Tarka-Embedding-150M-V1 is an embedding model with 150 million parameters, capable of generating 768-dimensional dense text representations. It is optimized for various downstream applications such as semantic similarity, search, and retrieval-augmented generation (RAG), focusing on capturing deep contextual semantics to support general text understanding across different domains.

Natural Language ProcessingSentence-transformers

This is a model specifically designed for chemical entity recognition, capable of accurately identifying compounds and substances in biomedical literature, providing strong support for biomedical research and clinical applications. This model is trained on the BC4CHEMD dataset and features high precision and domain-specific optimization.

Natural Language ProcessingTransformersEnglish

This is a model specifically designed for gene/protein entity recognition, capable of accurately identifying and extracting information about gene and protein mentions in biomedical texts. The model is trained on the BC2GM dataset, featuring high precision and domain-specific optimization, providing reliable support for clinical and research applications.

Natural Language ProcessingTransformersEnglish

This is a professional chemical entity recognition model that can accurately identify compounds and substances in biomedical literature, providing strong support for biomedical research and clinical applications. This model is trained on the BC4CHEMD dataset and features high precision and specific domain optimization.

Natural Language ProcessingTransformersEnglish

Seed-X-Instruct-7B is a powerful open-source multilingual translation language model that breaks the boundaries of translation ability within the range of 7 billion parameters. It has excellent translation performance, a lightweight architecture, and wide domain coverage, providing strong support for translation research and applications.

Natural Language ProcessingSafetensorsMultiple Languages

Medra4b is a multilingual (English and Romanian) text generation model fine-tuned on medical datasets, specializing in medical domain applications.

Natural Language ProcessingTransformersMultiple Languages

Medra is a medical domain-specific QA and summarization model supporting English and Romanian, designed for medical AI applications.

Natural Language ProcessingGgufMultiple Languages

BGE-m3 is a domain-specific text embedding model customized for legal applications. It can convert legal documents, sentences, and queries into dense vector representations, accurately capturing the subtle semantic relationships in legal language.

Natural Language ProcessingTransformersEnglish

Marsilia-Embeddings-FR-Base is a French embedding model specifically designed for financial domain tasks, demonstrating the importance of task-specific fine-tuning for embedding models in Retrieval-Augmented Generation (RAG) applications.

Natural Language ProcessingTransformersFrench

This is the Investopedia embedding model developed by the FinLang team for financial applications. It is fine-tuned based on BAAI/bge-base-en-v1.5 and maps sentences and paragraphs into a 768-dimensional dense vector space, suitable for semantic search and other tasks in the financial domain.

Natural Language ProcessingSafetensors

WisdomOcean-WisdomInterrogatory is a large legal domain model jointly developed by Zhejiang University, Alibaba DAMO Academy, and Huayuan Computing, focusing on legal intelligence applications and judicial efficiency enhancement.

Natural Language ProcessingTransformersMultiple Languages

SEC-BERT is a series of BERT models tailored for the financial domain, trained on 10-K annual reports from the U.S. Securities and Exchange Commission (SEC), supporting financial natural language processing research and fintech applications.

Natural Language ProcessingTransformersEnglish

LEGAL-BERT is a series of BERT models tailored for the legal domain, designed to support legal natural language processing research and applications.

Natural Language ProcessingJaxEnglish