Tashkeel-350M-v2 is a model specifically designed for phonetic notation of Arabic text, with 350 million parameters. This model is based on the ibm-granite/granite-4.0-h-350m model and is fine-tuned on the Misraj/Sadeed_Tashkeela dataset. It can automatically add correct phonetic symbols to Arabic text.

Natural Language ProcessingTransformersArabic

A lightweight Russian-English bilingual language model fine-tuned based on SmolLM2-135M, with enhanced Russian processing capabilities but notable limitations

Natural Language ProcessingSafetensorsMultiple Languages

BK-SDM-v2 is an efficient text-to-image synthesis model obtained by compressing SD-v2.1-base. It uses the block removal knowledge distillation technique to achieve effective distillation and retraining with limited data, providing a more lightweight solution for image generation.

Computer VisionDiffusers

BK-SDM is a stable diffusion model with architecture compression. By removing the residual and attention blocks in the U-Net and conducting knowledge distillation training on limited data, it achieves efficient text-to-image synthesis. This model significantly reduces the number of parameters while maintaining good generation quality.

MultimodalDiffusers

BK-SDM is a stable diffusion model compressed through architecture compression, used for efficient and general text-to-image synthesis. It achieves lightweight design by removing residual and attention blocks in the U-Net.

Computer VisionDiffusers

A model that generates music from images, outputting the music in ABC notation format.

MultimodalTransformers

A text-conditioned symbolic music generation model based on BART-base architecture that can generate ABC notation scores from natural language descriptions

MultimodalTransformersEnglish