uukuguy/neural-chat-7b-v3-1-dare-0.85
TEXT GENERATIONConcurrency Cost:1Model Size:7BQuant:FP8Ctx Length:8kPublished:Nov 20, 2023License:llama2Architecture:Transformer Open Weights Cold

The uukuguy/neural-chat-7b-v3-1-dare-0.85 model is a 7 billion parameter language model based on the Intel/neural-chat-7b-v3-1 architecture, fine-tuned using the DARE (Drop and REscale) method with a 0.85 weight mask rate. This experimental model explores the impact of parameter pruning on SFT LMs, demonstrating that a significant portion of delta parameters can be set to zero without compromising capabilities. It is optimized for general language understanding and generation tasks, maintaining performance while investigating model sparsity.

Loading preview...