This is a Dutch patient simulation model fine-tuned based on Google's Gemma 2 9B model, specifically designed for medical education scenarios. The model always responds in a fixed JSON structure, simulating a patient 'Maria' who has just completed surgery and is in the recovery process, supporting nursing students to exercise communication and clinical reasoning skills in a safe environment.

Natural Language ProcessingGgufOther

Moondream 3 Preview HF is a re-implementation of the Moondream 3 (Preview) model based on the HuggingFace Transformers architecture specification, making it fully compatible with the Hugging Face ecosystem. It is a multimodal vision-language model that uses a Mixture of Experts (MoE) text backbone, with approximately 9 billion parameters and 2 billion active parameters.

MultimodalTransformers

This is the GGUF format version of the GPT-OSS 20B model based on WeOpenML, which first implements the innovative MoE CPU expert offloading technology. This technology achieves a 99.9% reduction in video memory while maintaining the full generation quality, and only requires 2MB of video memory to run a 20 billion parameter mixture of experts model.

Natural Language ProcessingSafetensorsMultiple Languages

A version fine-tuned based on google/medgemma-4b-it, specifically designed for binary breast X-ray image classification on the OMAMA 256×256 dataset. This model uses LoRA (Low-Rank Adaptation) for parameter-efficient adjustment and performs excellently in the breast cancer classification task, with the accuracy increasing from 12% of the base model to 95%.

MultimodalTransformersEnglish

An advanced named entity recognition model specifically designed to extract structured information from resumes. This model was trained on 22,542 resume samples, achieving an F1 score of 90.87%. It can recognize 25 types of entities, including personal information, contact details, work experience, educational background, and skills.

Natural Language ProcessingSafetensorsMultiple Languages

T5Gemma is a lightweight encoder-decoder research model launched by Google. By adapting a decoder-only pre-trained model to an encoder-decoder architecture, it achieves a better quality-efficiency trade-off. This model has a 9 billion parameter encoder and a 2 billion parameter decoder, and is suitable for various generation tasks such as question answering, summarization, and reasoning.

Natural Language ProcessingTransformers

A Ukrainian-optimized model based on Gemma 2 9B, developed by INSAIT Institute, featuring exceptional Ukrainian cultural and language understanding while retaining the original top-tier English capabilities.

Natural Language ProcessingTransformersMultiple Languages

TxGemma is a series of lightweight, advanced open language models based on Gemma 2, specifically fine-tuned for therapeutic development. Available in 2B, 9B, and 27B sizes, it excels in processing information related to therapeutic modalities and targets.

Natural Language ProcessingTransformersEnglish

TxGemma is a lightweight open-source language model based on Gemma 2, fine-tuned specifically for therapeutic development, available in 2B, 9B, and 27B sizes.

Natural Language ProcessingTransformersEnglish

TxGemma is a lightweight open-source language model based on Gemma 2, fine-tuned specifically for therapeutic development, available in 2B, 9B, and 27B sizes.

Natural Language ProcessingTransformersEnglish

TxGemma is a lightweight open-source language model series fine-tuned based on Gemma 2, optimized for therapeutic development, available in 2B, 9B, and 27B scales.

Natural Language ProcessingTransformersEnglish

TxGemma is a lightweight open-source language model series based on Gemma 2, specifically fine-tuned for therapeutic development, available in 2B, 9B, and 27B sizes.

Natural Language ProcessingTransformersEnglish

FocalCodec is a low bitrate speech codec based on focal modulation technology. It is designed for efficient compression of speech signals, which can significantly reduce the bitrate while maintaining high speech quality. This model is trained on the LibriTTS 960 dataset and provides 50Hz checkpoints for 16kHz and 24kHz sampling rates, suitable for speech communication and storage scenarios that require low bandwidth transmission.

Audio ProcessingSafetensors

GaMS - 9B is an improved model based on Google Gemma 2 - 9B. It has undergone continuous pre - training specifically for the Slovenian language and also supports English, Croatian, Serbian, and Bosnian. This model performs excellently in Slovenian NLP tasks and is a high - performance open - source language model for the Slovenian - speaking community.

Natural Language ProcessingTransformersMultiple Languages

A LoRA model trained on the FLUX.1-dev base model for generating images of Alicia Silverstone's appearance from the late 90s to early 2000s.

MultimodalDiffusers

Lightweight NSFW image detection model with 98.56% accuracy, size only 1/18-1/20 of similar models

Computer VisionTimm

The Llamacpp imatrix quantized version based on the 01 - ai/Yi - Coder - 9B - Chat model, implemented using the transformers library, supports text generation tasks, and uses the apache - 2.0 license. This version significantly reduces the model size through quantization technology while maintaining good performance.

Natural Language ProcessingTransformers

ArtiWaifu Diffusion 2.0 is a high-quality anime-style image generation model fine-tuned based on Stable Diffusion XL, supporting over 9,000 art styles and more than 6,000 anime characters.

Computer VisionDiffusersEnglish

A LoRa-trained text-to-image model specifically designed to generate images in the style of late 90s/early 2000s PS1/N64 gaming consoles.

MultimodalDiffusers

InternLM-XComposer2.5 is an outstanding text-image understanding and creation model that achieves GPT-4V level performance with just 7B parameters, supporting 24K interleaved text-image context and extendable to 96K long context.

MultimodalTransformers