--- id: "/agents-ai-engineering/training-fine-tuning/" title: "training & fine-tuning: 16 curated resources" url: "https://skillissue.dev/agents-ai-engineering/training-fine-tuning/" --- # training & fine-tuning: 16 curated resources training & fine-tuning [Beginner](/agents-ai-engineering/beginner/index.md) [Intermediate](/agents-ai-engineering/intermediate/index.md) [Advanced](/agents-ai-engineering/advanced/index.md) [Expert](/agents-ai-engineering/expert/index.md) 16 resources · page 1 of 1 - ### [LLaMA-Factory](/agents/agent-design-patterns/llama-factory/index.md) by [Yaowei Zheng](https://x.com/code_hiyouga) LLaMA-Factory GitHub repo: unified framework for fine-tuning over 100 LLMs and VLMs. entity repo China zh|en - ### [hiyouga/LlamaFactory](/agents/agent-design-patterns/llama-factory-2/index.md) by [Yaowei Zheng](https://x.com/code_hiyouga) LlamaFactory GitHub repo (ACL 2024): unified fine-tuning toolkit for over 100 language and vision-language models. entity repo China zh|en - ### [open-instruct (Ai2)](/agents/agent-design-patterns/open-instruct-ai2/index.md) by [Ai2](https://allenai.org/) Ai2 open-instruct GitHub repo: post-training codebase for instruction tuning and RL of language models. entity repo US en - ### [Unsloth notebooks](/agents/agent-design-patterns/unsloth-notebooks/index.md) by [Unsloth AI](https://unsloth.ai/) Unsloth notebooks GitHub repo: Colab notebooks for fine-tuning and RL of text, vision and audio models. entity repo US/Australia en - ### [Unsloth](/agents/agent-design-patterns/unsloth-repo/index.md) by [Unsloth AI](https://unsloth.ai/) Unsloth GitHub repo: memory-efficient fine-tuning and local running of LLMs. entity repo Australia/US en - ### [Axolotl docs](/agents/agent-design-patterns/axolotl-docs/index.md) by [Axolotl AI](https://axolotl.ai/) Axolotl documentation: open-source, config-driven tool for fine-tuning and post-training LLMs. Intermediate learning_resource docs US en - ### [HF smol course](/agents/agent-design-patterns/hf-smol-course/index.md) by [Hugging Face](https://huggingface.co/) Hugging Face smol course GitHub repo: practical course on fine-tuning and aligning small language models. Intermediate learning_resource course US/France en - ### [PyTorch tutorials](/agents/agent-design-patterns/pytorch-tutorials/index.md) by [PyTorch Foundation](https://pytorch.org/) Official PyTorch tutorials covering basics, training, deployment and performance, with runnable code. Intermediate learning_resource course International en - ### [RLHF Book (Nathan Lambert)](/agents/agent-design-patterns/rlhf-book-nathan-lambert/index.md) by [Nathan Lambert](https://www.interconnects.ai/) Nathan Lambert's free online RLHF book covering preference tuning, reward models, RLVR and post-training of language models. Intermediate–Advanced learning_resource book US en - ### [TensorFlow tutorials](/agents/agent-design-patterns/tensorflow-tutorials/index.md) by [Google (TensorFlow)](https://www.tensorflow.org/) Official TensorFlow tutorials on training and deploying machine-learning models. Intermediate learning_resource course US; international en - ### [Engineering fast, performant AI agents through fine-tuning (Decagon)](/agents/agent-design-patterns/decagon-engineering-fast-agents-through-fine-tuning/index.md) by [Decagon](https://decagon.ai/) Decagon engineering post on using several fine-tuned smaller models to cut latency in customer-service agents. Advanced learning_resource blog US en - ### [Direct Preference Optimization](/agents/agent-design-patterns/direct-preference-optimization/index.md) by [Rafael Rafailov et al. (Stanford University)](https://www.stanford.edu/) arXiv paper (2023) introducing Direct Preference Optimization (DPO), preference training without a separate reward model. Advanced learning_resource paper US en - ### [LoRA](/agents/agent-design-patterns/lora/index.md) by [Edward J. Hu et al. (Microsoft)](https://www.microsoft.com/) arXiv paper (2021) "LoRA: Low-Rank Adaptation of Large Language Models", introducing LoRA, low-rank adaptation for fine-tuning large models. Advanced learning_resource paper US en - ### [Training language models to follow instructions with human feedback](/agents/agent-design-patterns/training-language-models-to-follow-instructions-with-human-feedback/index.md) by [Long Ouyang et al. (OpenAI)](https://openai.com/) arXiv paper (2022) "Training language models to follow instructions with human feedback", describing InstructGPT and the RLHF post-training pipeline. Advanced learning_resource paper US en - ### [TRL documentation](/agents/agent-design-patterns/trl-documentation/index.md) by [Hugging Face](https://huggingface.co/) Hugging Face TRL documentation: trainers for SFT, DPO, GRPO and other post-training methods. Advanced learning_resource docs International en - ### [Tülu 3](/agents/agent-design-patterns/t-lu-3/index.md) by [Nathan Lambert et al. (Ai2)](https://allenai.org/) arXiv paper (2024) describing Tülu 3, a fully open post-training recipe that introduced RLVR. Expert learning_resource paper US en [Plain-text Markdown copy](/agents-ai-engineering/training-fine-tuning/index.md)