# Apache-2.0 License

Qwen3-32B-8bit is an 8-bit quantized version of the Qwen3-32B model, designed for text generation tasks and released by mlx-community.

This is a GGUF format conversion version based on the Wan-AI/Wan2.1-T2V-14B model, primarily used for text-to-video generation tasks.

OpenF5 TTS is an open-source text-to-speech model trained on the F5-TTS framework, supporting zero-shot voice cloning functionality, released under the Apache 2.0 license for commercial use.

Qwen3-0.6B is an open-source language model based on the Transformer architecture, with a parameter scale of 600 million, suitable for natural language processing tasks such as text summarization.

OLMo 2 1B SFT is a supervised fine-tuned version of the OLMo-2-0425-1B model, trained on the Tulu 3 dataset, designed to achieve state-of-the-art performance across multiple tasks.

A 14B-parameter multimodal model released by Alibaba PAI, supporting text-to-video generation tasks

A learned sparse retrieval model supporting 15 languages, designed specifically for OpenSearch, enabling efficient retrieval without inference

A table classification model based on the Apache-2.0 license, supporting the English language, primarily used for table data classification tasks.

Jina Embeddings V2 Base Code is a transformer-based English text embedding model, specializing in feature extraction and sentence similarity calculation for code-related texts.

This is a medical summarization model trained on the Bilal-Mamji/Medical-summary dataset, primarily used for generating concise summaries from medical texts.

This is a visual question answering model based on the Apache-2.0 license, supporting the English language, and focusing on handling vision-related question answering tasks.

Optical Character Recognition model specialized for Japanese text in manga

A 3B-parameter large language model fine-tuned on the OpenAssistant/oasst1 dataset, trained using H2O LLM Studio

A 12B-parameter educational safety evaluation model designed specifically for classroom content appropriateness assessment

Insufficient model information available to provide a specific introduction.

Stanza is a precise and efficient multilingual text analysis toolkit that provides text analysis capabilities for Urdu.

A Persian sentence embedding model based on ParsBERT for generating high-quality sentence vector representations

This is a customized lightweight version of bert-base-multilingual-cased, optimized specifically for Thai language processing while maintaining the original model's accuracy.

This is a text processing model supporting Russian, primarily used for text generation and text completion tasks.