# Lightweight and Efficient

A Mixture of Experts model designed to serve as the soul of AI virtual anchors, combining code generation, instruction following, and multi-turn dialogue capabilities

GGUF quantized version of DeepSeek-V3-0324, suitable for local text generation tasks.

PEGASUS Medium is a fine-tuned version of the PEGASUS model, specifically optimized for abstractive text summarization tasks on Indonesian news articles.

Depth Anything V2 is currently the most powerful monocular depth estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unannotated images.

Chinese ELECTRA is a pre-trained model developed by the Harbin Institute of Technology-iFLYTEK Joint Lab (HFL) based on the ELECTRA model released by Google and Stanford University. It features a small parameter size and high performance.

A lightweight BERT model specialized for the legal domain, with only 33% the size of BERT-BASE, significantly improving efficiency while maintaining performance

Chinese ELECTRA is a pre-trained model developed by the Harbin Institute of Technology-iFLYTEK Joint Lab based on Google's ELECTRA architecture, with only 1/10 the parameters of BERT but comparable performance.