# Unsloth Accelerated Training

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.

A fine-tuned version of the Qwen2-VL-7B model, trained using Unsloth and Huggingface TRL library, achieving 2x inference speed improvement.

Cogito-Maximus is an advanced text generation model optimized based on the Qwen2.5-72B instruction fine-tuning model. It uses Unsloth for accelerated training and the TRL fine-tuning framework, and is suitable for various text generation scenarios.

A multimodal model fine-tuned based on Qwen2.5-VL-7B-Instruct, utilizing the Unsloth acceleration framework and TRL library for training, achieving a 2x speed improvement

A fine-tuned Turkish text generation model based on unsloth/Llama-3.2-1B-bnb-4bit, specializing in summarization tasks.

TwinLlama-3.1-8B is a model trained based on Meta-Llama-3.1-8B, designed to mimic the writing style and knowledge of the author and their co-authors.