This project is the result of 4-bit (UINT4, SVD rank of 32) quantization of Tencent's Hunyuan Image 3.0 model. It uses the SDNQ quantization method and is specifically designed for text-to-image generation tasks.

MultimodalTransformers

The Linglong Linear Preview is a hybrid linear sparse large language model open-sourced by InclusionAI, with a total of 17.1B parameters and 3.0B activated parameters. This model implements long-text reasoning based on a hybrid linear attention mechanism, achieving near-linear computational complexity and near-constant space complexity during inference.

Natural Language ProcessingSafetensorsMultiple Languages

Quasar-3.0-7B is the distilled version of the upcoming 400B Quasar 3.0 model, showcasing the early strength and potential of the Quasar architecture.

Natural Language ProcessingTransformers

Granite Guardian 3.0 8B is a fine-tuned Granite 3.0 8B instruction model developed by IBM Research, specifically designed to detect risky content in prompts and responses.

Natural Language ProcessingTransformersEnglish

Animagine XL 3.0 Base is the foundational version of an advanced anime text-to-image model, focusing on establishing core functionalities and refining key aspects.

Computer VisionDiffusersEnglish

Animagine XL 3.0 is the latest open-source anime text-to-image model developed based on Stable Diffusion XL, focusing on high-quality anime image generation with improved hand anatomy and conceptual understanding.

Computer VisionDiffusersEnglish

Kandinsky 3.0 is an open-source text-to-image diffusion model developed based on the Kandinsky2-x model series, incorporating more Russian culture-related data to enhance text understanding and visual generation quality.

Computer VisionDiffusers

Speaker diarization pipeline trained on pyannote.audio 3.0.0, supporting automatic voice activity detection, speaker change detection and overlapping speech detection

Audio ProcessingPyannote.audio

BEREL 3.0 is an embedding model based on the BERT architecture, specifically designed for rabbinic coded language, providing support for relevant research and applications.

Natural Language ProcessingTransformersOther

ERNIE 3.0 is a large-scale knowledge-enhanced pre-trained model for language understanding and generation, developed by Baidu.

Natural Language ProcessingTransformersChinese

ERNIE 3.0 is a large-scale knowledge-enhanced pre-training model for language understanding and generation, with efficient language processing capabilities.

Natural Language ProcessingTransformersChinese

ERNIE 3.0 is a large-scale knowledge-enhanced pre-training model launched by Baidu for language understanding and generation, with micro-zh being its small Chinese version.

Natural Language ProcessingTransformersChinese

ERNIE 3.0 is a large-scale knowledge-enhanced pre-trained model for Chinese language understanding and generation, with the mini version being its lightweight implementation.

Natural Language ProcessingTransformersChinese

ERNIE 3.0 is a large-scale knowledge-enhanced pre-trained model for language understanding and generation, developed by Baidu.

Natural Language ProcessingTransformersChinese

ERNIE 3.0 is a large-scale knowledge-enhanced pre-trained model for Chinese language understanding and generation, developed by Baidu Research.

Natural Language ProcessingTransformersChinese

This model is a fine-tuned speech recognition model based on facebook/wav2vec2-base on the Common Voice 3.0 English dataset, achieving a word error rate of 0.247 on the test set.

Audio ProcessingTransformers

This model adopts the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 License, suitable for application scenarios requiring specific copyright conditions.

Natural Language ProcessingTransformers

Swedish NER model based on KB-BERT architecture, fine-tuned on SUCX 3.0 NER corpus while preserving original case features

Natural Language ProcessingTransformersOther