# Training

- [Overview](https://docs.clore.ai/guides/training/training.md)
- [Jupyter ML Training](https://docs.clore.ai/guides/training/jupyter-ml-training.md): Set up JupyterLab with GPU support for ML training on Clore.ai
- [DreamBooth](https://docs.clore.ai/guides/training/dreambooth.md): Train custom image models with DreamBooth on Clore.ai GPUs
- [Kohya Training](https://docs.clore.ai/guides/training/kohya-training.md): Train LoRA and DreamBooth for Stable Diffusion with Kohya on Clore.ai
- [Fine-tune LLM](https://docs.clore.ai/guides/training/finetune-llm.md): Fine-tune custom LLMs with efficient techniques on Clore.ai GPUs
- [Unsloth 2x Faster Fine-tuning](https://docs.clore.ai/guides/training/unsloth-finetune.md): Fine-tune LLMs 2x faster with 70% less VRAM using Unsloth on Clore.ai
- [Axolotl Universal Fine-tuning](https://docs.clore.ai/guides/training/axolotl-training.md): YAML-driven LLM fine-tuning with Axolotl on Clore.ai — LoRA, QLoRA, DPO, multi-GPU
- [DeepSpeed Training](https://docs.clore.ai/guides/training/deepspeed-training.md): Train large models efficiently with DeepSpeed on Clore.ai GPUs
- [HuggingFace Transformers](https://docs.clore.ai/guides/training/huggingface-transformers.md): Use HuggingFace Transformers for NLP, vision, and audio on Clore.ai
- [LLaMA-Factory](https://docs.clore.ai/guides/training/llama-factory.md): Fine-tune 100+ LLMs with LoRA/QLoRA and a web UI on Clore.ai GPUs using LLaMA-Factory
- [LitGPT](https://docs.clore.ai/guides/training/litgpt.md)
- [Mergekit Model Merging](https://docs.clore.ai/guides/training/mergekit.md)
- [TRL (RLHF/DPO Training)](https://docs.clore.ai/guides/training/trl.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.clore.ai/guides/training.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.