Publisher
Use Case(1)
NIM Type
Sorting by Most Recent
nvidia /
nv-rerankqa-mistral-4b-v3GPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.
nvidia /
nv-embedqa-e5-v5GPU-accelerated generation of text embeddings used for question-answering retrieval.
nvidia /
nv-embed-v1Generates high-quality numerical embeddings from text inputs.
baai /
bge-m3Embedding model for text retrieval tasks, excelling in dense, multi-vector, and sparse retrieval.
snowflake /
arctic-embed-lGPU-accelerated generation of text embeddings.
nvidia /
embed-qa-4GPU-accelerated generation of text embeddings used for question-answering retrieval.
nvidia /
rerank-qa-mistral-4bGPU-accelerated model optimized for providing a probability score that a given passage contains the information to answer a question.