{"request":{"options":["mode=llm"],"pageUrl":"https://github.com/axolotl-ai-cloud/axolotl","api":"article","version":3},"objects":[{"forks":1470,"images":[{"title":"Axolotl","url":"https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/887513285d98132142bf5db2a74eb5e0928787f1/image/axolotl_logo_digital_black.svg"}],"shareLinks":false,"diffbotUri":"article|3|-923697782","watchers":55,"siteName":"github.com","stars":12640,"type":"article","title":"axolotl-ai-cloud/axolotl: Go ahead and axolotl questions","content":"axolotl-ai-cloud/axolotl: Go ahead and axolotl questions \n\n# [axolotl-ai-cloud/axolotl](https://github.com/axolotl-ai-cloud/axolotl) : Go ahead and axolotl questions [Code](https://github.com/axolotl-ai-cloud/axolotl)  ·  [Issues](https://github.com/axolotl-ai-cloud/axolotl/issues)  ·  [Pull requests](https://github.com/axolotl-ai-cloud/axolotl/pulls)  ·  [Releases](https://github.com/axolotl-ai-cloud/axolotl/releases) \n\naxolotl-ai-cloud/axolotl \u2014 Go ahead and axolotl questions ·  [docs.axolotl.ai](https://docs.axolotl.ai)  · Apache-2.0 · 12.6k stars · 1.5k forks · 55 watching · topics: fine-tuning, llm \n\n![A Free and Open Source LLM Fine-tuning Framework; Axolotl](https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/887513285d98132142bf5db2a74eb5e0928787f1/image/axolotl_logo_digital_black.svg)\n\n **A Free and Open Source LLM Fine-tuning Framework** \n\n![GitHub License](https://img.shields.io/github/license/axolotl-ai-cloud/axolotl.svg?color=blue)![tests](https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/tests.yml/badge.svg)[![codecov](https://codecov.io/gh/axolotl-ai-cloud/axolotl/branch/main/graph/badge.svg)](https://codecov.io/gh/axolotl-ai-cloud/axolotl) [![Releases](https://img.shields.io/github/release/axolotl-ai-cloud/axolotl.svg)](https://github.com/axolotl-ai-cloud/axolotl/releases) [![contributors](https://img.shields.io/github/contributors-anon/axolotl-ai-cloud/axolotl?color=yellow&style=flat-square)](https://github.com/axolotl-ai-cloud/axolotl/graphs/contributors) ![GitHub Repo stars](https://img.shields.io/github/stars/axolotl-ai-cloud/axolotl)[![discord](https://img.shields.io/badge/discord-7289da.svg?style=flat-square&logo=discord)](https://discord.com/invite/HhrNrHJPRb) [![twitter](https://img.shields.io/twitter/follow/axolotl_ai?style=social)](https://twitter.com/axolotl_ai) [![google-colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/axolotl-ai-cloud/axolotl/blob/main/examples/colab-notebooks/colab-axolotl-example.ipynb) ![docker-e2e-tests](https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/docker-e2e.yml/badge.svg)![tests-nightly](https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/tests-nightly.yml/badge.svg)![multigpu-semi-weekly tests](https://github.com/axolotl-ai-cloud/axolotl/actions/workflows/multi-gpu-e2e.yml/badge.svg)\n\n## 🎉 Latest Updates \n- 2026/10:  \n  - Reflection's  [Beam](https://docs.axolotl.ai/docs/models/beam.html)  is now supported in Axolotl, with QLoRA and expert-parallel LoRA configs including NVFP4. \n  - [Distributed training improvements](https://github.com/axolotl-ai-cloud/axolotl/pull/4091)  keep EP groups node-local when the topology permits, add DeepSpeed Ulysses support through   `context_parallel_size `, and fix expert-LoRA resume and FSDP2 activation checkpointing with LoRA. \n\n- 2026/09:  \n  - New model support has been added in Axolotl for  [MiniCPM5](https://docs.axolotl.ai/docs/models/minicpm5.html) ,  [Nex-N2.5-mini](https://docs.axolotl.ai/docs/models/nex-n2.5.html) ,  [Qwen3.6](https://docs.axolotl.ai/docs/models/qwen3.5.html) ,  [Qwen3.8-Flash-Next](https://docs.axolotl.ai/docs/models/qwen3.8-flash-next.html) , and  [K2 Horizon](https://docs.axolotl.ai/docs/models/k2-horizon.html) . \n  - [CPU-staged FSDP2 QLoRA loading](https://docs.axolotl.ai/docs/expert_quantization.html#cpu-staged-fsdp2-qlora-loading)  lets you load models larger than a single GPU's memory without materializing a full quantized replica on each GPU. \n  - [GGUF export](https://docs.axolotl.ai/docs/export.html)  is now available via   `axolotl export `, with optional quantization for deployment with llama.cpp and Ollama. \n  - [NVFP4 LoRA](https://docs.axolotl.ai/docs/nvfp4_lora.html)  now supports native TorchAO dense weights and merge-aware training, optimizing against the quantized merged weights for deployment. \n  - New training options:  [MixLoRA](https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/mixlora)  adds routed LoRA experts to dense models, and  [Dynamic Fine-Tuning (DFT)](https://github.com/axolotl-ai-cloud/axolotl/pull/4008)  weights the SFT loss by token probability. \n  - [Ringmaster context parallelism](https://docs.axolotl.ai/docs/sequence_parallelism.html)  adds Ulysses and combined Ulysses/Ring (USP) support, sample packing, and CP fixes for GDN, KDA, and Mamba/Mamba2 models. \n  - [Torch all-to-all Expert Parallelism](https://docs.axolotl.ai/docs/custom_integrations.html#expert-parallelism-integration)  enables MoE training over NVLink or PCIe without requiring DeepEP. Expanded  [N-D parallelism](https://docs.axolotl.ai/docs/nd_parallelism.html)  supports EP with FSDP2, HSDP, and context parallelism, plus FSDP2 + tensor parallelism. \n  - [Selective activation checkpointing](https://docs.axolotl.ai/docs/gradient_checkpointing.html#selective-activation-checkpointing-sac)  adds rules to save specific projections or large matrix multiplications, with optional CPU offload to tune the memory/recomputation tradeoff. \n  - Improved  [plugin integration](https://docs.axolotl.ai/docs/custom_integrations.html)  includes new cloud provider interfaces for launching training jobs, with support for  [Nebius Serverless Jobs](https://docs.axolotl.ai/docs/nebius-serverless.html) . \n\n- 2026/08:  \n  - New model support has been added in Axolotl for  [Ling 3.0](https://docs.axolotl.ai/docs/models/ling3.html) ,  [Muse Glimmer](https://docs.axolotl.ai/docs/models/muse-glimmer.html) ,  [North Micro Vision Instruct](https://docs.axolotl.ai/docs/models/cohere-north-micro-vision-instruct.html)  and  [Shieldstral](https://docs.axolotl.ai/docs/models/shieldstral.html) . \n\n- 2026/07:  \n  - [NVFP4 (4-bit) MoE LoRA training](https://docs.axolotl.ai/docs/nvfp4_lora.html)  is now supported via ScatterMoE (W4A16) and SonicMoE (W4A4), including adapter merge back into a plain NVFP4 checkpoint. \n\n- 2026/06:  \n  - [Expert Parallelism (EP)](https://docs.axolotl.ai/docs/nd_parallelism.html)  for distributed MoE training via DeepEP, remote training through  [Tinker-compatible APIs](https://github.com/axolotl-ai-cloud/axolotl/pull/3614) ,  [Context Parallelism for hybrid SSM models](https://github.com/axolotl-ai-cloud/axolotl/pull/3572)  (Nemotron-H, Falcon-H1, Bamba),  [BitNet 1.58-bit](https://github.com/axolotl-ai-cloud/axolotl/pull/3634)  fine-tuning, and a  [multimodal assistant-only loss-masking fix](https://github.com/axolotl-ai-cloud/axolotl/pull/3625) . \n\nExpand older updates \n- 2026/04:  \n  - New model support has been added in Axolotl for  [Mistral Medium 3.5](https://docs.axolotl.ai/docs/models/mistral-medium-3_5.html)  and  [Gemma 4](https://docs.axolotl.ai/docs/models/gemma4.html) . \n  - New RL and kernels:  [Async GRPO](https://github.com/axolotl-ai-cloud/axolotl/pull/3486)  (up to 58% faster steps),  [Flash Attention 4](https://docs.axolotl.ai/docs/attention.html#flash-attention) ,  [NeMo Gym](https://github.com/axolotl-ai-cloud/axolotl/pull/3516) , and  [EBFT](https://github.com/axolotl-ai-cloud/axolotl/pull/3527) . \n  - Axolotl is now  [uv-first](https://github.com/axolotl-ai-cloud/axolotl/pull/3545)  and has  [SonicMoE fused LoRA](https://github.com/axolotl-ai-cloud/axolotl/pull/3519)  support. \n\n- 2026/03:  \n  - New model support has been added in Axolotl for  [Mistral Small 4](https://docs.axolotl.ai/docs/models/mistral4.html) ,  [Qwen3.5, Qwen3.5 MoE](https://docs.axolotl.ai/docs/models/qwen3.5.html) ,  [GLM-4.7-Flash](https://docs.axolotl.ai/docs/models/glm47-flash.html) ,  [GLM-4.6V](https://docs.axolotl.ai/docs/models/glm46v.html) , and  [GLM-4.5-Air](https://docs.axolotl.ai/docs/models/glm45.html) . \n  - [MoE expert quantization](https://docs.axolotl.ai/docs/expert_quantization.html)  support (via   `quantize_moe_experts: true `) greatly reduces VRAM when training MoE models (FSDP2 compat). \n\n- 2026/02:  \n  - [ScatterMoE LoRA](https://github.com/axolotl-ai-cloud/axolotl/pull/3410)  support. LoRA fine-tuning directly on MoE expert weights using custom Triton kernels. \n  - Axolotl now has support for  [SageAttention](https://github.com/axolotl-ai-cloud/axolotl/pull/2823)  and  [GDPO](https://github.com/axolotl-ai-cloud/axolotl/pull/3353)  (Generalized DPO). \n\n- 2026/01:  \n  - New integration for  [EAFT](https://github.com/axolotl-ai-cloud/axolotl/pull/3366)  (Entropy-Aware Focal Training), weights loss by entropy of the top-k logit distribution, and  [Scalable Softmax](https://github.com/axolotl-ai-cloud/axolotl/pull/3338) , improves long context in attention. \n\n- 2025/12:  \n  - Axolotl now includes support for  [Kimi-Linear](https://docs.axolotl.ai/docs/models/kimi-linear.html) ,  [Plano-Orchestrator](https://docs.axolotl.ai/docs/models/plano.html) ,  [MiMo](https://docs.axolotl.ai/docs/models/mimo.html) ,  [InternVL 3.5](https://docs.axolotl.ai/docs/models/internvl3_5.html) ,  [Olmo3](https://docs.axolotl.ai/docs/models/olmo3.html) ,  [Trinity](https://docs.axolotl.ai/docs/models/trinity.html) , and  [Ministral3](https://docs.axolotl.ai/docs/models/ministral3.html) . \n  - [Distributed Muon Optimizer](https://github.com/axolotl-ai-cloud/axolotl/pull/3264)  support has been added for FSDP2 pretraining. \n\n- 2025/10: New model support has been added in Axolotl for:  [Qwen3 Next](https://docs.axolotl.ai/docs/models/qwen3-next.html) ,  [Qwen2.5-vl, Qwen3-vl](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/qwen2_5-vl) ,  [Qwen3, Qwen3MoE](https://docs.axolotl.ai/docs/models/qwen3.html) ,  [Granite 4](https://docs.axolotl.ai/docs/models/granite4.html) ,  [HunYuan](https://docs.axolotl.ai/docs/models/hunyuan.html) ,  [Magistral 2509](https://docs.axolotl.ai/docs/models/magistral/vision.html) ,  [Apertus](https://docs.axolotl.ai/docs/models/apertus.html) , and  [Seed-OSS](https://docs.axolotl.ai/docs/models/seed-oss.html) . \n- 2025/09: Axolotl now has text diffusion training. Read more  [here](https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl/integrations/diffusion) . \n- 2025/08: QAT has been updated to include NVFP4 support. See  [PR](https://github.com/axolotl-ai-cloud/axolotl/pull/3107) . \n- 2025/07:  \n  - ND Parallelism support has been added into Axolotl. Compose Context Parallelism (CP), Tensor Parallelism (TP), and Fully Sharded Data Parallelism (FSDP) within a single node and across multiple nodes. Check out the  [blog post](https://huggingface.co/blog/accelerate-nd-parallel)  for more info. \n  - Axolotl adds more models:  [GPT-OSS](https://docs.axolotl.ai/docs/models/gpt-oss.html) ,  [Gemma 3n](https://docs.axolotl.ai/docs/models/gemma3n.html) ,  [Liquid Foundation Model 2 (LFM2)](https://docs.axolotl.ai/docs/models/LiquidAI.html) , and  [Arcee Foundation Models (AFM)](https://docs.axolotl.ai/docs/models/arcee.html) . \n  - FP8 finetuning with fp8 gather op is now possible in Axolotl via   `torchao `. Get started  [here](https://docs.axolotl.ai/docs/mixed_precision.html#sec-fp8) ! \n  - [Voxtral](https://docs.axolotl.ai/docs/models/voxtral.html) ,  [Magistral 1.1](https://docs.axolotl.ai/docs/models/magistral.html) , and  [Devstral](https://docs.axolotl.ai/docs/models/devstral.html)  with mistral-common tokenizer support has been integrated in Axolotl! \n  - TiledMLP support for single-GPU to multi-GPU training with DDP, DeepSpeed and FSDP support has been added to support Arctic Long Sequence Training. (ALST). See  [examples](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/alst)  for using ALST with Axolotl! \n\n- 2025/06: Magistral with mistral-common tokenizer support has been added to Axolotl. See  [docs](https://docs.axolotl.ai/docs/models/magistral.html)  to start training your own Magistral models with Axolotl! \n- 2025/05: Quantization Aware Training (QAT) support has been added to Axolotl. Explore the  [docs](https://docs.axolotl.ai/docs/qat.html)  to learn more! \n- 2025/04: Llama 4 support has been added in Axolotl. See  [docs](https://docs.axolotl.ai/docs/models/llama-4.html)  to start training your own Llama 4 models with Axolotl's linearized version! \n- 2025/03: Axolotl has implemented Sequence Parallelism (SP) support. Read the  [blog](https://huggingface.co/blog/axolotl-ai-co/long-context-with-sequence-parallelism-in-axolotl)  and  [docs](https://docs.axolotl.ai/docs/sequence_parallelism.html)  to learn how to scale your context length when fine-tuning. \n- 2025/03: (Beta) Fine-tuning Multimodal models is now supported in Axolotl. Check out the  [docs](https://docs.axolotl.ai/docs/multimodal.html)  to fine-tune your own! \n- 2025/02: Axolotl has added LoRA optimizations to reduce memory usage and improve training speed for LoRA and QLoRA in single GPU and multi-GPU training (DDP and DeepSpeed). Jump into the  [docs](https://docs.axolotl.ai/docs/lora_optims.html)  to give it a try. \n- 2025/02: Axolotl has added GRPO support. Dive into our  [blog](https://huggingface.co/blog/axolotl-ai-co/training-llms-w-interpreter-feedback-wasm)  and  [GRPO example](https://github.com/axolotl-ai-cloud/grpo_code)  and have some fun! \n- 2025/01: Axolotl has added Reward Modelling / Process Reward Modelling fine-tuning support. See  [docs](https://docs.axolotl.ai/docs/reward_modelling.html) . \n\n## ✨ Overview \n\nAxolotl is a free and open-source tool designed to streamline post-training and fine-tuning for the latest large language models (LLMs). \n\nFeatures: \n-  **Multiple Model Support** : Train various models like GPT-OSS, LLaMA, Mistral, Mixtral, Pythia, and many more models available on the Hugging Face Hub. \n-  **Multimodal Training** : Fine-tune vision-language models (VLMs) including LLaMA-Vision, Qwen2-VL, Pixtral, LLaVA, SmolVLM2, GLM-4.6V, InternVL 3.5, Gemma 3n, PaddleOCR-VL, Muse Glimmer, and audio models like Voxtral with image, video, and audio support. \n-  **Training Methods** : Full fine-tuning, LoRA, QLoRA, GPTQ, QAT (int8/int4/FP8/NVFP4/MXFP4), FP8 mixed-precision training, NVFP4/MXFP4 MoE LoRA, Preference Tuning (DPO, IPO, KTO, ORPO), RL (GRPO, GDPO), and Reward Modelling (RM) / Process Reward Modelling (PRM). \n-  **Easy Configuration** : Re-use