Pulp_collage is a text-to-image generation model trained based on a specific base model. It can generate images with a vintage collage art style through the specific trigger word 'rentler', providing more possibilities for creative image generation.

Computer VisionDiffusers

This is an astronomy professional model fine-tuned based on the Gemma-3-4B model. It is specifically optimized for Portuguese astronomy Q&A and can provide more accurate and contextually relevant Portuguese astronomy answers.

Natural Language ProcessingTransformersEnglish

Thinkless is a large language model trained via reinforcement learning, capable of adaptively selecting short or long-chain reasoning modes, significantly reducing inference computational costs.

Natural Language ProcessingTransformers

The Thinkless framework is a learnable framework that enables large models to adaptively choose between short reasoning or long-chain reasoning based on task complexity and their own capabilities.

Natural Language ProcessingTransformers

Vintern-1B-v3_5 is a 1-billion-parameter vision-language model supporting image-text generation tasks.

MultimodalGguf

Vintern-3B-beta is a multilingual foundation model that supports English, Vietnamese, and Chinese, and is mainly used for image-text to text conversion tasks.

MultimodalTransformersMultiple Languages

A visual question answering model fine-tuned based on InternVL3-1B and Vintern-1B-v3_5, supporting Vietnamese, suitable for image content understanding and question-answering tasks.

MultimodalSafetensorsOther

KunoRZN-Llama-3-3B is VinkuraAI's flagship multilingual model, supporting over 12 Indian languages and English, specifically designed for education, healthcare, and daily tasks.

Natural Language ProcessingTransformersMultiple Languages

A Vietnamese text classification model fine-tuned from vinai/phobert-base-v2, achieving 89.62% accuracy on the validation set

Natural Language ProcessingTransformers

Gemma 3 is a lightweight open-source multimodal model series by Google, supporting text and image inputs with text generation capabilities. This version is a 27B parameter instruction-tuned model using quantization-aware training, offering lower memory requirements while maintaining near-original quality.

MultimodalGguf

Gemma 3 is a lightweight open model built by Google based on Gemini technology, supporting text and image inputs to generate text outputs. The 12B version is instruction-tuned and suitable for various generation and comprehension tasks.

MultimodalGguf

Gemma 3 is a lightweight open-source multimodal model family launched by Google, built on the same technology as Gemini, supporting text and image inputs and generating text outputs.

MultimodalGguf

A text-to-image model that incorporates Leonardo da Vinci's artistic style, blending Renaissance aesthetics with modern AI painting through LoRA technology.

Computer VisionDiffusers

LoRA trained on the Wan2.1 14B T2V model for generating retro VHS-style videos

MultimodalDiffusersEnglish

A sentiment analysis model fine-tuned from vinai/phobert-base-v2, achieving 93.6% accuracy on the evaluation set

Natural Language ProcessingTransformers

This is a 256-rank style low-rank adapter for generating animations via the Wan2.1 1.3B model, trained on 70 paintings by masters Dubosarskiy and Vinogradov.

MultimodalDiffusersOther

This is an image generation model based on the Flux architecture, specifically designed to generate realistic amateur photography-style images. The model supports various parameter settings and version selections, and can generate photographic works with a vintage blog and Flickr style based on text descriptions.

Computer VisionDiffusers

Vintern-3B-R-beta is a multimodal large language model focused on complex reasoning tasks based on images, capable of decomposing reasoning steps and effectively controlling hallucination phenomena.

MultimodalTransformersMultiple Languages

Vintix is a multi-task action model achieved through contextual reinforcement learning, demonstrating outstanding performance across multiple benchmarks.

This is a fine-tuned sentence transformer model based on sentence-transformers/all-MiniLM-L6-v2, designed to map text into a 384-dimensional vector space, supporting tasks like semantic similarity computation.

Natural Language ProcessingSafetensors