This is a text generation model optimized using PEFT (Parameter-Efficient Fine-Tuning) and LoRA techniques based on the Google Gemma-2B-IT base model. The model is optimized for specific tasks while maintaining the capabilities of the base model through parameter-efficient methods.

Natural Language ProcessingPeft

This model is a violence detection model based on the VideoMAE architecture. After pre-training on the Kinetics dataset, it was fine-tuned for 92 rounds for the violence detection task. The model uses the Vision Transformer architecture and is specifically designed for video content analysis, capable of identifying violent behaviors in videos.

Computer VisionTransformers

This is a 6-bit quantized version converted from the Kimi-Linear-48B-A3B-Instruct model, optimized for the Apple MLX framework. The model retains the powerful instruction-following ability of the original model, while significantly reducing storage and computational requirements through quantization technology, making it suitable for efficient operation on Apple hardware.

Natural Language ProcessingMlx

This is a 4-bit quantized version converted from the moonshotai/Kimi-Linear-48B-A3B-Instruct model, optimized for the Apple MLX framework, providing efficient text generation capabilities.

Natural Language ProcessingMlx

Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods in various scenarios, including short and long contexts, as well as reinforcement learning extension mechanisms. It can effectively solve the problem of low efficiency of traditional attention mechanisms in long context tasks and bring more efficient solutions to fields such as natural language processing.

Natural Language ProcessingTransformers

Kimi Linear is an efficient hybrid linear attention architecture that outperforms traditional full attention methods in short context, long context, and reinforcement learning scenarios. It optimizes attention computation through the Kimi Delta Attention (KDA) mechanism, significantly improving performance and hardware efficiency, and is particularly good at handling long context tasks up to 1 million tokens.

Natural Language ProcessingTransformers

This model is a video understanding model based on the VideoMAE-Large architecture, pre-trained on the Kinetics dataset and then fine-tuned on an unknown dataset. It achieved an accuracy of 85.86% and a loss value of 0.7987 on the evaluation set, demonstrating excellent video classification ability.

Computer VisionTransformers

MLX is a text generation library built on the Qwen/Qwen3-Next-80B-A3B-Thinking base model, focusing on efficient inference and text generation tasks. This model adopts an advanced architecture design, supporting high-performance text processing under large-scale parameters.

Natural Language ProcessingMlx

A text generation model optimized based on the MLX library. It uses the Qwen/Qwen3-Next-80B-A3B-Instruct base model and is optimized with the bf16 data type, focusing on efficient text generation tasks and providing high-performance support for related field development.

Natural Language ProcessingMlx

This is a high-quality quantized version of Moonshot AI's Kimi-K2-Instruct-0905 model, using the HQ4_K quantization method. It is specifically optimized for inference performance, supports a context length of 75,000, and is suitable for text generation tasks.

Natural Language ProcessingGgufOther

This is the MLX format conversion version of the moonshotai/Kimi-K2-Instruct-0905 model, using the innovative DQ3_K_M dynamic 3-bit quantization technology, specifically optimized for Apple Silicon Mac devices. It significantly reduces memory usage while maintaining performance close to 4-bit quantization.

Natural Language ProcessingMlx

This is a quantized version of the moonshotai/Kimi-K2-Instruct-0905 model, dedicated to making knowledge accessible to everyone. This project provides optimized model weights for easy deployment and use on various hardware.

Natural Language ProcessingGguf

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

This is the GGUF format quantized version of the moonshotai/Kimi-K2-Instruct-0905 model, using the ik_llama.cpp branch for optimal quantization. The model adopts a mixture of experts architecture, supports Chinese dialogue and text generation tasks, and has been optimized with various quantization schemes to significantly reduce memory usage while maintaining high quality.

Natural Language ProcessingGgufOther

KONI-4B-instruct-20250901 is a large language model developed by the Korea Institute of Science and Technology Information (KISTI) focusing on the technology field. It supports Korean and English and performs excellently in various scientific benchmark tests, outperforming other pre-trained models of the same scale.

Natural Language ProcessingTransformersMultiple Languages

This is a statically quantized version of the KiruruP/anime-recommendation-multilingual-mpnet-base-v2-final model, specifically designed for sentence similarity calculation and feature extraction tasks, mainly supporting English. The model offers multiple quantized versions to meet different performance and quality requirements.

Natural Language ProcessingTransformersEnglish

Kimi-VL-A3B-Thinking-2506 is a multimodal visual language model developed by MoonshotAI. It supports the joint understanding and reasoning of images and text, has the ability of chain-of-thought reasoning, and can handle complex visual language tasks.

MultimodalGguf

Kimina-Prover-Distill-0.6B is a theorem proving model developed by Project Numina and the Kimi team, focusing on the ability to solve competition-style problems in Lean 4. It is a distilled version of the Kimina-Prover-72B model, achieving an accuracy of 68.85% on MiniF2F-test.

Natural Language ProcessingTransformersEnglish

This is a LoRA model trained based on the FLUX.1-dev model, specifically designed to generate images of Deborah Jane Ashby, a former British glamour model. This model was trained locally using the Fluxgym framework and can generate images of models in the style of the 1980s - 1990s.

Computer VisionDiffusers

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