Priyal | DS & ML on Instagram: "1. Hugging Face Transformers + PEFT The most popular ecosystem for fine-tuning LLMs. Supports LoRA, QLoRA, Adapters, Prefix Tuning, and integrates smoothly with the HF Trainer. 2. Axolotl A production-grade framework for SFT, DPO, ORPO, RLHF, LoRA/QLoRA, and multi-GPU setups. Simple YAML configs and massive flexibility. 3. Unsloth Ultra-fast, memory-efficient fine-tuning. Lets you train 7B–13B models on small consumer GPUs. Great for speed and low VRAM. 4. LLaMA F

Hugging Face Hub documentation

Managing datasets and models in your Hugging Face organization