mychen76/mistral-7b-merged-dare_6x7
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:4kPublished:Mar 11, 2024License:apache-2.0Architecture:Transformer Open Weights Cold

The mychen76/mistral-7b-merged-dare_6x7 is a 7 billion parameter language model based on the Mistral-7B-v0.1 architecture, created by mychen76 through a DARE TIES merge of several fine-tuned models. This merge technique combines the strengths of models like SamirGPT-v1, Slerp-CM-mist-dpo, EmbeddedLLM/Mistral-7B-Merge-14-v0.2, and Weyaxi/Einstein-v4-7B. It demonstrates strong performance across various benchmarks, including an average score of 73.46 on the Open LLM Leaderboard, making it suitable for general-purpose text generation and reasoning tasks.

Loading preview...