--- tags: - sentence-transformers - feature-extraction - code-search - code-embedding - retrieval - modernbert - dense base_model: Shuu12121/NightOwl pipeline_tag: feature-extraction library_name: sentence-transformers license: apache-2.0 datasets: - Shuu12121/coir_hard_negative_datasets_v3_kd - Shuu12121/owl_code_search_hard_negative_datasets_V2_kd - Shuu12121/codeedit_hard_negative_datasets_kd --- # NightOwl-CodeEmbedding πŸ¦‰ `NightOwl-CodeEmbedding` is a compact 768-dimensional dense embedding model specialized for code retrieval, code-edit retrieval, and technical question answering. The model is fine-tuned from [`Shuu12121/NightOwl`](https://huggingface.co/Shuu12121/NightOwl), a ModernBERT-based code model. It uses CLS pooling with cosine similarity and does **not** require `query:` / `passage:` style prefixes. ## Highlights * Compact (150.8M parameters) yet competitive on CoIR-style code retrieval benchmarks * On the [MTEB(Code, v1)](https://huggingface.co/spaces/mteb/leaderboard) leaderboard it ranks **18th out of 241 models overall** and is the **top-scoring single-vector model under 300M parameters** among scored entries on the official board, ahead of many models an order of magnitude larger (see [Leaderboard Standing](#leaderboard-standing)) * Covers **eight programming languages**, including Rust and TypeScript in addition to the six CodeSearchNet languages * Handles a wide range of code retrieval scenarios: NL-to-code search, code-to-code retrieval, **code-edit retrieval**, and technical QA * Trained with hard negatives mined by `Qwen/Qwen3-Embedding-0.6B` (15 hard negatives per anchor) * Decontaminated against CodeSearchNet test splits and the CodeEditSearchRetrieval benchmark (see [Data Decontamination](#data-decontamination)) * Drop-in compatible with `sentence-transformers`, Apache-2.0 license ## Supported Languages The training data covers the six CodeSearchNet languages plus two additional languages: * Go, Java, JavaScript, PHP, Python, Ruby (CodeSearchNet languages) * **Rust, TypeScript** (additional) Performance on languages outside this set is not guaranteed and may vary. ## Usage ```python from sentence_transformers import SentenceTransformer model = SentenceTransformer("Shuu12121/NightOwl-CodeEmbedding") queries = ["Python function that sorts a list in descending order"] documents = [ "def sort_desc(values): return sorted(values, reverse=True)", "def average(values): return sum(values) / len(values)", ] query_embeddings = model.encode(queries) document_embeddings = model.encode(documents) # Cosine similarity (embeddings are normalized internally by similarity()) scores = model.similarity(query_embeddings, document_embeddings) print(scores) ``` ## Model Details | Property | Value | | ----------------------- | -------------------- | | Base model | `Shuu12121/NightOwl` | | Architecture | ModernBERT | | Parameters | 150,779,136 | | Embedding dimension | 768 | | Pooling | CLS pooling | | Maximum sequence length | 1,024 tokens | | Similarity | Cosine similarity | | Query/document prefixes | Not required | | Weight dtype | FP32 | | Weight memory | 575 MiB | | License | Apache-2.0 | ## MTEB Results The model was evaluated with MTEB on code-related retrieval and technical QA tasks. Evaluation setup: * Model revision: `c7c8a57b9539297e192d5cf39b9aecf1fb376edd` * MTEB version: `2.15.1` * Metric: `NDCG@10` * Hardware: NVIDIA GeForce RTX 5090 * Batch size: 64 Multi-subset task scores are reported as macro averages. | Task | Split | NDCG@10 | | -------------------------------- | ------: | ----------: | | AppsRetrieval | test | 0.39177 | | COIRCodeSearchNetRetrieval | test | 0.84264 | | CodeEditSearchRetrieval | trainΒΉ | 0.74808 | | CodeFeedbackMT | test | 0.76690 | | CodeFeedbackST | test | 0.85207 | | CodeSearchNetCCRetrieval | test | 0.91805 | | CodeSearchNetRetrieval | test | 0.89239 | | CodeTransOceanContest | test | 0.75953 | | CodeTransOceanDL | test | 0.36057 | | CosQA | test | 0.42810 | | StackOverflowQA | test | 0.86608 | | SyntheticText2SQL | test | 0.68266 | | **Macro average, all 12 tasks** | | **0.70907** | | **CoIR macro average, 10 tasks** | | **0.68684** | ΒΉ `CodeEditSearchRetrieval` does not provide a standard `test` split in MTEB, so the official `train` split is used for evaluation. These examples were **not** used for fine-tuning. See [Data Decontamination](#data-decontamination) for details. ### Leaderboard Standing On the public [MTEB(Code, v1)](https://huggingface.co/spaces/mteb/leaderboard) leaderboard, the model's task-mean score (70.91, i.e. the 12-task macro average above Γ—100) places it as follows: * **#18 of 241 models overall**, ahead of many models that are an order of magnitude larger * **#6 of 155 among sub-1B-parameter dense single-vector models** β€” and the **smallest model in that top six**. The five models ranked above it are all β‰ˆ0.33–0.6B parameters (`F2LLM-v2-0.6B/330M`, `pplx-embed-v1-0.6b`, `C2LLM-0.5B`, `Qwen3-Embedding-0.6B`), i.e. 2–4Γ— larger. * **#1 among ranked dense single-vector models under 300M parameters** (the leaderboard's small-model view) * **#2 once late-interaction / multi-vector models are included**, behind only `lightonai/LateOn-Code` (a multi-vector late-interaction model β€” see the [head-to-head below](#head-to-head-vs-lateon-code)) > **Reading the numbers fairly.