README.md

---
license: apache-2.0
library_name: sentence-transformers
pipeline_tag: sentence-similarity
base_model: voyageai/voyage-4-nano
tags:
  - sentence-transformers
  - code-retrieval
  - multilingual
  - matryoshka
datasets:
  - BrokkAI/Quarry
---

# Muninn

Muninn is a 346M-parameter multilingual retriever for natural-language-query →
code-function retrieval, with an 8,192-token serving context and 2,048-dimensional
embeddings.

It is trained from `voyageai/voyage-4-nano` and uses a bidirectional Qwen3 encoder.
Muninn supports Matryoshka truncation at 512, 1,024, 1,536, and 2,048 dimensions. We
recommend 2,048 dimensions: that is the native evaluation setting, and truncating to 512
cost roughly two recall points at depth on Quarry.

## Usage

Muninn requires `trust_remote_code=True` because this repository includes the custom
`Qwen3BidirectionalModel` implementation.

```python
from sentence_transformers import SentenceTransformer

model = SentenceTransformer(
    "BrokkAI/Muninn",
    trust_remote_code=True,
    truncate_dim=2048,
)
model.max_seq_length = 8192

queries = ["Where is retry backoff calculated for failed HTTP requests?"]
documents = [
    "src/net/client.py/HttpClient/retry_delay\n"
    "class HttpClient:def retry_delay(self, attempt):\n"
    "    return min(60, 2 ** attempt)"
]

query_embeddings = model.encode(queries, prompt_name="query", normalize_embeddings=True)
document_embeddings = model.encode(
    documents, prompt_name="document", normalize_embeddings=True
)
scores = model.similarity(query_embeddings, document_embeddings)
print(scores)
```

The exact inference prompts are:

```text
query:    Represent the query for retrieving supporting documents: 
document: Represent the document for retrieval: 
```

### Document format

Quarry results use the header format produced by `swerank_document_text()` before the
document prompt is applied. For a free function:

```text
{path}/{function_name}
{source}
```

For a class method:

```text
{path}/{ClassName}/{function_name}
class {ClassName}:{source}
```

The worked usage example above is therefore the exact representation of a method named
`HttpClient.retry_delay` in `src/net/client.py`. Preserve this shape when comparing against
reported results.

## Quarry results

[Quarry](https://huggingface.co/datasets/BrokkAI/Quarry) contains 6,525 synthetic behavioral
queries over real repository revisions. The metric is strict all-gold micro recall@k: for
each query, `|gold ∩ top-k| / |gold|`, followed by a flat mean over queries. Models use their
native dimensions and the header document format above.

We measured every row ourselves with the Quarry harness. Muninn leads a field that includes
much larger open models and commercial APIs.

| Model | Params | recall@5 | recall@20 | recall@50 |
|---|---:|---:|---:|---:|
| **Muninn** | 346M | **61.4** | **82.6** | **90.7** |
| voyage-code-3 | API | 59.1 | 81.8 | 90.4 |
| voyage-4 | API | 59.0 | 80.8 | 90.0 |
| SweRank-Large | 7B | 58.5 | 80.6 | 89.6 |
| Nemotron-3-Embed-1B | 1B | 58.3 | 79.9 | 88.7 |
| bge-code-v1 | 1.5B | 58.2 | 79.8 | 88.7 |
| voyage-4-nano (base) | 346M | 57.5 | 79.7 | 89.0 |
| voyage-4-lite | API | 57.3 | 79.6 | 89.0 |
| Qwen3-Embedding-8B | 8B | 56.0 | 78.2 | 88.1 |
| SweRank-Small | 137M | 53.5 | 74.6 | 83.9 |
| [Muninn-small](https://huggingface.co/BrokkAI/Muninn-small) | 47M | 52.3 | 74.6 | 84.7 |
| text-embedding-3-large | API | 51.7 | 74.3 | 85.0 |
| Qwen3-Embedding-0.6B | 0.6B | 50.9 | 72.8 | 83.8 |
| granite-embedding-small-english-r2 (Muninn-small base) | 47M | 47.7 | 69.7 | 80.5 |

## Other benchmarks

† marks published numbers (SweRank paper for the localization benchmarks; the CoIR
leaderboard and the Qwen3-Embedding paper elsewhere). Unmarked rows are our measurements
on the same protocol as the corresponding published numbers.

**SWE-Bench-Lite localization** — 274 Python issues, function-level accuracy:

| Model | Acc@5 | Acc@10 |
|---|---:|---:|
| **Muninn (346M)** | **73.4** | 79.6 |
| SweRank-Large (7B)† | 71.9 | **82.1** |
| SweRank-Small (137M)† | 63.1 | 74.5 |
| Muninn-small (47M) | 48.5 | 61.0 |

**LocBench** — 560 Python issues, function-level accuracy:

| Model | Acc@10 | Acc@15 |
|---|---:|---:|
| SweRank-Large (7B)† | **63.2** | **67.3** |
| **Muninn (346M)** | 60.2 | 65.7 |
| SweRank-Small (137M)† | 58.6 | 63.4 |
| Muninn-small (47M) | 46.4 | 51.6 |

**CoIR text-to-code** — NDCG@10:

| Model | APPS | CosQA |
|---|---:|---:|
| bge-code-v1 (1.5B)† | **98.1** | **46.7** |
| voyage-code-3 (API)† | 93.6 | 34.5 |
| Qwen3-Embedding-8B† | 91.1 | 38.0 |
| **Muninn (346M)** | 77.4 | 31.3 |
| Qwen3-Embedding-0.6B† | 75.3 | 36.5 |
| Muninn-small (47M) | 12.4 | 35.1 |

**CodeSearchNet** — mean NDCG@10 over six languages (Python, JavaScript, Go, Ruby, Java,
PHP; 1,000 queries per language):

| Model | Mean NDCG@10 |
|---|---:|
| Qwen3-Embedding-8B† | **92.7** |
| Qwen3-Embedding-0.6B† | 91.0 |
| **Muninn (346M)** | 90.1 |
| SweRank-Small (137M) | 87.9 |
| SweRank-Large (7B) | 85.0 |
| Muninn-small (47M) | 77.8 |

## Languages

C, C++, C#, Go, Java, JavaScript, PHP, Python, Rust, Scala, and TypeScript.

## License and attribution

Muninn is released under the Apache License 2.0. It is derived from
[`voyageai/voyage-4-nano`](https://huggingface.co/voyageai/voyage-4-nano), also released
under Apache-2.0. See `LICENSE` for the full license text.