---
title: intfloat/e5-mistral-7b-instruct
description: Improving Text Embeddings with Large Language Models. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 20. Mistral, 7.1B parameters.
canonical_url: https://superlinked.com/models/intfloat-e5-mistral-7b-instruct
last_updated: 2026-06-09
---

# intfloat/e5-mistral-7b-instruct

Improving Text Embeddings with Large Language Models. Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei, arXiv 2024

Source: [intfloat/e5-mistral-7b-instruct on HuggingFace](https://huggingface.co/intfloat/e5-mistral-7b-instruct)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Mistral |
| Parameters | 7.1B |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 4,096 |
| Max sequence length | 4,096 tokens |
| License | mit |
| Inputs | text |
| Languages | en |

## Benchmarks

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.3932 · map at 10: 0.1477 · mrr at 10: 0.6024

**Performance (L4 b1 c16):** Corpus 3.1K tok/s · Corpus p50 1.2s · Query 212 tok/s · Query p50 230.4ms

[Reference](https://www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/)

### NanoFiQA2018Retrieval

Domain: finance · Task: retrieval · Language: en

Smaller subset of the FiQA financial QA dataset

**Quality:** ndcg at 10: 0.5960 · map at 10: 0.5317 · mrr at 10: 0.6404

**Performance (L4 b1 c16):** Corpus 2.9K tok/s · Corpus p50 670.1ms · Query 466 tok/s · Query p50 224.6ms

[Reference](https://sites.google.com/view/fiqa/)