Training Fine Tuning
16 resources · page 1 of 1
LLaMA-Factory
Creator not supplied; see original source.
LLaMA-Factory GitHub repo: unified framework for fine-tuning over 100 LLMs and VLMs.
hiyouga/LlamaFactory
Creator not supplied; see original source.
LlamaFactory GitHub repo (ACL 2024): unified fine-tuning toolkit for over 100 language and vision-language models.
open-instruct (Ai2)
Creator not supplied; see original source.
Ai2 open-instruct GitHub repo: post-training codebase for instruction tuning and RL of language models.
Unsloth notebooks
Creator not supplied; see original source.
Unsloth notebooks GitHub repo: Colab notebooks for fine-tuning and RL of text, vision and audio models.
Unsloth
Creator not supplied; see original source.
Unsloth GitHub repo: memory-efficient fine-tuning and local running of LLMs.
Axolotl docs
Creator not supplied; see original source.
Axolotl documentation: open-source, config-driven tool for fine-tuning and post-training LLMs.
HF smol course
Creator not supplied; see original source.
Hugging Face smol course GitHub repo: practical course on fine-tuning and aligning small language models.
PyTorch tutorials
Creator not supplied; see original source.
Official PyTorch tutorials covering basics, training, deployment and performance, with runnable code.
RLHF Book (Nathan Lambert)
Creator not supplied; see original source.
Nathan Lambert's free online RLHF book covering preference tuning, reward models, RLVR and post-training of language models.
TensorFlow tutorials
Creator not supplied; see original source.
Official TensorFlow tutorials on training and deploying machine-learning models.
Engineering fast, performant AI agents through fine-tuning (Decagon)
Creator not supplied; see original source.
Decagon engineering post on using several fine-tuned smaller models to cut latency in customer-service agents.
Direct Preference Optimization
Creator not supplied; see original source.
arXiv paper (2023) introducing Direct Preference Optimization (DPO), preference training without a separate reward model.
LoRA
Creator not supplied; see original source.
arXiv paper (2021) "LoRA: Low-Rank Adaptation of Large Language Models", introducing LoRA, low-rank adaptation for fine-tuning large models.
Training language models to follow instructions with human feedback
Creator not supplied; see original source.
arXiv paper (2022) "Training language models to follow instructions with human feedback", describing InstructGPT and the RLHF post-training pipeline.
TRL documentation
Creator not supplied; see original source.
Hugging Face TRL documentation: trainers for SFT, DPO, GRPO and other post-training methods.
Tülu 3
Creator not supplied; see original source.
arXiv paper (2024) describing Tülu 3, a fully open post-training recipe that introduced RLVR.