neph1/bellman-7b-mistral-instruct-v0.2
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Dec 16, 2023License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

neph1/bellman-7b-mistral-instruct-v0.2 is a 7 billion parameter Mistral-based instruction-tuned language model developed by neph1. It has been Qlora trained for approximately two epochs on 14,000 rows of Q&A, Python examples, and general instruction-type questions, with a 4096 token context length. This model is specifically optimized to improve knowledge in Swedish topics and enhance the quality of the Swedish language, making it particularly suitable for Swedish-centric applications.

Loading preview...