This is an experimental quantized large language model that uses the Deckard (qx) quantization method with 3-bit quantization for the embedding layer. The model is reconstructed using the Norm-Preserving Bi-Projection Elimination (NPBA) technique, which not only removes the security restriction mechanism but also enhances the model's cognitive depth and reasoning ability.

Natural Language ProcessingMlx

Qwen3-VL is the most powerful vision-language model in the Tongyi series. It has excellent text understanding and generation capabilities, in - depth visual perception and reasoning capabilities, long - context support, strong spatial and video dynamic understanding capabilities, and outstanding agent interaction capabilities.

MultimodalTransformers

Qwen3-VL is the most powerful visual language model in the Tongyi series. It has excellent text understanding and generation capabilities, in - depth visual perception and reasoning abilities, long - context support, strong spatial and video dynamic understanding abilities, and agent interaction capabilities. This repository provides GGUF - format weights, supporting efficient inference on devices such as CPUs and GPUs.

MultimodalTransformers

Qwen3 - VL is the most powerful vision - language model in the Tongyi series. It has excellent text understanding and generation capabilities, in - depth visual perception and reasoning abilities, long - context support, strong spatial and video dynamic understanding abilities, and outstanding intelligent agent interaction abilities.

MultimodalTransformers

PokeeResearch - 7B is a 7 - billion - parameter in - depth research agent model developed by Pokee AI. It combines Reinforcement Learning from AI Feedback (RLAIF) and a powerful reasoning framework, enabling reliable, aligned, and scalable research - level reasoning in tool - enhanced large language models. It is suitable for complex multi - step research workflows.

Natural Language ProcessingTransformersEnglish

This model is based on GPT-OSS-20B and fine-tuned using the Unsloth reinforcement learning framework. The aim is to optimize inference efficiency and reduce vulnerabilities that occur during reinforcement learning from human feedback (RLHF) training. The fine-tuning process focuses on the robustness and efficiency of alignment, ensuring that the model maintains inference depth without incurring excessive computational overhead.

Natural Language ProcessingTransformersEnglish

Qwen3-VL is the most powerful vision - language model in the Tongyi series, with excellent text understanding and generation capabilities, in - depth visual perception and reasoning abilities, long - context support, enhanced spatial and video dynamic understanding abilities, and strong agent interaction capabilities.

MultimodalTransformers

MapAnything is an end-to-end trained Transformer model that can take multiple modalities as input and directly regress the decomposed metric 3D geometric structure of the scene. This model supports more than 12 different 3D reconstruction tasks, including multi-image SfM, multi-view stereo vision, and monocular metric depth estimation.

Computer VisionSafetensorsEnglish

Qwen3-4B-Thinking-2507 is an upgraded version of the Qwen3-4B model, significantly improving thinking ability, reasoning quality, and depth, and performing excellently in various tasks, supporting 256K long context understanding.

Natural Language ProcessingTransformers

DINOv3 is a series of general visual foundation models developed by Meta AI. Without fine-tuning, it can outperform specialized state-of-the-art models in a wide range of visual tasks. This model uses self-supervised learning to generate high-quality dense features and performs excellently in various tasks such as image classification, segmentation, and depth estimation.

Computer VisionTransformersEnglish

Qwen3-235B-A22B-Thinking-2507 is a powerful large language model with significant improvements in reasoning tasks, general capabilities, and long context understanding. It is suitable for highly complex reasoning scenarios. The model has continuously expanded its thinking ability in the past three months, improving the quality and depth of reasoning.

Natural Language ProcessingTransformers

Jan - Nano is a compact language model with 4 billion parameters, designed specifically for in - depth research tasks and optimized to support MCP server integration.

Natural Language ProcessingGguf

DeepSeek-R1-0528 is a minor version upgrade model of the DeepSeek R1 series. It significantly improves the inference depth and ability through increased computing resources and algorithm optimization, and performs excellently in multiple benchmark tests such as mathematics and programming.

Natural Language ProcessingTransformers

A LoRA trained on the Wan2.1 14B I2V 480p model, featuring smooth curved paths for camera movement around subjects to enhance depth and cinematic motion effects.

Computer VisionDiffusersEnglish

KiraDepth is a text-to-image generation model based on Stable Diffusion XL, specializing in creating 2.25D/2.5D-style images with depth, detail, and shadows, particularly suited for anime-style artwork.

Computer VisionDiffusersEnglish

Muse-12B is a large language model focused on text adventures and role-playing, excelling in emotional depth and long-context narrative coherence.

Natural Language ProcessingTransformersEnglish

GLM - 4 - Z1 - 32B - 0414 is a new - generation open - source large language model in the GLM family, with 32 billion parameters and the ability for in - depth thinking. Through cold - start and extended reinforcement learning training, it performs excellently in mathematics, code, and logic tasks and supports convenient local deployment.

Natural Language ProcessingTransformersMultiple Languages

An image generation model based on depth information that can control the depth of field effect and spatial structure of generated images through depth maps.

Computer VisionDiffusersEnglish

Image depth estimation model based on Latent Bridging Matching (LBM) technology, achieving rapid image transformation through latent space bridging

Computer VisionSafetensors

YamNet is an audio event classification model trained on the AudioSet dataset. It uses the Mobilenet_v1 depthwise separable convolution architecture and is optimized for deployment on mobile devices. It can accurately identify and classify various audio events.

Audio ProcessingPytorch