Results for “sigma”

Train, fine-tune, and deploy LLMs using LitGPT's clean implementations of 20+ architectures like Llama, Gemma, and Phi.

Train and run Mamba state-space models with O(n) complexity, achieving faster inference and longer context than Transformers.

Trains LLMs with SimPO, a reference-free preference optimization method that outperforms DPO, using configurable hyperparameters and workflows for various models and tasks.

Train language models with SimPO, a reference-free preference optimization method that outperforms DPO without needing a reference model.

Fine-tune Gemma models locally using QLoRA, Unsloth, or TRL for SFT, DPO, and reward modeling, with dataset preparation and conversion to GGUF or LiteRT-LM.