A statically quantized version based on the AQ-MedAI/Diver-GroupRank-7B model, specifically designed for tasks such as paragraph sorting, text sorting, reasoning, and information retrieval. It offers multiple quantization levels to meet different hardware requirements.

Natural Language ProcessingTransformersEnglish

The top model in the aquif-3.5 series, with advanced inference capabilities and a large context window of 1 million tokens, and has excellent performance in multiple benchmark tests. The comprehensive AAII score reaches 60 points.

Natural Language ProcessingTransformersMultiple Languages

The aquif-3.5 series is the masterpiece released on November 3, 2025, including two versions, Plus and Max, which provide advanced inference capabilities and an unprecedented 1 million token context window, achieving state-of-the-art performance in their respective categories.

Natural Language ProcessingTransformersMultiple Languages

Aquif-3.5-Max-42B-A3B is a large language model with 42 billion parameters, which has undergone MXFP4_MOE quantization processing. It optimizes inference efficiency while maintaining high-quality text generation capabilities. This model is based on an advanced mixture-of-experts architecture and is suitable for various natural language processing tasks.

Natural Language ProcessingGguf

This is the MXFP4_MOE quantized version of the aquif-3.5-Plus-30B-A3B model. Through quantization technology, the model's resource occupancy is significantly reduced while maintaining similar performance, which has high engineering practice value.

Natural Language ProcessingGguf

AQUA-7B is the first large language model specifically designed for the aquaculture industry, providing professional insights and solutions.

Natural Language ProcessingTransformersEnglish

EchoLLaMA is a multimodal AI system capable of converting 3D visual data into natural speech descriptions while supporting interactive dialogue through voice input.

MultimodalTransformers

AQUILA-Engine-v1 is a fine-tuned version based on the Qwen2.5-VL-7B-Instruct model, specifically designed for the detection, recognition, and analysis of aerospace engine components.

MultimodalSafetensorsMultiple Languages

A writing evaluation specialized model fine-tuned from Qwen2.5-7B-Instruct, trained with a 12K-scale SFT dataset

Natural Language ProcessingTransformers

LLaVE-2B is a 2-billion-parameter multimodal embedding model based on Aquila-VL-2B, featuring a 4K token context window and supporting embeddings for text, images, multiple images, and videos.

MultimodalTransformersEnglish

MiewID-msv3 is a contrastive learning-trained feature extractor for individual re-identification across 64 terrestrial and aquatic wildlife species on a large-scale high-quality dataset.

Computer VisionTransformers

Flux_Aquarell_Watercolor_V2 is a text-to-image generation model based on FLUX.1-dev, specifically designed to generate watercolor-style images. The model uses a specific trigger 'AQUACOLTOK' to guide the generation of watercolor art effects, and performs particularly well on white backgrounds.

Computer VisionDiffusersEnglish

This is the official AQLM quantized version of the Meta-Llama-3.1-8B-Instruct model, fine-tuned using the PV-Tuning method. Through advanced quantization techniques, the size of the original model is compressed from 16.1GB to 4.1GB, significantly improving inference efficiency while maintaining good performance.

Natural Language ProcessingTransformers

This is the official quantized version of the Meta Llama 3.1 8B instruction model, using the AQLM quantization method and PV-Tuning fine-tuning technology. It significantly reduces the model size while maintaining high performance, compressing from 16.1GB to 3.4GB.

Natural Language ProcessingTransformers

MiewID-msv2 is a wildlife individual re-identification feature extractor trained through contrastive learning, supporting the recognition of 54 terrestrial and aquatic species.

Computer VisionTransformers

A Sinhala speech recognition model fine-tuned based on openai/whisper-small, supporting conversion of Sinhala speech to text.

Audio ProcessingTransformers

A speech-to-text model fine-tuned based on openai/whisper-small, supporting audio translation and text generation tasks.

Audio ProcessingTransformers

A multilingual large language model based on Mistral 7B, incorporating chat vector technology, focused on text generation tasks

Natural Language ProcessingTransformersEnglish

This model is a question-answering model based on the DeBERTa architecture, fine-tuned on the SQuAD1, AQA, and NewsQA datasets.

Natural Language ProcessingTransformers

A Q&A model fine-tuned on SQuAD1, AQA, and NewsQA datasets based on the DeBERTa-base model

Natural Language ProcessingTransformers