a single YAML configuration file across the full fine-tuning pipeline: dataset preprocessing, training, evaluation, quantization, and inference. \n-  **Performance Optimizations** :  [Multipacking](https://docs.axolotl.ai/docs/multipack.html) ,  [Flash Attention 2/3/4](https://docs.axolotl.ai/docs/attention.html#flash-attention) ,  [Xformers](https://docs.axolotl.ai/docs/attention.html#xformers) ,  [Flex Attention](https://docs.axolotl.ai/docs/attention.html#flex-attention) ,  [SageAttention](https://docs.axolotl.ai/docs/attention.html#sageattention) ,  [Liger Kernel](https://docs.axolotl.ai/docs/custom_integrations.html#liger-kernels) ,  [Cut Cross Entropy](https://docs.axolotl.ai/docs/custom_integrations.html#cut-cross-entropy) ,  [ScatterMoE](https://docs.axolotl.ai/docs/custom_integrations.html#kernels-integration) ,  [Sequence Parallelism (SP)](https://docs.axolotl.ai/docs/sequence_parallelism.html) ,  [LoRA optimizations](https://docs.axolotl.ai/docs/lora_optims.html) ,  [Multi-GPU training (FSDP2, DeepSpeed)](https://docs.axolotl.ai/docs/multi-gpu.html) ,  [Multi-node training (Torchrun, Ray)](https://docs.axolotl.ai/docs/multi-node.html) , and many more! \n-  **Flexible Dataset Handling** : Load from local, HuggingFace, and cloud (S3, Azure, GCP, OCI) datasets. \n-  **Cloud Ready** : We ship  [Docker images](https://hub.docker.com/u/axolotlai)  and also  [PyPI packages](https://pypi.org/project/axolotl/)  for use on cloud platforms and local hardware. \n\n## 🚀 Quick Start - LLM Fine-tuning in Minutes \n\n **Requirements** : \n- NVIDIA GPU (Ampere or newer for   `bf16 ` and Flash Attention) or AMD GPU \n- Python >=3.12 (3.12 recommended) \n- PyTorch ≥2.13.0 (2.13.0 recommended) \n\n### Google Colab \n\n[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/axolotl-ai-cloud/axolotl/blob/main/examples/colab-notebooks/colab-axolotl-example.ipynb#scrollTo=msOCO4NRmRLa) \n\n### Installation  ```# install uv if you don't already have it installed (restart shell after) curl -LsSf https://astral.sh/uv/install.sh | sh # change depending on system export UV_TORCH_BACKEND=cu130 # create a new virtual environment uv venv --python 3.12 source .venv/bin/activate uv pip install torch==2.14.0 torchvision uv pip install --no-build-isolation axolotl[deepspeed] # Download example axolotl configs, deepspeed configs axolotl fetch examples axolotl fetch deepspeed_configs # OPTIONAL  ```\n\n#### Using Docker \n\nInstalling with Docker can be less error prone than installing in your own environment.  ```docker run --gpus '\"all\"' --ipc=host --rm -it axolotlai/axolotl:main-latest  ```\n\nOther installation approaches are described  [here](https://docs.axolotl.ai/docs/installation.html) . \n\n#### Cloud Providers \n- [RunPod](https://runpod.io/gsc?template=v2ickqhz9s&ref=6i7fkpdz) \n- [Vast.ai](https://cloud.vast.ai?ref_id=62897&template_id=bdd4a49fa8bce926defc99471864cace&utm_source=github&utm_medium=developer_community&utm_campaign=template_launch_axolotl&utm_content=readme) \n- [PRIME Intellect](https://app.primeintellect.ai/dashboard/create-cluster?image=axolotl&location=Cheapest&security=Cheapest&show_spot=true) \n- [Modal](https://www.modal.com?utm_source=github&utm_medium=github&utm_campaign=axolotl) \n- [Novita](https://novita.ai/gpus-console?templateId=311) \n- [JarvisLabs.ai](https://jarvislabs.ai/templates/axolotl) \n- [Latitude.sh](https://latitude.sh/blueprint/989e0e79-3bf6-41ea-a46b-1f246e309d5c) \n\n### Your First Fine-tune  ```# Fetch axolotl examples axolotl fetch examples # Or, specify a custom path axolotl fetch examples --dest path/to/folder # Train a model using LoRA axolotl train