** MTEB(Code, v1) reports a *zero-shot %* for > each model β€” the fraction of leaderboard tasks the model was *not* trained on. > `NightOwl-CodeEmbedding` is **8%** zero-shot: it was trained on most of these > task families, so its score reflects strong **in-domain** retrieval rather > than zero-shot transfer. Models marked **100%** (e.g. `embeddinggemma-300m`, > the `granite-embedding` r2 family, `Qwen3-Embedding`) are evaluated fully > out-of-domain, so a raw score comparison across rows with different > zero-shot % is not apples-to-apples. The fairest direct comparisons are to > other code-specialized models at similar zero-shot levels (e.g. > `LateOn-Code` at 8%, the `F2LLM` / `C2LLM` families at 8–58%). ### Comparison with similar-sized models The table below compares `NightOwl-CodeEmbedding` with other compact code / general embedding models on MTEB(Code, v1), with a size ladder of larger models for reference. Score is the leaderboard task mean (higher is better); the *Zero-shot* column is the share of tasks the model did not train on. | Model | Params | Type | Emb. dim | Max tokens | Zero-shot | MTEB(Code, v1) ↑ | | ---------------------------------------------------- | ------: | -------------- | -------------- | ---------: | --------: | ---------------: | | **`NightOwl-CodeEmbedding`** (this model) | 150.8M | single-vector | 768 | 1,024 | 8% | **70.91** | | `codefuse-ai/F2LLM-v2-160M` | 159M | single-vector | 640 | 40,960 | 58% | 70.38 | | `google/embeddinggemma-300m` | 308M | single-vector | 768 | 2,048 | 100% | 68.76 | | `codefuse-ai/F2LLM-v2-80M` | 80M | single-vector | 320 | 40,960 | 58% | 67.97 | | `ibm-granite/granite-embedding-311m-multilingual-r2` | 312M | single-vector | 768 | 8,192 | 100% | 63.84 | | _Late-interaction (multi-vector) reference_ | | | | | | | | `lightonai/LateOn-Code` | 149M | multi-vector | 128 (per-tok) | 2,048 | 8% | 74.12 | | _Larger single-vector reference (size ladder)_ | | | | | | | | `codefuse-ai/F2LLM-v2-0.6B` (#1 sub-1B) | 596M | single-vector | 1,024 | 40,960 | 58% | 77.41 | | `Qwen/Qwen3-Embedding-0.6B` | 596M | single-vector | 1,024 | 32,768 | 100% | 75.42 | | `codefuse-ai/F2LLM-v2-14B` (#1 overall) | 13.99B | single-vector | 5,120 | 40,960 | 58% | 80.75 | Takeaways: * Among compact **single-vector dense** models, `NightOwl-CodeEmbedding` is the strongest entry in the leaderboard's small-model view while also being one of the smallest, edging out `F2LLM-v2-160M` and clearly ahead of `embeddinggemma-300m`. * The sub-1B leaders (`F2LLM-v2-0.6B`, `Qwen3-Embedding-0.6B`) score ~4–6.5 points higher but are ~4Γ— the parameter count and use larger embedding dimensions, which directly increases index size and inference cost. * The 14B model at the top of the overall board is ~10 points higher but ~93Γ— larger, sitting in a different deployment cost regime entirely. ### Head-to-head vs LateOn-Code `lightonai/LateOn-Code` is the only sub-0.5B model that outranks `NightOwl-CodeEmbedding` once multi-vector models are included, so it is worth a closer look. It is a **ColBERT-style late-interaction** model (built with PyLate on ModernBERT-base): it stores **one 128-dimensional vector per token** and scores with the MaxSim operator, rather than a single 768-d vector per text. That buys accuracy at the cost of a larger index and a different retrieval path (PyLate + a PLAID index), whereas `NightOwl` is a drop-in single-vector `sentence-transformers` model. Per-task NDCG@10 (Γ—100) on MTEB(Code, v1); both models are code-specialized and in-domain (8% zero-shot), so this is a like-for-like comparison. **Bold** marks the higher score on each task. | Task | NightOwl-CodeEmbedding | LateOn-Code (multi-vec) | | -------------------------- | ---------------------: | ----------------------: | | AppsRetrieval | 39.18 | **54.76** | | COIRCodeSearchNetRetrieval | 84.26 | **86.57** | | CodeEditSearchRetrieval | **74.81** | 64.99 | | CodeFeedbackMT | 76.69 | **82.22** | | CodeFeedbackST | 85.21 | **90.40** | | CodeSearchNetCCRetrieval | **91.81** | 89.32 | | CodeSearchNetRetrieval | 89.24 | **90.40** | | CodeTransOceanContest | 75.95 | **87.44** | | CodeTransOceanDL | 36.06 | **41.00** | | CosQA | 42.81 | **45.23** | | StackOverflowQA | 86.61 | **93.43** | | SyntheticText2SQL | **68.27** | 63.67 | | **Average** | 70.91 | **74.12** | `LateOn-Code` wins on average, driven mostly by AppsRetrieval and the feedback/translation/QA tasks. However, `NightOwl-CodeEmbedding` wins on three tasks that map directly to its design focus: * **CodeEditSearchRetrieval** (+9.8): matching edit intents to code changes β€” `NightOwl`'s dedicated code-edit training shows here. * **CodeSearchNetCCRetrieval** (+2.5): code-to-code / similar-function retrieval. * **SyntheticText2SQL** (+4.6): NL-to-SQL retrieval. So for single-vector code-edit and code-to-code retrieval specifically, `NightOwl` is competitive with or ahead of a higher-average multi-vector model, while keeping a standard dense-vector index. (LateOn-Code scores sourced from the model's [MTEB(Code, v1) table](https://huggingface.co/lightonai/LateOn-Code).) Because the benchmark suite consists of in-domain code retrieval tasks related to the model's training distribution, these results should not be interpreted as strictly zero-shot performance. ## Base Model: the NightOwl Backbone `NightOwl-CodeEmbedding` is fine-tuned from [`Shuu12121/NightOwl`](https://huggingface.co/Shuu12121/NightOwl), a ModernBERT-style code encoder that was **pre-trained from scratch** β€” including its own tokenizer β€” rather than adapted from a general-purpose checkpoint. The whole stack, from tokenization to the pre-training objective, is controlled for code. **Code-aware tokenizer.** NightOwl uses a custom 50,368-token BPE tokenizer in which whitespace is tokenized **independently** of adjacent words, so indentation is represented by its own tokens instead of being merged into "leading-whitespace + word" pieces. In code the same identifier recurs at many indentation depths; folding whitespace into those pieces would spend large parts of the vocabulary on near-duplicate "indent + token" variants. Keeping whitespace separate avoids that waste and lets the fixed vocabulary budget cover more genuinely distinct subwords, while still representing indentation faithfully β€” which matters for whitespace-significant languages such as Python. **Two-phase pre-training with line-level masking.** NightOwl is trained with masked-language modeling (`mlm_probability = 0.3`) in two phases: * *Phase 1 β€” mixed pre-training:* standard random-token MLM over code, natural language, and technical documentation (produces `NightOwl-Pre`). * *Phase 2 β€” code-only continuation:* **line-level MLM**, where entire source-code lines are masked instead of random tokens. This aligns the pre-training objective with code search and retrieval, where the unit of meaning is closer to a line or statement than an isolated token. The recommended `NightOwl` checkpoint is this Phase-2 result. Backbone architecture (base): | Property | Value | | ------------------------------ | ----------------------------------------------------- | | Architecture | ModernBERT (alternating local/global attention, RoPE) | | Parameters | β‰ˆ150M | | `hidden_size` / layers / heads | 768 / 19 / 12 | | Vocabulary | 50,368 (custom code BPE) | | Max sequence length | 1,024 (Phase 1) β†’ 2,048 (Phase 2) | Pre-training data mixes `bigcode/starcoder2data-extras` (Kaggle notebooks, StackOverflow threads, GitHub issues, technical documentation, …) with whole-file source from `Shuu12121/github-file-programs-dataset` across the eight supported languages (Python, JavaScript, TypeScript, Java, Go, Rust, Ruby, PHP). Long examples are split into chunks so all tokens are used rather than truncated. As a raw backbone β€” before any embedding fine-tuning β€” NightOwl reaches **0.8436 average MRR** on MTEB `CodeSearchNetRetrieval` under a fixed SentenceTransformer fine-tuning protocol, ahead of CodeBERT-base (0.7944), GraphCodeBERT-base (0.8325), UniXCoder-base (0.8003), and ModernBERT-base (0.8182) evaluated the same way. `NightOwl-CodeEmbedding` builds the retrieval model described in this card on top of that backbone. ## Training The model was trained with `CachedMultipleNegativesRankingLoss` using bidirectional query-to-document and document-to-query objectives. | Property | Value | | -------------------------- | ----------------------------------------- | | Training samples | 2,534,400 | | Positives per anchor | 1 | | Negatives per anchor | 15 | | Loss | `CachedMultipleNegativesRankingLoss` | | Objective | Bidirectional retrieval training | | Hard-negative mining model | `Qwen/Qwen3-Embedding-0.6B` | | Epochs | 1 | | Learning rate | 6e-5 | | Batch size | 1024 | ### Training Data The training data is a mixture of: 1. **Public code-retrieval datasets** covering the following CoIR task families: AppsRetrieval, COIRCodeSearchNetRetrieval, CodeFeedbackMT, CodeFeedbackST, CodeSearchNetCCRetrieval, CodeSearchNetRetrieval, CodeTransOceanContest, CodeTransOceanDL, CosQA, StackOverflowQA, and SyntheticText2SQL. 2. **Custom code-comment pair data** consisting of code snippets paired with natural-language description comments across the eight supported languages (the six CodeSearchNet languages plus Rust and TypeScript). 