This model is a violence detection model based on the VideoMAE architecture. After pre-training on the Kinetics dataset, it was fine-tuned for 92 rounds for the violence detection task. The model uses the Vision Transformer architecture and is specifically designed for video content analysis, capable of identifying violent behaviors in videos.

Computer VisionTransformers

Qwen3-VL-TimeTravel is a version fine-tuned on the MBZUAI/TimeTravel dataset using the Unsloth library based on the Qwen3-VL-8B-Instruct model. This model is specifically designed to generate descriptions of historical cultural relic images and has professional capabilities in historical and cultural relic analysis.

MultimodalTransformersEnglish

Three document layout analysis models (nano, small, medium) based on the YOLOv11 architecture, fine-tuned on the DocLayNet dataset, can accurately detect 11 types of layout elements such as text, tables, and charts in documents, suitable for document understanding and information extraction tasks.

Lightning-4b is a language model designed and trained specifically for local device data analysis tasks. It can run smoothly on a laptop with 16GB of memory without sending data to large language model providers, ensuring data privacy and security.

Natural Language ProcessingTransformersEnglish

Neeto-1.0-8b-GGUF is a quantized version based on S4nfs/Neeto-1.0-8b, designed specifically for medical exam preparation and medical applications. This model is created using llama.cpp and has been rigorously trained on medical datasets, focusing on medical-related tasks such as medical exam preparation, case analysis, and medical reasoning.

Natural Language ProcessingTransformersEnglish

Schematron-3B is a long context extraction model launched by Inference.net, focusing on converting noisy HTML into clean, typed JSON that conforms to custom schemas. This model is specifically trained for web scraping, data ingestion, and converting arbitrary pages into structured records, providing an efficient solution for data processing and analysis.

Natural Language ProcessingTransformers

A Bengali sentiment analysis model based on the Transformer architecture, fine-tuned on the SentiGOLD dataset, supporting 5-category sentiment analysis, and capable of effectively handling formal and informal texts, suitable for scenarios such as social media and reviews.

Natural Language ProcessingTransformersOther

Datarus-R1-14B-Preview is an open-source language model based on 14 billion parameters, fine-tuned on the basis of Qwen2.5-14B-Instruct. This model is specifically designed as a virtual data analyst and a solver for graduate-level problems, capable of learning from complete analysis trajectories, including reasoning steps, code execution, error tracking, and final conclusions.

Natural Language ProcessingTransformersEnglish

A model specifically designed for chemical entity recognition, capable of accurately identifying and extracting relevant entities from biomedical texts, and has significant value in fields such as drug discovery and medical data analysis.

Natural Language ProcessingTransformersEnglish

LoggenixMoE133M is a lightweight Mixture of Experts (MoE) causal language model with a total of 133M parameters and 80M active parameters. This model is trained from scratch on a custom dataset containing root cause analysis, code generation, and inference tasks. It supports special tokens for agent capabilities and is suitable for deployment on edge devices and the construction of professional AI agents.

Natural Language ProcessingTransformers

A model for three-class sentiment analysis of Russian financial comments, with data sourced from the Tinkoff Pulse platform

Natural Language ProcessingSafetensorsOther

A Chinese text classification model fine-tuned on the Weibo 100k sentiment analysis dataset based on bert-base-chinese

Natural Language ProcessingTransformersChinese

This is a pre-trained DistilBERT model fine-tuned on the SST-2 dataset for sentiment analysis. It can predict whether a given text expresses positive or negative sentiment.

Natural Language ProcessingPytorchEnglish

A model pre-trained on the Pythia-1b architecture and fine-tuned on single-cell RNA sequencing data via the Cell2Sentence framework, suitable for various single-cell and multicellular analysis tasks.

Scientific ComputingTransformersEnglish

A financial domain sentiment analysis model fine-tuned based on econo-sentence-v2, achieving 96.2% accuracy on the Financial Phrase Bank dataset

Natural Language ProcessingTransformersEnglish

A reinforced reasoning model based on the Llama-3.2-3B-Instruct architecture, excelling in mathematical analysis, logical reasoning, and structured data comprehension.

Natural Language ProcessingTransformersMultiple Languages

DDoSBert is a network security detection model based on the Transformer architecture, specifically designed to identify and defend against Distributed Denial of Service (DDoS) attacks. This model can effectively detect complex DDoS attack patterns by performing text classification analysis on network traffic data.

Natural Language ProcessingTransformersMultiple Languages

OASIS is a state-of-the-art code embedding model developed by Kwaipilot, integrating repository-level program analysis, the OASIS-instruct data synthesis algorithm, and a specialized fusion loss function, setting new benchmarks in code search efficiency and accuracy.

Natural Language ProcessingSafetensors

This project conducts word frequency statistical analysis based on the SlimPajama-627B dataset, providing high-frequency word data support for natural language processing tasks, and can assist in model optimization and improve processing efficiency and accuracy.

Natural Language ProcessingTransformers

A Transformer-based tabular classification model for financial data analysis

Natural Language ProcessingTransformers