teknium/OpenHermes-7B
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Sep 14, 2023License:mitArchitecture:Transformer0.0K Open Weights Cold

OpenHermes-7B by Teknium is a 7 billion parameter instruction-tuned language model, fine-tuned on 242,000 entries of primarily GPT-4 generated data. It uniquely utilizes sample packing during training to enhance efficiency, making it suitable for general instruction-following tasks. The model's training dataset is fully open-source, distinguishing it from other models in its class.

Loading preview...