ERNIE-4.5-21B-A3B is a large language model developed by Baidu. It has been optimized with 4-bit quantization by the LM Studio team using the MLX framework, specifically optimized for Apple chips. This model has 21 billion parameters, supports Chinese and English, and uses the Apache-2.0 open-source license.

Natural Language ProcessingTransformersMultiple Languages

PP-OCRv4_server_rec is a text line recognition model in the PP-OCRv4_rec series developed by the PaddleOCR team. It supports text line recognition in general Chinese and English scenarios, mainly focusing on Chinese.

PP-OCRv3_mobile_rec is a lightweight text line recognition model developed by the PaddleOCR team. It uses the SVTR algorithm and supports Chinese and English recognition, especially focusing on Chinese scenarios.

PP-FormulaNet_plus-M is an enhanced formula recognition model developed by the PaddleOCR team. It supports Chinese formula recognition and improves the processing ability for complex formulas.

PP-OCRv4_mobile_rec is a lightweight text line recognition model developed by the PaddleOCR team, focusing on efficient text recognition in Chinese and English scenarios.

PP-FormulaNet_plus-L is an enhanced formula recognition model developed by the PaddleOCR team. It supports Chinese formula recognition, and the maximum number of tokens is increased to 2560, making it suitable for complex formula scenarios.

PP-Chart2Table is a multimodal model developed by the PaddlePaddle team, focusing on Chinese and English chart parsing and capable of efficiently converting charts into data tables.

MultimodalPaddleMultiple Languages

PP-OCRv5_mobile_rec is the latest generation of text line recognition model developed by the PaddleOCR team. It supports the recognition of four languages: Simplified Chinese, Traditional Chinese, English, and Japanese, and is suitable for various complex text scenarios.

Conan-embedding-v1 is a Chinese text embedding model developed by the Tencent BAC team, focusing on semantic representation and similarity calculation for Chinese text.

Natural Language ProcessingGgufChinese

Conan-embedding-v1 is a Chinese text embedding model developed by the Tencent BAC team, implemented based on the sentence-transformers library, suitable for various Chinese natural language processing tasks.

Natural Language ProcessingGguf

Kolors is a large-scale text-to-image latent diffusion model independently developed by Kwai's Kolors team, excelling in visual quality of generated images, complex semantic restoration, and Chinese/English font rendering.

MultimodalDiffusersMultiple Languages

Alibaba PAI team's open-source Chinese latent diffusion model supporting Chinese text-to-image generation

Computer VisionDiffusers

A tiny Chinese BERT model developed by Academia Sinica's CKIP team, suitable for Traditional Chinese natural language processing tasks

Natural Language ProcessingTransformersChinese

A Traditional Chinese Transformer model developed by the Academia Sinica CKIP team, including architectures such as ALBERT, BERT, GPT2, and natural language processing tools

Natural Language ProcessingTransformersChinese

A Traditional Chinese natural language processing model developed by the Academia Sinica CKIP team, based on the ALBERT architecture, supporting tasks such as word segmentation and part-of-speech tagging.

Natural Language ProcessingTransformersChinese

A lightweight ALBERT model developed by Academia Sinica's CKIP team, supporting Traditional Chinese NLP tasks

Natural Language ProcessingTransformersChinese

Pangu α is a 2.6 billion parameter Chinese pre-trained language model developed by Peng Cheng Laboratory and a joint technical team, trained on 2048 Ascend processors with powerful text generation capabilities.

Natural Language ProcessingTransformers

This is a Traditional Chinese ALBERT model developed by Academia Sinica's CKIP team, suitable for various natural language processing tasks.

Natural Language ProcessingTransformersChinese

Traditional Chinese natural language processing model developed by Academia Sinica's CKIP team, supporting tasks like word segmentation and part-of-speech tagging

Natural Language ProcessingTransformersChinese

A Traditional Chinese GPT2 model developed by Academia Sinica's CKIP team, suitable for Chinese text generation tasks.

Natural Language ProcessingJaxChinese