# Edge device adaptation

Kanana 1.5 is the new version of the Kanana model series, with significant improvements in coding, mathematics, and function calling capabilities, capable of processing inputs up to 32K tokens, and up to 128K tokens when using YaRN.

OlympicCoder-7B is a code generation model optimized based on Qwen2.5-Coder-7B-Instruct. It uses the IQ-DynamicGate ultra-low bit quantization technology and is designed for memory-constrained environments.

Ultra-low-bit quantization (1-2 bit) large language model using IQ-DynamicGate technology, supporting multilingual text generation tasks

RWKV-7 model based on flash-linear attention format, supporting multilingual text generation tasks.

RT-DETRv2 is an improved real-time object detection Transformer model that enhances performance through strategies such as selective multi-scale feature extraction and dynamic data augmentation.

RT-DETRv2 is an optimized real-time object detection model based on the RT-DETR architecture. It improves detection accuracy while maintaining real-time performance through selective multi-scale feature extraction and enhanced training strategies.

A vision transformer model specifically designed for smart agriculture systems to identify crop diseases, supporting detection of various diseases in crops such as corn, potatoes, rice, and wheat.