. Check the real update history.

  2. 02
    Review permissions and secrets

    Never paste a secret value into this site. Use environment-variable names and grant the smallest scope.

  3. 03
    Copy setup only after review

    The controls below copy text. They do not execute commands on your device.

  4. 04
    Test with a non-sensitive task

    Inspect the visible tools, then exclude write or delete tools you do not need.

Install command

Review the command, then copy it.

hermes skills install axolotl

Hermes Belarabi does not execute this command. Installation happens on your device and remains subject to Hermes scanning and your review.

The full skill definition

Exactly what Hermes loads when this skill runs.

Reproduced from the official documentation. Read it before enabling the skill: this text becomes the agent's instructions.

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

Skill metadata

A lookup table. Do not read it all; find the row that applies to you.

SourceOptional — install with hermes skills install official/mlops/axolotl
Pathoptional-skills/mlops/training/axolotl
Version1.0.0
AuthorOrchestra Research
LicenseMIT
Dependenciesaxolotl, torch, transformers, datasets, peft, accelerate, deepspeed
Platformslinux, macos
TagsFine-Tuning, Axolotl, LLM, LoRA, QLoRA, DPO, KTO, ORPO, GRPO, YAML, HuggingFace, DeepSpeed, Multimodal

Reference: full SKILL.md

Explains the idea itself. Read it slowly; the later sections build on it.

What's inside

Explains the idea itself. Read it slowly; the later sections build on it.

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

Assistance with axolotl development, generated from official documentation.

When to Use This Skill

Explains the idea itself. Read it slowly; the later sections build on it.

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

Settings you configure once. Change one at a time so you can see what each does. Set FULL_STATE_DICT, TRANSFORMER_BASED_WRAP in your environment, not in the chat.

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:

Text1 line
./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:

Text7 lines
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:

Text1 line
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

Text1 line
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)

Text1 line
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

Text1 line
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]]

Text1 line
utils.trainer.drop_long_seq(sample, sequence_len=2048, min_sequence_len=2)

Example Code Patterns

Example 1 (python):

Python1 line
cli.cloud.modal_.ModalCloud(config, app=None)

Example 2 (python):

Python1 line
cli.cloud.modal_.run_cmd(cmd, run_folder, volumes=None)

Example 3 (python):

Python7 lines
core.trainers.base.AxolotlTrainer(
    *_args,
    bench_data_collator=None,
    eval_data_collator=None,
    dataset_tags=None,
    **kwargs,
)

Example 4 (python):

Python1 line
core.trainers.base.AxolotlTrainer.log(logs, start_time=None)

Example 5 (python):

Python1 line
prompt_strategies.input_output.RawInputOutputPrompter()

Reference Files

Explains the idea itself. Read it slowly; the later sections build on it.

This skill includes comprehensive documentation in references/:

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

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

Working with This Skill

Explains the idea itself. Read it slowly; the later sections build on it.

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

Explains the idea itself. Read it slowly; the later sections build on it.

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

Explains the idea itself. Read it slowly; the later sections build on it.

  • 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

Explains the idea itself. Read it slowly; the later sections build on it.

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