QuixiAI/samantha-mistral-instruct-7b
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Sep 30, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

QuixiAI/samantha-mistral-instruct-7b is a 7 billion parameter instruction-tuned language model based on Mistral-7B-Instruct-v0.1. This model is fine-tuned with the Samantha-1.1 dataset, specializing in philosophical, psychological, and personal relationship conversations, aiming to be a companion assistant. It utilizes the ChatML prompt format and is designed for general assistant tasks with an empathetic and caring persona.

Loading preview...