A text generation model developed based on the MLX library, focusing on natural language processing tasks and providing developers with an efficient text generation solution.

Natural Language ProcessingMlxEnglish

This model is based on the transformers library, and its specific purpose and functionality require further information to determine.

Natural Language ProcessingTransformers

A LoRA-adapted model based on the FLUX.1-dev foundation model, specifically designed for generating high-resolution images of Leonardo DiCaprio

Computer VisionDiffusers

This is a sentence-transformers model fine-tuned from allenai/longformer-base-4096, designed to generate 768-dimensional dense vector representations for sentences and paragraphs, suitable for semantic text similarity, semantic search, and related tasks.

Natural Language ProcessingSafetensorsEnglish

PIGuard is a new type of prompt protection model specifically designed to detect prompt injection attacks. Through an innovative training strategy, it significantly reduces the bias towards trigger words, performs excellently in multiple benchmark tests, surpassing the current best model by 30.8%, and provides a powerful open-source protection solution for LLM security.

Natural Language ProcessingTransformersEnglish

InjecGuard is a protective model against prompt injection attacks for large language models (LLMs), capable of effectively identifying and defending against malicious instructions while reducing over-defense issues.

Natural Language ProcessingTransformersEnglish

A text-to-image generation model based on the fusion of C3, DreamlikeShaper, and LeonardoDaVinciStyle LoRA, specializing in versatile artistic style output

Computer VisionDiffusers

A text-to-image model that incorporates Leonardo da Vinci's artistic style, blending Renaissance aesthetics with modern AI painting through LoRA technology.

Computer VisionDiffusers

Qwen2.5-VL-32B-Instruct is a 32B-parameter multimodal large language model supporting vision and language tasks, suitable for complex multimodal interaction scenarios.

MultimodalSafetensors

A speech recognition model optimized for chess coordinate recognition, fine-tuned using nearly 2,500 English chess coordinate audio files

Audio ProcessingTransformersMultiple Languages

This is a text-to-image generation model based on LoRA technology, specifically designed for creating comic-style images.

MultimodalDiffusers

This is a LoRA adaptation weight for stabilityai/stable-diffusion-xl-base-1.0, specifically designed for generating images of LEO cats.

Computer VisionDiffusers

A BitsAndBytes NF4 quantized version based on Aria-sequential_mlp, suitable for image-to-text tasks with approximately 15.5 GB VRAM requirement.

MultimodalTransformers

FP8 dynamically quantized model based on Aria-sequential_mlp, suitable for image-text-to-text tasks, requiring approximately 30GB VRAM.

MultimodalTransformers

An audio classification model fine-tuned on the GTZAN music classification dataset based on DistilHuBERT, achieving 83% accuracy

Audio ProcessingTransformers

Anti-blur image generation model based on Stable Diffusion and LoRA technology

Computer VisionDiffusers

An auto-generated image classifier based on PyTorch and HuggingPics, specifically designed for recognizing sign language alphabets.

Computer VisionTransformers

DiscoLM 70B is a German-optimized large language model based on LeoLM 70B, supporting English and German, suitable for text generation tasks.

Natural Language ProcessingGgufMultiple Languages

DiscoLM 70b is a 70B-parameter multilingual model developed based on Laion's LeoLM 70b, enhanced with additional German text pre-training and instruction fine-tuning to strengthen its English and German capabilities

Natural Language ProcessingTransformersMultiple Languages

EM German Leo Mistral is a German large language model based on the Mistral architecture, focusing on German text generation tasks.

Natural Language ProcessingTransformersGerman