princeton-nlp/Mistral-7B-Base-SFT-RRHF
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Jul 6, 2024Architecture:Transformer Cold

princeton-nlp/Mistral-7B-Base-SFT-RRHF is a 7 billion parameter language model developed by princeton-nlp, fine-tuned using the RRHF (Rank Responses to align with Human Feedback) method. This model is based on the Mistral-7B-Base architecture and is specifically designed for improved alignment with human preferences. It is suitable for tasks requiring nuanced response generation and preference optimization, building upon a 4096 token context length.

Loading preview...