Moonshine Tiny is a lightweight Vietnamese automatic speech recognition model developed by Moonshine AI (formerly Useful Sensors). It has only 27M parameters and is specifically designed for resource-constrained platforms. It performs excellently on the Fleurs and Common Voice 17 datasets.

Audio ProcessingTransformersOther

Granite-3.1-8B-Instruct is a long-context instruction model with 8 billion parameters, fine-tuned from Granite-3.1-8B-Base. It combines open-source instruction datasets and internal synthetic datasets, and is specifically designed to effectively solve long-context problems, supporting multiple languages and various AI tasks.

Natural Language ProcessingTransformers

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

GLM-4-9B is an open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. It performs excellently in the evaluation of datasets such as semantics, mathematics, reasoning, code, and knowledge. It supports multiple languages and various advanced features, including web browsing, code execution, custom tool invocation, and long text reasoning.

Natural Language ProcessingSafetensorsMultiple Languages

GLM-4-9B is an open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. It performs excellently in the evaluation of datasets such as semantics, mathematics, reasoning, code, and knowledge, and has advanced features such as multilingual support.

Natural Language ProcessingSafetensorsMultiple Languages

GLM-4-9B-Chat is an open-source version of the latest generation of pre-trained models in the GLM-4 series launched by Zhipu AI. It performs excellently in the evaluation of datasets such as semantics, mathematics, reasoning, code, and knowledge. It supports advanced features such as multi-round dialogue, web browsing, and code execution, and also supports multilingual and long-context reasoning.

Natural Language ProcessingTransformersMultiple Languages

Granite-3.0-1B-A400M-Instruct is a 1-billion parameter instruction-tuned model developed by IBM, fine-tuned from Granite-3.0-1B-A400M-Base. This model is trained using various open-source instruction datasets and internal synthetic datasets, and supports multilingual processing and multi-domain AI assistant applications.

Natural Language ProcessingTransformers

This is a pathological image analysis model based on the Vision Transformer architecture, specifically designed for the classification and feature extraction of medical pathological images. The model performs excellently on multiple pathological image datasets, providing an effective AI solution for pathological diagnosis and research.

Computer VisionTimm

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

Phi-3-Clinical Edition is a fine-tuned model specifically designed for researchers and developers in the biomedical field. Trained on U.S. government clinical trial datasets, it aims to provide high-quality insights to support R&D in healthcare and pharmaceutical innovation.

Natural Language ProcessingTransformers

A Llama3 model fine-tuned specifically for medical Q&A, trained on AI medical chatbot datasets to provide professional medical answers.

Natural Language ProcessingTransformersMultiple Languages

BRIA 2.3 is a text-to-image model trained on legally compliant datasets, integrating technological innovation with ethical responsibility and legal safeguards, setting a new benchmark for the AI industry.

Computer VisionDiffusers

Cinder is an AI chatbot focused on science and educational dialogue, based on the TinyLlama 1.1 billion parameter model, trained with a variety of unique datasets.

Natural Language ProcessingGguf

Mixtral MOE 2x10.7B is a large language model based on the Mixture of Experts architecture, which combines the advantages of two base models, Sakura-SOLAR-Instruct and CarbonVillain. This model performs excellently in text generation tasks and has been evaluated on multiple public datasets, including benchmark tests such as AI2 Reasoning Challenge, HellaSwag, and MMLU.

Natural Language ProcessingTransformers

A conversational assistant model based on Mistral-v0.1, trained with a mix of AIRIC dataset and multiple public datasets, equipped with social dialogue capabilities.

Natural Language ProcessingTransformers

Experimental 8x7b Mixture of Experts model developed based on Mistral AI's Mixtral 8x7b, fine-tuned on Synthia, MetaMathQA, and Capybara datasets

Natural Language ProcessingTransformersEnglish

This is a text-to-image AI model built based on Stable Diffusion technology, specifically designed to generate images in anime, manga, and illustration styles. The model combines the base models of SDXL and SD 1.5 and has been trained on multiple datasets.

Computer VisionDiffusersEnglish

Saily 220B is a powerful AI model built by merging based on Llama2-70B. It has been fine-tuned on multiple specific domain datasets and has capabilities in multiple aspects such as code, humor, mathematics, logical understanding, physics, reasoning, psychology, and role-playing.

Natural Language ProcessingTransformersEnglish

OpenChat is a series of open-source language models that have been fine-tuned on diverse and high-quality multi-round dialogue datasets, aiming to achieve high performance with limited data.

Natural Language ProcessingTransformersEnglish

RedPajama-INCITE-Chat-3B-v1 is a chat language model with 2.8 billion parameters jointly developed by Together Computer and leading open-source AI communities. It has been fine-tuned on the OASST1 and Dolly2 datasets to specifically enhance dialogue capabilities.

Natural Language ProcessingTransformersEnglish