sonthenguyen/NeuralHermes-2.5-Mistral-7B
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jan 18, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

NeuralHermes-2.5-Mistral-7B is a 7 billion parameter instruction-tuned language model developed by sonthenguyen, based on the Mistral architecture. It is fine-tuned using DPO on a synthetic dataset derived from GPT-4, making it suitable for chat and instruction-following tasks. This model specializes in generating high-quality responses by distilling knowledge from larger, more capable models.

Loading preview...