Parrotlet-e is an advanced multilingual medical embedding model optimized specifically for medical terms in various Indian languages. It is fine - tuned based on BAAI/bge - m3 and trained on over 18 million pairs of multilingual medical terms. It supports 12 Indian languages and English and has strong robustness against abbreviations, spelling variations, and colloquial expressions in clinical documents.

Natural Language ProcessingTransformers

This is a high-performance 4-bit quantized version of the Kimi K2 Instruct model, optimized for running on Apple Silicon (M1/M2/M3/M4) Macs using the MLX framework. The model has 671 billion parameters, supports a 128K context window, and achieves an excellent balance between quality and efficiency, making it an ideal choice for most practical deployments.

Natural Language ProcessingMlxMultiple Languages

This is the MLX format conversion version of Meituan's LongCat-Flash-Chat model, using the innovative DQ6_K_M quantization technology. It is optimized for Apple Mac Studio M3 Ultra devices with 512GB of memory, significantly reducing memory usage while maintaining performance close to 8-bit quantization.

Natural Language ProcessingMlx

GLM-4.6 is an efficient text generation model based on the MLX framework. It uses 6.5-bit quantization technology, significantly reducing the computational resource requirements while maintaining high-quality text generation capabilities. This model can run on a single M3 Ultra device and supports efficient text generation tasks.

Natural Language ProcessingMlxMultiple Languages

Based on the moonshotai/Kimi-K2-Instruct-0905 base model, a large language model dynamically quantized using the improved MLX 0.26. Through an innovative dynamic quantization strategy, it significantly reduces hardware requirements while maintaining excellent performance and can run efficiently on a single M3 Ultra device.

Natural Language ProcessingMlx

Kimi-K2 Dynamic MLX is a text generation project built on the moonshotai/Kimi-K2-Instruct model, using the optimized MLX library to achieve efficient quantization performance. This model runs on a single M3 Ultra machine with 512GB RAM, supports multiple quantization methods, and shows excellent perplexity metrics in tests.

Natural Language ProcessingMlx

This is a static quantized version of the moka-ai/m3e-base model, specifically designed for text embedding tasks and supporting both Chinese and English. It offers a variety of quantization levels, from Q2_K to f16, to meet the performance and accuracy requirements of different scenarios.

Natural Language ProcessingTransformersMultiple Languages

A surrealist-style text-to-image generation model developed by Alvdansen Lab, based on Stable Diffusion XL with LoRA technology.

Computer VisionDiffusers

SSCD is a deep learning model for image copy detection, capable of extracting image features and performing similarity comparisons.

Computer VisionTransformers

This is an open source project based on the Apache 2.0 license, which provides users with extensive usage rights and guarantees. The specific functions and features of the model need to be further confirmed.

Natural Language ProcessingTransformers

M3 is a multimodal model that allows explicit control of visual granularity at runtime and can serve as a metric for image/dataset complexity. It is fine-tuned from LLaMA/Vicuna.

MultimodalTransformers

M3D is a 3D medical image analysis technology based on multimodal large language models, including the M3D-Data dataset, M3D-LaMed model, and M3D-Bench evaluation benchmark.

MultimodalTransformers

M3D-CLIP is a CLIP model specifically designed for 3D medical imaging, achieving visual and language alignment through contrastive loss.

MultimodalTransformers

This is an embedding model specifically designed for French and English. Based on the sentence-transformers framework, it can map sentences and paragraphs to a 1024-dimensional dense vector space and can be used for tasks such as clustering and semantic search. This model is obtained by fine-tuning the dense model of BGE M3 on custom French and English data.

Natural Language ProcessingSentence-transformers

This is a sentence embedding model based on sentence-transformers, capable of converting text into 768-dimensional vector representations, suitable for tasks such as semantic similarity calculation.

Natural Language ProcessingTransformers

An automatic speech recognition (ASR) model fine-tuned on the Persian Common Voice dataset based on Facebook's wav2vec2-large-xlsr-53 model

Audio ProcessingTransformersOther

A speech recognition model fine-tuned on the Turkish Common Voice dataset based on facebook/wav2vec2-large-xlsr-53

Audio ProcessingJaxOther

The first ALBERT model specifically for Persian, based on Google's ALBERT base v2.0 architecture, trained on diverse Persian corpora

Natural Language ProcessingTransformersOther

This is an Estonian automatic speech recognition (ASR) model fine-tuned from the facebook/wav2vec2-large-xlsr-53 model, trained using the Common Voice dataset.

Audio ProcessingJaxOther

Persian (ZWNJ) sentence embedding model based on RoBERTa architecture for generating sentence-level feature representations

Natural Language ProcessingTransformers