mlabonne/AlphaMonarch-7B

mlabonne/AlphaMonarch-7B is a 7 billion parameter DPO fine-tuned language model developed by mlabonne, based on a merge of several models including NeuralMonarch-7B. It features an 8k context window and is optimized to retain strong reasoning abilities while significantly improving conversational capabilities. This model excels in instruction following, reasoning, and conversational tasks, making it suitable for general-purpose chat, roleplay, and storytelling applications.