---
title: NovaSearch/stella_en_1.5B_v5
description: We released a Jasper and Stella model technology report and code.(2025.1). Qwen2, 1.5B parameters.
canonical_url: https://superlinked.com/models/novasearch-stella_en_1-5b_v5
last_updated: 2026-05-24
---

# NovaSearch/stella_en_1.5B_v5

We released a Jasper and Stella model technology report and code.(2025.1)

Source: [NovaSearch/stella_en_1.5B_v5 on HuggingFace](https://huggingface.co/NovaSearch/stella_en_1.5B_v5)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Qwen2 |
| Parameters | 1.5B |
| Tasks | Encode |
| Outputs | Dense |
| Dimensions | Dense: 1,024 |
| Max sequence length | 512 tokens |
| License | mit |
| Inputs | text |

## Benchmarks

### CQADupstackPhysicsRetrieval

Domain: scientific · Task: retrieval · Language: en

Duplicate question retrieval from StackExchange Physics

Corpus: 38,314 · Queries: 1,039

**Quality:** ndcg at 10: 0.5293 · map at 10: 0.4592 · mrr at 10: 0.5136

**Performance (L4 b1 c16):** Corpus 11.7K tok/s · Corpus p50 180.9ms · Query 2.0K tok/s · Query p50 73.7ms

[Reference](http://nlp.cis.unimelb.edu.au/resources/cqadupstack/)

### CosQA

Domain: technology · Task: retrieval · Language: en

Code search with natural language queries

Corpus: 6,267 · Queries: 500

**Quality:** ndcg at 10: 0.3239 · map at 10: 0.2437 · mrr at 10: 0.2626

**Performance (L4 b1 c16):** Corpus 8.5K tok/s · Corpus p50 100.4ms · Query 1.2K tok/s · Query p50 71.8ms

[Reference](https://arxiv.org/abs/2105.13239)

### FiQA2018

Domain: finance · Task: retrieval · Language: en

Financial opinion mining and question answering

Corpus: 57,599 · Queries: 648

**Quality:** ndcg at 10: 0.6050 · map at 10: 0.5203 · mrr at 10: 0.6769

**Performance (L4 b1 c16):** Corpus 13.0K tok/s · Corpus p50 222.0ms · Query 2.2K tok/s · Query p50 74.6ms

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

### LegalBenchConsumerContractsQA

Domain: legal · Task: retrieval · Language: en

Question answering on consumer contracts

Corpus: 153 · Queries: 396

**Quality:** ndcg at 10: 0.8108 · map at 10: 0.7641 · mrr at 10: 0.7653

**Performance (L4 b1 c16):** Corpus 16.7K tok/s · Corpus p50 522.2ms · Query 2.7K tok/s · Query p50 84.9ms

[Reference](https://huggingface.co/datasets/nguha/legalbench)

### NFCorpus

Domain: medical · Task: retrieval · Language: en

Biomedical literature search from NutritionFacts.org

Corpus: 3,593 · Queries: 323

**Quality:** ndcg at 10: 0.4170 · map at 10: 0.1630 · mrr at 10: 0.6201

**Performance (L4 b1 c16):** Corpus 12.8K tok/s · Corpus p50 406.0ms · Query 1.0K tok/s · Query p50 70.5ms

[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: 0.6555 · map at 10: 0.5859 · mrr at 10: 0.6764

**Performance (L4 b1 c16):** Corpus 1.2K tok/s · Corpus p50 1.5s · Query 1.1K tok/s · Query p50 117.8ms

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

### SCIDOCS

Domain: scientific · Task: retrieval · Language: en

Citation prediction, document classification, and recommendation for scientific papers

Corpus: 25,656 · Queries: 1,000

**Quality:** ndcg at 10: 0.2666 · map at 10: 0.1649 · mrr at 10: 0.4293

**Performance (L4 b1 c16):** Corpus 12.5K tok/s · Corpus p50 257.9ms · Query 2.0K tok/s · Query p50 77.3ms

[Reference](https://allenai.org/data/scidocs)

### SciFact

Domain: scientific · Task: retrieval · Language: en

Scientific claim verification using research literature

Corpus: 5,183 · Queries: 300

**Quality:** ndcg at 10: 0.8004 · map at 10: 0.7557 · mrr at 10: 0.7662

**Performance (L4 b1 c16):** Corpus 12.8K tok/s · Corpus p50 356.8ms · Query 3.0K tok/s · Query p50 80.0ms

[Reference](https://github.com/allenai/scifact)

### StackOverflowQA

Domain: technology · Task: retrieval · Language: en

Programming question answering from Stack Overflow

Corpus: 19,931 · Queries: 1,994

**Quality:** ndcg at 10: 0.9134 · map at 10: 0.8970 · mrr at 10: 0.8970

**Performance (L4 b1 c16):** Corpus 14.2K tok/s · Corpus p50 265.9ms · Query 15.6K tok/s · Query p50 329.0ms

[Reference](https://arxiv.org/abs/2407.02883)