This is an open-source LoRA model specifically designed for Qwen-Image, focusing on simulating the realistic look and feel of modern iPhone photography. The model is trained on more than 5000 real iPhone-style photos and can generate clear, natural images suitable for social media sharing.

Computer VisionDiffusers

This model is a joke rating model fine-tuned on multilingual text based on FacebookAI/xlm-roberta-large. It is specifically designed to evaluate the quality and humor level of jokes. It achieved an accuracy of 0.4005 and a root mean square error of 5.0327 on the evaluation set.

Natural Language ProcessingTransformers

Charlotte-AMY is a fine-tuned small language model developed by Clemylia, with 51 million parameters, focusing on the fields of hope, friendship, ethics, and support. This model adheres to the concept of 'training quality is better than the number of parameters' and performs excellently in semantic clarity and coherence, providing high-quality ethical consultation and emotional support services.

Natural Language ProcessingTransformersFrench

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

This is a video action recognition model fine-tuned on the WLASL dataset based on the VideoMAE-Base architecture. After 200 epochs of training, it achieved a top-1 accuracy of 52.96% and a top-5 accuracy of 79.88% on the evaluation set, specifically designed for sign language action recognition tasks.

Computer VisionTransformers

This is the Nunchaku quantization (SVDQ) version of the UltraReal Fine-Tune text-to-image model based on Danrisi's Flux architecture. The model offers two quantization formats: INT4 for non-Blackwell architecture GPUs (before the 50 series) and NVFP4 for Blackwell architecture GPUs (50 series), aiming to reduce hardware requirements while maintaining image generation quality.

Computer VisionDiffusersEnglish

gpt-oss-safeguard-120b is a security reasoning model built by OpenAI based on gpt-oss, with 117 billion parameters (5.1 billion of which are active parameters). This model is specifically designed for security use cases and can classify text content and perform basic security tasks according to the provided security policies.

Natural Language ProcessingTransformers

Lamapi/next-12b is a large language model based on 12B parameters. It is fine-tuned with a multilingual dataset, supports more than 50 languages, has efficient text generation capabilities, and is suitable for natural language processing tasks in multiple fields such as chemistry, code, biology, finance, and law.

Natural Language ProcessingTransformersMultiple Languages

MiniMax-M2-5bit is a 5-bit quantized version converted from the MiniMaxAI/MiniMax-M2 model, optimized specifically for the MLX framework. This model is a large language model that supports text generation tasks and is released under the MIT license.

Natural Language ProcessingMlx

This is a quantized version based on Qwen3-Coder-REAP-25B-A3B, specifically optimized for Mac devices. It uses the Deckard (qx) formula for quantization, with 6-bit quantization for the embedding layer, heads, and selective attention paths, and 5-bit quantization for the rest, with a group size of 32. It achieves more efficient operation while maintaining a quality close to q8 quantization.

Natural Language ProcessingMlxEnglish

This is a fine-tuned version of the Qwen-Coder-14B model on the network dataset, specifically optimized for network data scenarios. It performs better in specific network tasks compared to the base version. The model was trained for 3 epochs with a learning rate of 5e-5.

Natural Language ProcessingTransformers

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

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

This is the MLX format conversion version of Meituan's LongCat-Flash-Chat model, using the innovative DQ6_K_M quantization technology. It is optimized for Apple Mac Studio M3 Ultra devices with 512GB of memory, significantly reducing memory usage while maintaining performance close to 8-bit quantization.

Natural Language ProcessingMlx

This is an English to Sanskrit translation model fine-tuned based on the T5-small architecture. After 50 rounds of training, the validation loss reaches 0.1564, enabling efficient and accurate translation of English text into Sanskrit.

Natural Language ProcessingTransformers

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

Stable Diffusion v1-5 is a text-to-image generation model based on latent diffusion technology, capable of generating realistic images according to text descriptions. This model is trained on the LAION-2B dataset, supports English text input, and generates images with a resolution of 512x512.

MultimodalDiffusers

Wan2.2 is a significant upgrade version of the basic video model. It introduces the Mixture of Experts (MoE) architecture, incorporates carefully curated aesthetic data, and is trained on larger datasets to enhance the ability to generate complex motions. This model supports generating 5-second videos with 480P and 720P resolutions, and has significant improvements in video generation quality and performance.

MultimodalDiffusers

The 5-bit quantized version of the IBM Granite-4.0-H-Tiny model, optimized for Apple silicon chips. It uses a hybrid architecture of Mamba-2 and soft attention, combined with a Mixture of Experts model (MoE), to achieve efficient inference while maintaining high quality.

Natural Language ProcessingMlxMultiple Languages

Apriel-1.5-15b-Thinker is a 15-billion parameter multimodal reasoning model developed by ServiceNow. It has the ability to reason with text and images, and its performance can rival models 10 times larger. It scored 52 points on the manual analysis index and performed excellently in enterprise domain benchmark tests.

MultimodalTransformers