Free Trial
Jurassic-2 Light is the quickest large language model (LLM) by AI21 Labs and is available for you to deploy in your private environment. Small but mighty, Jurassic-2 Light is ideal for simple language tasks that require maximum affordability and minimal latency in your private environment. Common...
Model Package - Fulfilled on Amazon SageMaker
This algorithm uses a neural network built in Tensorflow to predict anomalies from transaction and/or sensor data feeds. The model outputs predictions and reconstruction errors for the observations that highlight potential anomalies. Using an adjustable lower order basis representation of the...
Algorithm - Fulfilled on Amazon SageMaker
Given an input image, this model will return object coordinates and category predictions. The format of coordinates is encoded as (left, top, right, bottom) of the absolute pixel locations. This model is trained on COCO dataset with 80 common object categories. It can be used as fast and reliable...
Model Package - Fulfilled on Amazon SageMaker
Given an input image, this model will return object coordinates and category predictions. The format of coordinates is encoded as (left, top, right, bottom) of the absolute pixel locations. This model is trained on COCO dataset with 80 common object categories. It can be used as fast and reliable...
Model Package - Fulfilled on Amazon SageMaker
Free Trial
Embedding models, a crucial building block for retrieval systems, semantic search, and retrieval-augmented generation (RAG), are neural networks that convert documents into numerical vectors. Voyage-code-2 is a cutting-edge embedding model that is trained particularly for semantic retrieval of code...
Model Package - Fulfilled on Amazon SageMaker
Free Trial
Embed Light translates text into numerical vectors that models can understand. The most advanced generative AI apps rely on high-performing embedding models to understand the nuances of user inputs, search results, and documents. Embed Light is a smaller version of Embed with 384 dimensions. This...
Model Package - Fulfilled on Amazon SageMaker
Free Trial
Paraphrase is a task-specific model (TSM) by AI21 Labs that’s built to paraphrase any text – from entire paragraphs and sentences to single words – and offer suggested rewrites that take context into account and preserve the text’s original meaning. The endpoint is pre-loaded and ready to serve...
Model Package - Fulfilled on Amazon SageMaker
Jina Embeddings v2 Base model is optimized for highly accurate embeddings - For speed of inference and memory efficiency use the Small model. jina-embeddings-v2-base-en is an open-source English embedding model supporting 8192 sequence length. This state-of-the-art AI embedding model enables many...
Model Package - Fulfilled on Amazon SageMaker
Free Trial
Embedding models are neural networks that convert documents into numerical vectors. They are a crucial building block for retrieval systems, semantic search, and retrieval-augmented generation (RAG). voyage-finance-2 is optimized for finance domain retrieval and RAG. It demonstrates superior...
Model Package - Fulfilled on Amazon SageMaker
Ambarella’s Model Garden is a collection of models tuned for Ambarella's chipsets for ease of deployment. Users can select the domain and choose from one of the offered models based on their real world application. Every model undergoes transfer learning to adapt to user's dataset and then is...
Algorithm - Fulfilled on Amazon SageMaker
showing 21 - 30