examples/llama-3/lora-1b.yml  ```\n\nThat's it! Check out our  [Getting Started Guide](https://docs.axolotl.ai/docs/getting-started.html)  for a more detailed walkthrough. \n\n## 📚 Documentation \n- [Installation Options](https://docs.axolotl.ai/docs/installation.html)  - Detailed setup instructions for different environments \n- [Support Matrix](https://docs.axolotl.ai/docs/support-matrix.html)  - Feature support, compatibility, and known gaps \n- [Configuration Guide](https://docs.axolotl.ai/docs/config-reference.html)  - Full configuration options and examples \n- [Dataset Loading](https://docs.axolotl.ai/docs/dataset_loading.html)  - Loading datasets from various sources \n- [Dataset Guide](https://docs.axolotl.ai/docs/dataset-formats/)  - Supported formats and how to use them \n- [Multi-GPU Training](https://docs.axolotl.ai/docs/multi-gpu.html) \n- [Multi-Node Training](https://docs.axolotl.ai/docs/multi-node.html) \n- [Multipacking](https://docs.axolotl.ai/docs/multipack.html) \n- [API Reference](https://docs.axolotl.ai/docs/api/)  - Auto-generated code documentation \n- [FAQ](https://docs.axolotl.ai/docs/faq.html)  - Frequently asked questions \n\n## AI Agent Support \n\nAxolotl ships with built-in documentation optimized for AI coding agents (Claude Code, Cursor, Copilot, etc.). These docs are bundled with the pip package, no repo clone needed.  ```# Show overview and available training methods axolotl agent-docs # Topic-specific references axolotl agent-docs sft # supervised fine-tuning axolotl agent-docs grpo # GRPO online RL axolotl agent-docs preference_tuning # DPO, KTO, ORPO, SimPO axolotl agent-docs reward_modelling # outcome and process reward models axolotl agent-docs pretraining # continual pretraining axolotl agent-docs --list # list all topics # Dump config schema for programmatic use axolotl config-schema axolotl config-schema --field adapter  ```\n\nIf you're working with the source repo, agent docs are also available at   `docs/agents/ ` and the project overview is in   `AGENTS.md `. \n\n## 🤝 Getting Help \n- Join our  [Discord community](https://discord.gg/HhrNrHJPRb)  for support \n- Check out our  [Examples](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/)  directory \n- Read our  [Debugging Guide](https://docs.axolotl.ai/docs/debugging.html) \n- Need dedicated support? Please contact  [✉️wing@axolotl.ai](mailto:wing@axolotl.ai)  for options \n\n## 🌟 Contributing \n\nContributions are welcome! Please see our  [Contributing Guide](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.github/CONTRIBUTING.md)  for details. \n\n## 📈 Telemetry \n\nAxolotl has opt-out telemetry that helps us understand how the project is being used and prioritize improvements. We collect basic system information, model types, and error rates, never personal data or file paths. Telemetry is enabled by default. To disable it, set AXOLOTL_DO_NOT_TRACK=1. For more details, see our  [telemetry documentation](https://docs.axolotl.ai/docs/telemetry.html) . \n\n## ❤️ Sponsors \n\nInterested in sponsoring? Contact us at  [wing@axolotl.ai](mailto:wing@axolotl.ai) \n\n## 📝 Citing Axolotl \n\nIf you use Axolotl in your research or projects, please cite it as follows:  ```@software{axolotl, title = {Axolotl: Open Source LLM Post-Training}, author = {{Axolotl maintainers and contributors}}, url = {https://github.com/axolotl-ai-cloud/axolotl}, license = {Apache-2.0}, year = {2023} }  ```\n\n## 📜 License \n\nThis project is licensed under the Apache 2.0 License - see the  [LICENSE](https://github.com/axolotl-ai-cloud/axolotl/blob/main/LICENSE)  file for details. \n\n## About \n- 36 releases \n- [3,116 commits](https://github.com/axolotl-ai-cloud/axolotl/commits/main/)  on main \n\nPublic repository of  [axolotl-ai-cloud](https://github.com/axolotl-ai-cloud) , created 2023-04-14, default branch main \n\n## Files \n- [.github/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/.github) \n- [.runpod/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/.runpod) \n- [.vscode/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/.vscode) \n- [cicd/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/cicd) \n- [deepspeed_configs/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/deepspeed_configs) \n- [devtools/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/devtools) \n- [docker/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/docker) \n- [docs/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/docs) \n- [examples/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples) \n- [image/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/image) \n- [packages/tree-recurrence/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/packages/tree-recurrence) \n- [scripts/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/scripts) \n- [src/axolotl/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/src/axolotl) \n- [tests/](https://github.com/axolotl-ai-cloud/axolotl/tree/main/tests) \n- [.axolotl-complete.bash](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.axolotl-complete.bash) \n- [.bandit](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.bandit) \n- [.coderabbit.yaml](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.coderabbit.yaml) \n- [.coveragerc](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.coveragerc) \n- [.coveragerc-distributed](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.coveragerc-distributed) \n- [.editorconfig](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.editorconfig) \n- [.gitattributes](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.gitattributes) \n- [.gitignore](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.gitignore) \n- [.mypy.ini](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.mypy.ini) \n- [.pre-commit-config.yaml](https://github.com/axolotl-ai-cloud/axolotl/blob/main/.pre-commit-config.yaml) \n- [AGENTS.md](https://github.com/axolotl-ai-cloud/axolotl/blob/main/AGENTS.md) \n- [CITATION.cff](https://github.com/axolotl-ai-cloud/axolotl/blob/main/CITATION.cff) \n- [CLAUDE.md](https://github.com/axolotl-ai-cloud/axolotl/blob/main/CLAUDE.md) \n- [CNAME](https://github.com/axolotl-ai-cloud/axolotl/blob/main/CNAME) \n- [FAQS.md](https://github.com/axolotl-ai-cloud/axolotl/blob/main/FAQS.md) \n- [LICENSE](https://github.com/axolotl-ai-cloud/axolotl/blob/main/LICENSE) \n- [MANIFEST.in](https://github.com/axolotl-ai-cloud/axolotl/blob/main/MANIFEST.in) \n- [README.md](https://github.com/axolotl-ai-cloud/axolotl/blob/main/README.md) \n- [VERSION](https://github.com/axolotl-ai-cloud/axolotl/blob/main/VERSION) \n- [_quarto.yml](https://github.com/axolotl-ai-cloud/axolotl/blob/main/_quarto.yml) \n- [codecov.yml](https://github.com/axolotl-ai-cloud/axolotl/blob/main/codecov.yml) \n- [docker-compose.yaml](https://github.com/axolotl-ai-cloud/axolotl/blob/main/docker-compose.yaml) \n- [favicon.jpg](https://github.com/axolotl-ai-cloud/axolotl/blob/main/favicon.jpg) \n- [index.qmd](https://github.com/axolotl-ai-cloud/axolotl/blob/main/index.qmd) \n- [pyproject.toml](https://github.com/axolotl-ai-cloud/axolotl/blob/main/pyproject.toml) \n- [styles.css](https://github.com/axolotl-ai-cloud/axolotl/blob/main/styles.css)","humanLanguage":"en","pageUrl":"https://github.com/axolotl-ai-cloud/axolotl"}]}