This is a deep learning model based on the EfficientNet-B0 architecture, specifically designed for classifying the art styles of anime and visual novel images. The model can accurately identify 6 different anime art styles, including dark, flat, modern, cute, painting, and retro styles.

Computer VisionSafetensorsEnglish

PokeeResearch-7B is a 7-billion-parameter deep research intelligent agent developed by Pokee AI. It combines reinforcement learning based on AI feedback (RLAIF) with an inference framework and can execute complex multi-step research workflows, including self-correction, verification, and comprehensive analysis.

Natural Language ProcessingTransformersEnglish

BEVANet is a deep learning model designed for real-time semantic segmentation, which performs excellently on datasets such as Cityscapes. It achieves an outstanding performance of 81.0% mIoU and 32.8 FPS on the RTX3090, balancing the requirements of accuracy and speed.

Computer VisionSafetensors

Tongyi Deep Research 30B is a large language model with 30 billion parameters, designed specifically for long-cycle, deep information search tasks. This model performs excellently in multiple intelligent search benchmark tests, uses innovative quantization methods to improve performance, and supports intelligent pre-training, supervised fine-tuning, and reinforcement learning.

Natural Language ProcessingTransformersEnglish

Persian OCR is a deep learning model for optical character recognition specifically designed for Persian text. It uses the CNN + Transformer architecture and is trained on a dataset containing 600,000 synthetic Persian text images, achieving a sequence accuracy of 96%.

Computer VisionPytorchOther

DeepSeek-GRM-16B is a generative reward model based on Self-Principled Critique Tuning (SPCT), which can generate a transparent 'Principle → Critique → Score' evaluation process for query-responses and can be used in tasks such as reinforcement learning, evaluation, and data collection of large language models.

Natural Language ProcessingTransformersMultiple Languages

DeepSeek-R1 is an inference model trained through large-scale reinforcement learning. It performs excellently in mathematics, code, and reasoning tasks, and can demonstrate powerful reasoning abilities without supervised fine-tuning, including self-verification, reflection, and generating long thought chains, etc.

Natural Language ProcessingTransformersEnglish

AASIST3 is an enhanced version based on the AASIST architecture, specifically designed for voice deep forgery detection. This model integrates Kolmogorov - Arnold Networks (KAN), combines self - supervised learning features and additional regularization techniques, which can effectively improve the performance and robustness of voice deep forgery detection.

Audio ProcessingSafetensorsEnglish

A deep learning model based on the MobileNetV2 architecture, specifically designed to identify and classify 120 different dog breeds. Fine-tuned through transfer learning techniques, it can accurately identify various dog breeds and provide confidence scores.

Computer VisionTransformers

BiRefNet is a deep learning model for binary image segmentation, specifically designed for background removal tasks. This model has been converted to the GGUF format and can perform lightweight inference on consumer-grade hardware through vision.cpp, enabling efficient image segmentation processing.

Computer VisionGguf

AceReason-Nemotron-7B is a mathematical and code reasoning model trained through reinforcement learning. It is developed based on DeepSeek-R1-Distilled-Qwen-7B and performs excellently in multiple reasoning benchmark tests.

Natural Language ProcessingTransformersMultiple Languages

DeepSWE-Preview is a fully open-source and advanced coding intelligent agent, trained through reinforcement learning, and performs excellently in software engineering tasks.

Natural Language ProcessingTransformersEnglish

This is a Transformers model published on the Hugging Face Hub. Specific information needs to be obtained from the model page. This model is based on an advanced deep learning architecture and is suitable for various natural language processing tasks.

Natural Language ProcessingTransformers

The Deep Ignorance Model Suite is a collection of 18 large language models with 6.9 billion parameters each. It aims to study methods of preventing models from learning unsafe technical capabilities (such as CBRN-related capabilities) by filtering pretrained data. This suite demonstrates that filtering data can effectively avoid the learning of bad knowledge while maintaining general performance and having anti-tampering capabilities.

Natural Language ProcessingTransformersEnglish

AceReason-Nemotron-7B is a mathematical and code reasoning model trained based on reinforcement learning. It starts training from DeepSeek-R1-Distilled-Qwen-7B and performs excellently in multiple benchmark tests.

Natural Language ProcessingTransformers

ConTextTab is a deep learning model that combines semantic understanding and context learning, specifically designed to handle tabular data. It processes different data modalities through specialized embedding methods and is trained on large-scale real-world tabular data, performing excellently in multiple benchmark tests, especially setting a new standard in the semantically rich CARTE benchmark test.

SAP RPT 1 OSS is a deep learning model that combines semantic understanding and context learning, specifically designed for tabular data prediction tasks. The model uses specialized embeddings for different data modalities and is trained on large-scale real-world tabular data, performing excellently in a wide range of benchmark tests.

SLANeXt_wired is a deep learning model for table structure recognition, which can convert non - editable table images into editable table formats (such as HTML).

VoxPolska Auralis is an advanced Polish text-to-speech (TTS) model that uses cutting-edge deep learning technology to accurately capture the nuances and intonations of the Polish language, converting written text into natural, fluent, and expressive speech.

Audio ProcessingTransformersOther

DeepSeek-R1-Llama-8B-F32-GGUF is the quantized version of DeepSeek-R1-Distill-Llama-8B, trained directly with reinforcement learning, featuring capabilities such as self-verification, reflection, and generating extended chain-of-thought reasoning.

Natural Language ProcessingTransformersEnglish