This project is the result of 4-bit (UINT4, SVD rank of 32) quantization of Tencent's Hunyuan Image 3.0 model. It uses the SDNQ quantization method and is specifically designed for text-to-image generation tasks.

MultimodalTransformers

franc3sca is a low-noise LoRA model based on the tencent/SRPO base model, specifically designed for text-to-image generation tasks. This model effectively triggers image generation through the specific trigger word 'franc3sca' and has the characteristic of low noise.

Computer VisionDiffusers

This is a project for generating images based on text, using LoRA and Diffusers technologies. It is based on the tencent/SRPO model and can generate relevant images through the specific trigger word 'hannah'.

Computer VisionDiffusers

ARC-Qwen-Video-7B is a multimodal model developed by Tencent ARC Laboratory for understanding real-world short videos. It is built on Qwen2.5-VL-7B-Instruct and supports the analysis and understanding of audio-video synchronization.

MultimodalTransformers

This is a fine-tuned and quantized version of Tencent's SRPO model, which mainly improves the clarity of generated images and the model's compatibility. It provides 8-bit/4-bit quantization options, bringing users a better experience.

Computer VisionDiffusersEnglish

SRPO is a human preference alignment method for diffusion models. Through Direct-Align technology and semantic relative preference optimization, it significantly improves the realism and aesthetic quality of the FLUX.1-dev model, and solves the problems of high computational cost in multi-step denoising and dependence on offline reward fine-tuning.

Computer VisionDiffusers

Hunyuan-MT-7B is a 7B parameter translation model launched by Tencent, supporting mutual translation of 33 languages, including 5 ethnic minority languages in China. This model performed excellently in the WMT25 competition, winning the first place in 30 out of 31 language categories, and proposed a complete translation model training framework from pre-training to integrated optimization.

Natural Language ProcessingTransformersMultiple Languages

This is the quantized version of Tencent's Hunyuan-MT-Chimera-7B model, dedicated to making knowledge accessible to everyone. It reduces the threshold for model deployment and operation through quantization technology.

Natural Language ProcessingGguf

This project provides a quantized version of Tencent's Hunyuan-MT-7B large language model. Through model compression technology, it reduces the computing and storage requirements, aiming to make knowledge accessible to everyone and make high-performance AI models more popular and user - friendly.

Natural Language ProcessingGguf

The Hunyuan translation model is an advanced machine translation system developed by Tencent, including the translation model Hunyuan-MT-7B and the integrated model Hunyuan-MT-Chimera. This model supports mutual translation of 33 languages, including mainstream languages such as Chinese, English, and French, as well as five ethnic minority languages in China, and performed excellently in the WMT25 competition.

Natural Language ProcessingTransformers

This is the quantized version of Tencent Hunyuan Translation Model 7B, which supports translation in multiple languages and can meet diverse translation needs in different scenarios. The model is quantized in the GGUF format, offering multiple quantization levels to adapt to different hardware and performance requirements.

Natural Language ProcessingTransformersMultiple Languages

A quantized version of the multilingual translation model based on Tencent's Hunyuan - MT - Chimera - 7B, offering multiple quantization precision options and supporting translation tasks for 36 languages, including mainstream and niche languages, providing an efficient tool for multilingual communication.

Natural Language ProcessingTransformersMultiple Languages

A quantized version of the Tencent Hunyuan 4B Instruction Model based on llama.cpp. Through quantization technology, the model can run more efficiently in resource-constrained environments while maintaining a certain level of performance and quality. It offers multiple quantization type options and supports online repackaging optimization.

Natural Language ProcessingGguf

This is a quantized version of the Tencent Hunyuan 1.8B Instruction Model. It uses llama.cpp for imatrix quantization processing and offers multiple quantization levels, effectively improving the model's running efficiency on different hardware. It supports running in LM Studio or projects based on llama.cpp.

Natural Language ProcessingGguf

This is the GGUF quantized version of Tencent Hunyuan's 0.5B instruction fine-tuning model. It is quantized using the imatrix technology of llama.cpp, offering multiple quantization options from BF16 to extremely low bit rates, suitable for Chinese dialogue tasks in resource-constrained environments.

Natural Language ProcessingGguf

Hunyuan is a series of efficient large language models open-sourced by Tencent, designed for multi-purpose deployment in various computing environments. From edge devices to high-concurrency production systems, these models can achieve optimal performance with advanced quantization support and ultra-long context capabilities.

Natural Language ProcessingTransformers

ARC-Hunyuan-Video-7B is a multimodal model developed by Tencent ARC Lab, specifically designed to understand short video content in the real world. It can process visual, audio, and text signals end-to-end, achieving in-depth structured understanding of videos by integrating multimodal clues.

MultimodalTransformers

A 5-bit quantized version converted from Tencent's Hunyuan A13B large model, suitable for the MLX framework on Apple chips

Natural Language ProcessingMlx

The 4-bit quantization version of Tencent Hunyuan A13B large language model, suitable for instruction following tasks

Natural Language ProcessingMlx

The quantized version of Tencent Hunyuan A13B Instruction Model, which uses technical means to improve operational efficiency while ensuring performance.

Natural Language ProcessingGguf