This project is a quantized version based on the MiniMaxAI/MiniMax-M2 model, aiming to make knowledge accessible to the public. It provides multiple model versions with different quantization levels and shows the perplexity performance indicators of each version.

Natural Language ProcessingGguf

Omni L1B3RT4S GENIE is an AI assistant fine-tuned based on the Qwen2.5-3B Instruct architecture. It is trained with customized examples of 1,103 elf characters, and has unique voice and loyalty modes, capable of providing users with a unique dialogue experience.

Natural Language ProcessingGgufEnglish

This is a LoRA model for flight and bullet time video effects based on Wan2.1, specifically designed to generate images with bullet time effects, capable of creating a unique visual effect where a character floats in the air and the camera perspective rotates around the character.

Computer VisionDiffusers

VieNeu-TTS is the first Vietnamese text-to-speech model that can run on personal devices and has the ability of instant voice cloning. Fine-tuned based on NeuTTS Air, it can generate natural and realistic Vietnamese speech and has real-time performance on the CPU.

Audio ProcessingSafetensorsOther

TheWhisper-Large-V3-Turbo is a high-performance fine-tuned version of the OpenAI Whisper Large V3 model, optimized by TheStage AI for real-time, low-latency, and low-power speech-to-text inference across multiple platforms. It supports stream transcription, word timestamps, and scalable performance, making it suitable for scenarios such as real-time subtitles, meetings, and device-side voice interfaces.

Audio ProcessingTransformersOther

Svara-TTS is an open-source multilingual text-to-speech model for Indian languages, supporting 19 languages (18 Indian languages + Indian English). This model is built based on the Orpheus-style discrete audio token method, aiming to achieve clear, expressive, and low-latency speech synthesis on ordinary GPUs/CPUs.

Audio ProcessingTransformersMultiple Languages

KaniTTS is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. Through a unique two-stage architecture that combines a large language model with an efficient audio codec, it achieves low-latency and high-quality speech synthesis, with a real-time factor as low as 0.2, which is 5 times faster than real-time speed.

Audio ProcessingTransformersEnglish

This is a quantized version of the Alibaba Tongyi Deep Research 30B-A3B model. It uses MXFP4_MOE quantization technology and additionally adds imatrix quantization, aiming to optimize model performance and resource utilization efficiency, and is suitable for text generation tasks.

Natural Language ProcessingGguf

The Wenxin Image Fusion Lora Model is an AI model specifically designed for image fusion and editing. It can correct the perspective of products, adjust lighting effects, and seamlessly integrate products into the background environment to achieve high-quality image synthesis.

Computer VisionDiffusers

LFM2-VL-3B is a multimodal vision-language model developed by Liquid AI, built on the LFM2 backbone architecture. It has powerful visual understanding and reasoning capabilities, especially excelling in fine-grained perception tasks. This model can efficiently process text and image inputs and supports native image processing with a resolution of up to 512×512.

MultimodalTransformersMultiple Languages

KaniTTS Pretrain v0.3 is a high-speed, high-fidelity text-to-speech model optimized for real-time conversational AI applications. It uses a two-stage pipeline architecture that combines a large language model and an efficient audio codec to achieve extremely low latency and high-quality speech synthesis.

Audio ProcessingTransformersMultiple Languages

PokeeResearch-7B is a 7-billion-parameter deep research intelligent agent developed by Pokee AI. It combines reinforcement learning based on AI feedback (RLAIF) with an inference framework and can execute complex multi-step research workflows, including self-correction, verification, and comprehensive analysis.

Natural Language ProcessingTransformersEnglish

DeepSeek-OCR is an advanced optical character recognition model developed by DeepSeek AI, focusing on exploring the boundaries of visual text compression and capable of efficiently extracting and converting text content from images.

MultimodalSafetensorsOther

Qwen-SEA-LION-v4-32B-IT is a large Southeast Asian language model built on Qwen3-32B, specifically pre-trained and instruction fine-tuned for the Southeast Asian region. This model continues pre-training on the SEA-Pile v2 corpus containing 7 Southeast Asian languages and undergoes instruction fine-tuning on 8 million pairs of high-quality question-and-answer data, possessing strong multilingual understanding and reasoning abilities.

Natural Language ProcessingTransformersMultiple Languages

This is a quantized version of the KAT-Dev model of Kwaipilot, processed using the imatrix quantization technology of llama.cpp, aiming to improve the running efficiency and performance of the model in different hardware environments. This version offers multiple quantization levels, from high quality to extreme compression, to meet different memory and computing resource requirements.

Natural Language ProcessingGguf

Bee-8B is an advanced fully open-source multimodal large language model that focuses on data quality and aims to narrow the performance gap with proprietary models. By using the high-quality Honey-Data-15M corpus and the advanced data processing pipeline HoneyPipe, it demonstrates excellent performance in complex reasoning and other aspects.

MultimodalTransformersEnglish

ArcMind is a next - generation dialogue model developed by ArcDevs, focusing on natural interaction, adaptive intelligence, and context precision, aiming to provide users with a seamless, human - like dialogue experience.

Natural Language ProcessingTransformersEnglish

This is a LoRA adapter trained based on the Wan2.1-T2V-14B model, specifically designed for text-to-video conversion tasks. The model is trained using the AI Toolkit to support video generation applications.

MultimodalDiffusers

This is a LoRA (Low-Rank Adaptation) model trained based on the Qwen-Image model, specifically designed for text-to-image generation tasks. This project is trained using AI Toolkit and can convert text descriptions into high-quality images, supporting use in various image generation tools.

MultimodalDiffusers

NVIDIA GPT-OSS-120B Eagle3 is an optimized version based on the OpenAI gpt-oss-120b model. It adopts the Mixture of Experts (MoE) architecture, with a total of 120 billion parameters and 5 billion active parameters. This model supports both commercial and non-commercial use and is suitable for text generation tasks, especially for the development of AI Agent systems, chatbots, and other applications.

Natural Language ProcessingSafetensors