3. **Code-edit data** derived from `commitpackft`, pairing edit intents with code changes. All datasets were constructed as hard-negative retrieval datasets: for each anchor, one positive and fifteen hard negatives were used. Hard negatives were mined with [`Qwen/Qwen3-Embedding-0.6B`](https://huggingface.co/Qwen/Qwen3-Embedding-0.6B), which retrieves semantically similar but non-matching candidates, producing negatives that are more difficult than random negatives. The mining model is used only during dataset construction and is not required at inference time. This setup is intended to improve discrimination between code snippets, programming questions, edit examples, and technically similar retrieval candidates. ### Data Decontamination To reduce benchmark contamination, the following overlaps were removed from the training data **before** training: * Overlaps between the custom code-comment pair data and the **CodeSearchNet test split** * Overlaps between the `commitpackft`-derived code-edit data and the **CodeEditSearchRetrieval** benchmark evaluation data For `CodeEditSearchRetrieval`, note that MTEB labels the evaluation split `train`. This refers only to the official split name available for the task; the evaluated examples were not included in this model's fine-tuning data. The reported score should therefore be interpreted as **in-domain generalization on held-out benchmark examples**, not as training-set performance β€” though, given the in-domain training distribution, also not as strictly zero-shot performance. ## Intended Use This model is intended for code-related retrieval tasks such as: * Natural language to code search * Code-to-code retrieval and similar function search * Code-edit retrieval (matching edit intents to code changes) * Retrieval over programming Q&A and technical questions * Local semantic code search systems * RAG systems over codebases and developer documentation Example use cases include indexing functions, snippets, programming solutions, StackOverflow-style answers, code review examples, and edit-related code examples. ## Limitations * The model is specialized for code-related retrieval and may underperform general-purpose text embedding models on unrelated natural language tasks. * Inputs longer than 1,024 tokens are truncated. This is a shorter context window than several models it competes with (e.g. the 8K+ token `F2LLM` and `granite` models), so very long files must be chunked. * MTEB(Code, v1) is largely in-domain for this model (8% zero-shot). On code domains, query styles, or languages far from the training distribution, expect lower performance than the leaderboard numbers suggest. * Performance may vary by programming language, query style, and the granularity of indexed code chunks; languages outside the eight supported languages are untested. * The model uses dense single-vector embeddings. For very fine-grained matching, rerankers or late-interaction models (such as `LateOn-Code`) may provide a higher average at the cost of a larger index and a non-standard retrieval path β€” though, as the [head-to-head](#head-to-head-vs-lateon-code) shows, single-vector `NightOwl` still leads on code-edit and code-to-code retrieval. ## Recommended Indexing Settings Encode both queries and documents with normalized embeddings: ```python embeddings = model.encode(texts, normalize_embeddings=True) ``` With normalized embeddings, dot product is equivalent to cosine similarity. For codebase search, indexing function-level or class-level chunks is usually recommended. Very long files may exceed the 1,024-token context limit and should be split into smaller semantic chunks. ## Citation If you use this model, please cite it together with the base model and Sentence Transformers. ```bibtex @misc{nightowl_codeembedding, title = {NightOwl-CodeEmbedding}, author = {Shuu12121}, year = {2026}, publisher = {Hugging Face}, url = {https://huggingface.co/Shuu12121/NightOwl-CodeEmbedding} } ```