nvidia/nv-embedqa-e5-v5

Model Overview

Description

The NVIDIA Retrieval QA E5 Embedding Model is an embedding model optimized for text question-answering retrieval.

An embedding model is a crucial component of a text retrieval system, as it transforms textual information into dense vector representations. They are typically transformer decoders that process tokens of input text (for example, question, passage) to output an embedding.

This model is ready for commercial use.

NVIDIA Retrieval QA E5 Embedding Model is a part of NVIDIA NeMo Retriever, which provides state-of-the-art, commercially-ready models and microservices, optimized for the lowest latency and highest throughput. It features a production-ready information retrieval pipeline with enterprise support. The models that form the core of this solution have been trained using responsibly selected, auditable data sources. With multiple pre-trained models available as starting points, developers can also readily customize them for their domain-specific use cases, such as Information Technology, Human Resource help assistants, and Research & Development research assistants.

Intended use

The NVIDIA Retrieval QA E5 Embedding Model is most suitable for users who want to build a question and answer application over a large text corpus, leveraging the latest dense retrieval technologies.

License/Terms of use

The use of this model is governed by the NVIDIA AI Foundation Models Community License Agreement and the MIT License (MIT).

Technology can have a profound impact on people and the world, and NVIDIA is committed to enabling trust and transparency in AI development. NVIDIA encourages users to adopt principles of AI ethics and trustworthiness to guide your business decisions by following the guidelines in the NVIDIA AI Foundation Models Community License Agreement.

Model Architecture

Architecture Type: Transformer
Network Architecture: Fine-tuned E5-Large-Unsupervised retriever
Embedding Dimension: 1024
Parameter Count: 335 million

The NVIDIA Retrieval QA E5 Embedding Model is a transformer encoder - a finetuned version of E5-Large-Unsupervised, with 24 layers and an embedding size of 1024, which is trained on public datasets. The AdamW optimizer is employed incorporating 100 warm up steps and 5e-6 learning rate with WarmupDecayLR scheduler. Embedding models for text retrieval are typically trained using a bi-encoder architecture. This involves encoding a pair of sentences (for example, query and chunked passages) independently using the embedding model. Contrastive learning is used to maximize the similarity between the query and the passage that contains the answer, while minimizing the similarity between the query and sampled negative passages not useful to answer the question.

Model Version(s)

NVIDIA Retrieval QA E5 Embedding Model v5

Short name: NV-EmbedQA-E5-v5

Training Dataset & Evaluation

Training Dataset

The development of large-scale public open-QA datasets has enabled tremendous progress in powerful embedding models. However, one popular dataset named MS MARCO restricts ‌commercial licensing, limiting the use of these models in commercial settings. To address this, we created our own training dataset blend based on public QA datasets, which each have a license for commercial applications.

The training dataset details are as follows:

Use Case: Information retrieval for question and answering over text documents.
Data Sources: Public datasets licensed for commercial use.
Language: English (US)
Volume: 400k samples from public datasets

Data Collection Method by dataset: Unknown
Labeling Method by dataset: Unknown

Evaluation Results

Properties: We evaluated the NVIDIA Retrieval QA E5 Embedding Model in comparison to literature open & commercial retriever models on academic benchmarks for question-answering -NQ, HotpotQA and FiQA(Finance Q&A) from BeIR benchmark and TechQA dataset. Note that the model was evaluated offline on A100 GPUs using the model's PyTorch checkpoint. In this benchmark, the metric used was Recall@5.

Open & Commercial Retrieval Models	Average Recall@5 on NQ, HotpotQA, FiQA, TechQA dataset
NV-EmbedQA-Mistral-7B-v2	72.97%
NV-EmbedQA-Mistral-7B-v1	64.93%
NV-EmbedQA-E5-v5	62.07%
NV-EmbedQA-E5-v4	57.65%
E5-Large-unsupervised	48.03%
BM25	44.67%

Data Collection Method by dataset: Unknown
Labeling Method by dataset: Unknown
Properties: The evaluation datasets are based on the MTEB/BEIR TextQA and TechQA, which are 4 public datasets. The size ranges between 10,000s up to 5M depending on the dataset.

Technical Details

Input

Input Type: text
Input Format: list of strings
Other Properties Related to Input: The model's maximum context length is 512 tokens. Texts longer than maximum length must either be chunked or truncated.

Output

Output Type: floats
Output Format: list of float arrays
Other Properties Related to Output: Model outputs embedding vectors of dimension 1024 for each text string

Software Integration

Runtime: NeMo Retriever Text Embedding NIM
Supported Hardware Microarchitecture Compatibility: NVIDIA Ampere, NVIDIA Hopper, NVIDIA Lovelace
Supported Operating System(s): Linux
Engine: TensorRT
Test Hardware: See Support Matrix from NIM documentation.

We evaluated the models optimized for different hardware on a small sample dataset of 600 queries.

Ethical Considerations

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ tab for the Explainability, Bias, Safety & Security, and Privacy subcards. Please report security vulnerabilities or NVIDIA AI Concerns here.