# High Reasoning Accuracy

This is an 8B-parameter model based on the Llama-3 architecture, merged using the mergekit tool, with strong text generation capabilities.

Blurdus-7b-v0.1 is a hybrid model obtained by merging three 7B-parameter models using LazyMergekit, demonstrating excellent performance across multiple benchmarks.

Stealth-v1.3 is an open-source large language model developed by Jan, supporting offline operation on local devices to ensure user privacy.

supermario-v2 is a merged model based on Mistral-7B-v0.1, combining three different models using the DARE_TIES method, with strong text generation capabilities.

This model is created by merging OpenHermes-2.5-Mistral-7B and Intel's neural-chat-7b-v3-2 using the ties merging method, focusing on text generation tasks.