# Knowledge Reasoning

GLM-4-32B-0414 is a large-scale language model developed by the THUDM team, based on the GLM architecture, suitable for various text generation tasks.

Kanana is a bilingual (Korean/English) language model series developed by Kakao. This 2.1B parameter version outperforms similar models in Korean while maintaining efficient computational costs.

A 7B-parameter large language model based on the Mistral architecture, efficiently trained using Unsloth and TRL libraries, demonstrating excellent performance in multiple benchmarks.

Misted-7B is a 7B-parameter large language model based on the fusion of OpenHermes-2-Mistral-7B and Mistral-7B-SlimOrca, primarily designed for text generation tasks.

orca_mini_13b is a text generation model trained on multiple high-quality datasets, focusing on instruction following and dialogue tasks.

A Q&A model fine-tuned based on hfl/chinese-pert-large, suitable for Chinese Q&A tasks