This is a quantized version of TheDrummer's Magidonia-24B-v4.3 large language model. By using the imatrix quantization technology of llama.cpp, GGUF format files with various precisions from BF16 to IQ2_XS are generated, aiming to run the model more efficiently under different hardware conditions (especially in resource-constrained environments) while maintaining the model performance as much as possible.

Natural Language ProcessingGguf

This model is a knowledge distillation model based on the Qwen3-4B architecture, trained with approximately 54.4 million tokens generated by Gemini 2.5 Flash, aiming to integrate the behavior, inference process, and knowledge of Gemini-2.5 Flash into a single dataset.

Natural Language ProcessingTransformersEnglish

Trouper-12B GGUF is a text generation model developed by DarwinAnim8or based on the original model. It is specifically optimized for role-playing and creative writing scenarios. This model is fine-tuned from Mistral-Nemo-Base-12B and trained using a custom 'Actors' dataset. The generated text is more natural and avoids the common 'AI language' features.

Natural Language ProcessingGgufEnglish

chroma_art-lora is a specially designed LoRA model aimed at endowing the generated images with unique artistic aesthetics, especially focusing on vivid colors and artistic styles. It is suitable for creating stylized digital artworks, such as anime, movie-like images, and desktop wallpapers.

Computer VisionDiffusers

An AI text detection model fine-tuned based on DeBERTa-v3-large, capable of accurately identifying whether text is written by humans or generated by AI, achieving an accuracy of approximately 97% when trained on a custom dataset.

Natural Language ProcessingSafetensorsEnglish

This is a quantized version based on the swiss-ai's Apertus-70B-Instruct-2509 model. Multiple quantized model files are generated using the imatrix technology of llama.cpp, aiming to improve the model's running efficiency and resource utilization, and support flexible selection of suitable quantization levels under different hardware conditions.

Natural Language ProcessingGguf

pejawan22-lora is a LoRA model trained based on AI technology, specifically designed for generating specific images and can be integrated with various AI tools. Images are generated by the trigger word 'peja'.

MultimodalDiffusers

WEBGEN DEVSTRAL IMAGES is an AI model focused on web page generation. It can generate single-page web pages using HTML, CSS, JS, and Tailwind technologies. This project is trained based on custom templates and uses the supervised fine-tuning method, training with a dataset generated by GPT-OSS-120B.

Natural Language ProcessingTransformersEnglish

This is a quantized version of the zerofata's L3.3-GeneticLemonade-Opus-70B model, aiming to optimize the model's running efficiency and performance on different hardware. By using specific quantization tools and methods, multiple quantized versions of the model are generated to meet the needs of different users.

Natural Language ProcessingGguf

An elastic model generated by TheStage AI's ANNA, offering multiple optimized versions to adapt to different scenario requirements, supporting multilingual text generation.

The Elastic Model is a series of models generated by TheStage AI ANNA, allowing free adjustment of model scale, latency, and quality through a sliding control bar, providing the fastest and most flexible solution for self-hosting scenarios.

Granite-3.2-2B-Instruct is a 2-billion-parameter long-context AI model specifically fine-tuned for reasoning capabilities. Built upon Granite-3.1-2B-Instruct, it was trained using a mix of permissively licensed open-source datasets and internally generated synthetic data to enhance performance on reasoning tasks.

Natural Language ProcessingGguf

Qwen2.5-14B-it-restore is a model generated by combining the della, ties, and model stock fusion methods based on the Qwen2.5-14B and Qwen2.5-14B-Instruct models, aiming to address the decline in instruction-following capability and weakened mathematical ability.

Natural Language ProcessingSafetensorsMultiple Languages

This is a collection of quantized models in GGUF format generated using the imatrix quantization method of llama.cpp based on the meta-llama/Llama-3.2-3B-Instruct model. This project provides multiple quantized versions with precisions ranging from 1-bit to 8-bit, aiming to reduce the storage and computational resource requirements for model deployment while maintaining model performance as much as possible.

Natural Language ProcessingGgufMultiple Languages

TinyLlama is a small large language model with 1.1 billion parameters. It has been pre-trained on 3 trillion tokens and fine-tuned on synthetic dialogue data generated by ChatGPT, aiming to provide efficient dialogue capabilities.

Natural Language ProcessingGguf

An experimental model built on Meta's Llama-3. It is fine-tuned using synthetic data generated by airoboros and further fine-tuned with multiple DPO datasets. It excels in various tasks such as context-based Q&A, summary generation, and long text generation.

Natural Language ProcessingTransformers

This model is an AI-generated text detection model trained on real human text and AI-generated text, effectively identifying whether the text is generated by artificial intelligence.

Natural Language ProcessingTransformersChinese

This model was created by fine-tuning the umm-maybe AI art detector on the Wikimedia-SDXL image pair dataset, specifically designed to detect images generated by SDXL.

Computer VisionTransformers

The SD-XL 1.0 Refiner Model is an image generation model developed by Stability AI, designed to enhance the quality of images generated by the SDXL base model, with particular expertise in the final denoising step.

Computer VisionDiffusers

This is a tool that uses advanced models to detect whether text content is generated by AI. It can distinguish between real content (Label_1) and false content generated by AI (Label_0), aiming to help users identify the source and credibility of information.

Natural Language ProcessingTransformers