This is an image text recognition model based on DeepSeek-OCR, which specifically solves the compatibility issues in the latest version of the transformers library, enabling the model to run smoothly in the latest versions such as transformers v4.57.1.

MultimodalTransformersEnglish

Lam-2 is the second-generation small language model (SLM) developed based on the custom architecture Aricate V4. It performs excellently in question and answer tasks and has outstanding language coherence and creativity. Compared with the previous generation products, Lam-2 has significantly improved in grammatical correctness and text generation quality.

Natural Language ProcessingSafetensorsFrench

meiki.text.detect.v0.1 is a high-precision, low-latency OCR model specifically designed for text detection in video games and comics, and it performs excellently on Japanese-related content. This model is based on the D-FINE detector architecture and uses MobileNet v4 small as the backbone network, offering two resolution variants to suit different application scenarios.

Computer VisionOnnxMultiple Languages

This is the quantized version of TheDrummer's Cydonia - R1 - 24B - v4.1 model. It uses the llama.cpp tool for multi-precision quantization processing and can run efficiently under different hardware conditions, providing users with more options.

Natural Language ProcessingGguf

Jina Embeddings v4 is a general-purpose embedding model designed for multimodal and multilingual retrieval, especially suitable for retrieving complex documents, including visually rich documents containing charts, tables, and illustrations.

MultimodalTransformersOther

CardProjector - v4 is a language model specifically designed for generating character cards. It is perfectly compatible with SillyTavern and can automatically generate detailed and well - structured character cards for creators and role - playing game players, greatly improving the efficiency of character creation.

Natural Language ProcessingSafetensorsEnglish

Trendyol LLM v4.1.0 is a generative model based on Trendyol LLM base v4.0 (a Qwen2.5 7B version further pre-trained on 13 billion tokens), specializing in e-commerce and Turkish language understanding.

Natural Language ProcessingSafetensorsOther

Yuna Ai V4 is a multilingual text generation model based on the LLaMA 3.1 8B architecture, focusing on providing intelligent dialogue and knowledge Q&A experiences. After training with over 3B tokens, it has advanced features such as quantum thinking and performs outstandingly in dialogue ability and creativity.

Natural Language ProcessingGgufMultiple Languages

CyberRealistic XL v4 is a high-quality text-to-image model focused on generating realistic images.

MultimodalDiffusers

A large language model with 12B parameters, merged by Lumimaid and Magnum v4, using the DELLA merging method and incorporating the Nemo model optimized for Claude input

Natural Language ProcessingTransformers

An NFT digital art generation model based on LoRA technology, specifically optimized for V4 NFT designs

Computer VisionDiffusers

Magnum V4 72B is a member of the model series built on Qwen, aiming to replicate the prose quality of the Claude 3 series models and suitable for local AI chat applications.

Natural Language ProcessingTransformersEnglish

Magnum v4-22B is a large language model fine-tuned based on Mistral-Small-Instruct-2409, specifically dedicated to replicating the text quality of the Claude 3 series models (especially Sonnet and Opus). This model provides a GGUF quantized version, supports a 32K context length, and is trained on multiple high-quality datasets.

Natural Language ProcessingTransformersEnglish

Fluently XL V4 is a high-performance text-to-image model ranked #4 on imgsys.org Arena, renowned for its precise human anatomy and dual capability in artistic and photorealistic generation.

Computer VisionDiffusers

Fluently V4.0-LCM is an all-purpose task model that achieves high-speed image generation by integrating multiple models and LCM technology, featuring precise anatomical structures and high artistic expression.

Computer VisionDiffusers

Fluently V4-inpainting is a versatile image processing model created by merging multiple checkpoints and LoRA techniques, excelling particularly in image inpainting and extension tasks.

Computer VisionDiffusers

Athena v4 is an experimental large language model suitable for role-playing, emotional role-playing, and general scenarios. Uses Alpaca format prompt templates.

Natural Language ProcessingTransformers

Mamba - GPT - 3B - V4 is an outstanding 3B parameter language model that performs excellently on the Open LLM leaderboard, surpassing dolly - v2 - 12b and providing high - quality language processing capabilities.

Natural Language ProcessingTransformersEnglish

Anything V4 is a latent diffusion model designed for anime enthusiasts, aimed at generating high-quality, high-detail anime-style images with simple prompts.

Computer VisionDiffusersEnglish

Anything V4 is a latent diffusion model for anime enthusiasts, capable of generating high-quality, high-detail anime-style images based on a small number of prompts.

Computer VisionDiffusersEnglish