Apriel-1.5-15b-Thinker is a multimodal reasoning model developed by the ServiceNow SLAM Lab, with a parameter scale of 15 billion. It has powerful text and image understanding and reasoning capabilities, adopting a chained reasoning mode of 'think-answer', aiming to achieve performance comparable to large models with a smaller model scale.

MultimodalTransformers

This is a quantized version of the Jamba-Mini-1.7 model from AI21 Labs, optimized using the imatrix technology of llama.cpp. It provides multiple quantization options for different hardware configurations and supports efficient reasoning.

Natural Language ProcessingGguf

A.X 4.0 Light is a lightweight large language model developed by SKT AI Model Lab, built on Qwen2.5 and optimized for Korean understanding and enterprise deployment.

Natural Language ProcessingTransformersMultiple Languages

Second-generation reasoning model developed by SmilyAI Labs, featuring a sarcastic antagonist-style AI persona with structured reasoning output

Natural Language ProcessingTransformersEnglish

Cohere Labs Command A is a research version of a 111-billion parameter model with open weights, optimized for the demanding enterprise needs that require fast, secure, and high-quality AI.

Natural Language ProcessingTransformersMultiple Languages

InternLM3-8B-Instruct is an 8-billion-parameter instruction model developed by Shanghai AI Laboratory, designed for general-purpose use and advanced reasoning, featuring high efficiency and low cost.

Natural Language ProcessingSafetensors

UNI 2 is a pathological AI visual backbone network developed by Mahmood Lab at Harvard University/Brigham and Women's Hospital. It is pre-trained on histopathology images based on self-supervised learning and supports multi-task evaluation.

Computer VisionTimmEnglish

Sailor2 is a community-driven project developed by Sea AI Lab, a multilingual large language model designed specifically for the Southeast Asian region. It offers three parameter scales of 1 billion, 8 billion, and 20 billion, supports 15 Southeast Asian languages, and is released under the Apache 2.0 license, enabling users in the region to more conveniently use advanced language technologies.

Natural Language ProcessingTransformersMultiple Languages

This is a model checkpoint provided for the Any-to-Any subnet collaboration between OMEGA Labs and Bittensor, aiming to achieve general artificial intelligence tasks.

CmdCaliper is the first embedding model series specifically designed for command line embedding, developed by CyCraft AI Lab.

Natural Language ProcessingSafetensors

CmdCaliper-base is a model specifically developed by the CyCraft AI Laboratory for command-line embedding. It has approximately 110 million parameters and outperforms the state-of-the-art sentence embedding models with three times more parameters in various command-line specific tasks. This model is an embedding model specifically designed for command-line semantic understanding.

Natural Language ProcessingSentence-transformers

FlowMirror is an end-to-end speech model developed by Zhejiang Jingzhunxue AI Lab, supporting tasks such as voice dialogue, ASR, and TTS, with a focus on educational applications

MultimodalTransformers

A Korean-optimized large language model developed by Saltlux AI Lab based on Meta Llama-3-8B, featuring an extended Korean tokenizer and pre-trained on 100GB of curated Korean data

Natural Language ProcessingTransformersMultiple Languages

InternLM-Math is a state-of-the-art bilingual open-source large language model for mathematical reasoning developed by the Shanghai AI Laboratory. It performs excellently in mathematical reasoning tasks, supports the solution and proof of various mathematical problems, can also be used as a reward model, and has practical functions such as data enhancement and code explanation.

Natural Language ProcessingGgufMultiple Languages

InternLM-20B is a 20-billion-parameter pretrained model jointly released by Shanghai AI Laboratory, SenseTime, The Chinese University of Hong Kong, and Fudan University. Pretrained on over 2.3T high-quality Chinese-English and code token data, it demonstrates outstanding comprehensive performance and powerful tool-calling capabilities.

Natural Language ProcessingTransformers

This is a tool that uses advanced models to detect whether text content is generated by AI. It can distinguish between real content (Label_1) and false content generated by AI (Label_0), aiming to help users identify the source and credibility of information.

Natural Language ProcessingTransformers

A Russian BERT model jointly trained by Sber AI team and MLSA Lab at Moscow State University's AI Institute, specializing in scientific text processing

Natural Language ProcessingTransformersOther