# safetensors format

A 4-bit quantized version based on deepseek-ai/Janus-Pro-7B, optimized for Apple chip devices and suitable for chat tasks.

4-bit quantized version based on deepseek-ai/Janus-Pro-1B, optimized for Apple chips using the MLX framework

Flex.1-alpha-Fp8 is the safetensors format version of the Flex.1-alpha model with float8_e4m3fn weights, suitable for text-to-image generation tasks.

TunBERT is an Arabic-based pre-trained language model developed by InstaDeepAI. This version is a converted model from the nemo format to the safetensors format.

ViT-tiny model converted from timm codebase, suitable for image classification tasks