dphn/dolphin-2.2.1-mistral-7b
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Oct 30, 2023License:apache-2.0Architecture:Transformer0.2K Open Weights Cold

dphn/dolphin-2.2.1-mistral-7b is a 7 billion parameter language model developed by Eric Hartford, based on MistralAI's Mistral-7B-v0.1 architecture. This model is fine-tuned for enhanced conversation, empathy, and multi-turn dialogue, incorporating elements from Microsoft's Orca and Samantha datasets. It is designed to be highly compliant and uncensored, making it suitable for diverse applications where custom alignment layers can be implemented.

Loading preview...