Tag: #kto

Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 2 posts

LLM Fine-tuning Frameworks 2026 — A Deep Dive into Axolotl, Unsloth, LLaMA-Factory, TRL, PEFT, and TorchTune
A complete map of the 2026 LLM fine-tuning ecosystem. Open-source frameworks like Axolotl, Unsloth, LLaMA-Factory, TRL, PEFT, and TorchTune. LLM Foundry (MosaicML, acquired by Databricks). Cloud fine-tuning APIs from Mod
2026-05-16 · 28 min read #llm #finetuning #axolotl #unsloth #llama-factory
From DPO to KTO: Latest Human Feedback Alignment Techniques Paper Review and Practical Implementation
Paper review and TRL-based practical implementation guide covering the latest human feedback alignment techniques such as DPO, IPO, and KTO that overcome RLHF limitations. Algorithm comparison, hyperparameter tuning, and
2026-03-05 · 22 min read #ai-papers #dpo #kto #alignment #2026-03

LLM Fine-tuning Frameworks 2026 — A Deep Dive into Axolotl, Unsloth, LLaMA-Factory, TRL, PEFT, and TorchTune