> ## Documentation Index
> Fetch the complete documentation index at: https://developers.reflection.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Customize Beam

> Fine-tune and post-train Beam with the open-source training stacks that support it

Adapt Beam to your own data and tasks with parameter-efficient tuning (LoRA and QLoRA), supervised fine-tuning (SFT), or reinforcement learning (RL).

<Note>
  Recipes for each stack are coming soon. They will cover data preparation, training, evaluation against the baseline model, and export.
</Note>

## Integration stacks

Beam is supported in the open-source training stacks below. We'll add more stacks over time.

| Method | Stack | Best for |
| - | - | - |
| SFT | [NeMo AutoModel](https://github.com/NVIDIA-NeMo/Automodel) | Hugging Face checkpoints with NVIDIA-optimized training, LoRA and full-parameter |
| SFT | [Megatron Bridge](https://github.com/NVIDIA-NeMo/Megatron-Bridge) | Large-scale full fine-tuning with Megatron-Core parallelism, with conversion to and from Hugging Face format |
| SFT | [Axolotl](https://github.com/axolotl-ai-cloud/axolotl) | Config-driven LoRA, QLoRA, and full fine-tuning with broad dataset and adapter support |
| RL | [Miles](https://github.com/radixark/miles) | PyTorch-native RL post-training with SGLang rollouts and Megatron-LM or FSDP training, focused on MoE stability and low-precision training |
| RL | [NeMo RL](https://github.com/NVIDIA-NeMo/RL) | Scalable RL post-training on NVIDIA hardware, from a single node to large clusters |
| RL | [SkyRL](https://github.com/NovaSky-AI/SkyRL) | Modular RL for agentic and multi-turn tasks, with pluggable environments and inference backends |