# DPO Fine-Tuning Optimization

A fine-tuned large language model based on mlabonne/gemma-3-27b-it-abliterated, trained using the Unsloth acceleration framework and Huggingface's TRL library, achieving a 2x efficiency improvement.

Chocolatine-Fusion-14B is a merged model that combines the strengths of the Chocolatine-2 series, enhancing reasoning capabilities and multi-turn dialogue performance through optimized fusion.

NeuralBeagle14-7B is a 7B-parameter large language model fine-tuned using the DPO method based on the Beagle14-7B model, excelling in the 7B parameter category.