|
|
--- |
|
|
tags: |
|
|
- ColBERT |
|
|
- PyLate |
|
|
- sentence-transformers |
|
|
- sentence-similarity |
|
|
- feature-extraction |
|
|
- generated_from_trainer |
|
|
- dataset_size:2117771 |
|
|
- loss:Contrastive |
|
|
- code |
|
|
- embeddings |
|
|
- retrieval |
|
|
- code search |
|
|
datasets: |
|
|
- lightonai/nv-embed-supervised-distill-dedup-code |
|
|
pipeline_tag: sentence-similarity |
|
|
library_name: PyLate |
|
|
license: apache-2.0 |
|
|
language: |
|
|
- en |
|
|
- code |
|
|
metrics: |
|
|
- MaxSim_accuracy@1 |
|
|
- MaxSim_accuracy@3 |
|
|
- MaxSim_accuracy@5 |
|
|
- MaxSim_accuracy@10 |
|
|
- MaxSim_precision@1 |
|
|
- MaxSim_precision@3 |
|
|
- MaxSim_precision@5 |
|
|
- MaxSim_precision@10 |
|
|
- MaxSim_recall@1 |
|
|
- MaxSim_recall@3 |
|
|
- MaxSim_recall@5 |
|
|
- MaxSim_recall@10 |
|
|
- MaxSim_ndcg@10 |
|
|
- MaxSim_mrr@10 |
|
|
- MaxSim_map@100 |
|
|
model-index: |
|
|
- name: PyLate |
|
|
results: |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: CodeSearchNetPython |
|
|
type: CodeSearchNetPython |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.855 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.958 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.972 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.98 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.855 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.31933333333333325 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.19440000000000004 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09800000000000002 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.855 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.958 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.972 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.98 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.9243945806879859 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.9057539682539687 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.9064418634729382 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: CodeSearchNetJavascript |
|
|
type: CodeSearchNetJavascript |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.707 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.815 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.845 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.877 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.707 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.2716666666666666 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.169 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.08770000000000001 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.707 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.815 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.845 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.877 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.7937015046112885 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.7667960317460317 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.7695522566859624 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: CodeSearchNetGo |
|
|
type: CodeSearchNetGo |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.92 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.978 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.987 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.991 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.92 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.32599999999999996 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.19740000000000005 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09910000000000002 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.92 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.978 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.987 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.991 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.9607370553228975 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.9504940476190477 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.9507803176498298 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: CodeSearchNetRuby |
|
|
type: CodeSearchNetRuby |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.737 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.87 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.899 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.921 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.737 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.2899999999999999 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.17980000000000002 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09210000000000003 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.737 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.87 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.899 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.921 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.8356874462458972 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.8076091269841275 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.8095189889370982 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: CodeSearchNetJava |
|
|
type: CodeSearchNetJava |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.755 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.914 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.937 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.951 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.755 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.30466666666666664 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.18740000000000004 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09510000000000002 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.755 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.914 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.937 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.951 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.8654697550394161 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.836704761904762 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.8379490131977781 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: py-late-information-retrieval |
|
|
name: Py Late Information Retrieval |
|
|
dataset: |
|
|
name: CodeSearchNetPhp |
|
|
type: CodeSearchNetPhp |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.802 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.91 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.932 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.953 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.802 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.30333333333333323 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.18640000000000004 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09530000000000001 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.802 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.91 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.932 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.953 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.8823849310511876 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.8592019841269843 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.8600229577124362 |
|
|
name: Maxsim Map@100 |
|
|
- task: |
|
|
type: code-search-network |
|
|
name: Code Search Network |
|
|
dataset: |
|
|
name: CodeSearchNet mean |
|
|
type: CodeSearchNet_mean |
|
|
metrics: |
|
|
- type: MaxSim_accuracy@1 |
|
|
value: 0.7959999999999999 |
|
|
name: Maxsim Accuracy@1 |
|
|
- type: MaxSim_accuracy@3 |
|
|
value: 0.9075000000000001 |
|
|
name: Maxsim Accuracy@3 |
|
|
- type: MaxSim_accuracy@5 |
|
|
value: 0.9286666666666666 |
|
|
name: Maxsim Accuracy@5 |
|
|
- type: MaxSim_accuracy@10 |
|
|
value: 0.9455 |
|
|
name: Maxsim Accuracy@10 |
|
|
- type: MaxSim_precision@1 |
|
|
value: 0.7959999999999999 |
|
|
name: Maxsim Precision@1 |
|
|
- type: MaxSim_precision@3 |
|
|
value: 0.30249999999999994 |
|
|
name: Maxsim Precision@3 |
|
|
- type: MaxSim_precision@5 |
|
|
value: 0.1857333333333334 |
|
|
name: Maxsim Precision@5 |
|
|
- type: MaxSim_precision@10 |
|
|
value: 0.09455000000000002 |
|
|
name: Maxsim Precision@10 |
|
|
- type: MaxSim_recall@1 |
|
|
value: 0.7959999999999999 |
|
|
name: Maxsim Recall@1 |
|
|
- type: MaxSim_recall@3 |
|
|
value: 0.9075000000000001 |
|
|
name: Maxsim Recall@3 |
|
|
- type: MaxSim_recall@5 |
|
|
value: 0.9286666666666666 |
|
|
name: Maxsim Recall@5 |
|
|
- type: MaxSim_recall@10 |
|
|
value: 0.9455 |
|
|
name: Maxsim Recall@10 |
|
|
- type: MaxSim_ndcg@10 |
|
|
value: 0.877062545493112 |
|
|
name: Maxsim Ndcg@10 |
|
|
- type: MaxSim_mrr@10 |
|
|
value: 0.8544266534391536 |
|
|
name: Maxsim Mrr@10 |
|
|
- type: MaxSim_map@100 |
|
|
value: 0.8557108996093405 |
|
|
name: Maxsim Map@100 |
|
|
--- |
|
|
|
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/609bbe2f4932693ca2009d6a/BWfClY8hoQIS_Qf9rVa__.png" width="700" height="auto"> |
|
|
|
|
|
# LateOn-Code |
|
|
|
|
|
The [LateOn-Code collection](https://huggingface.co/collections/lightonai/lateon-code) is composed of [PyLate](https://github.com/lightonai/pylate) models optimized for code retrieval. These late interaction models are first pre-trained following the methodology of [CoRNStack](https://arxiv.org/pdf/2412.01007). These pre-trained models are then further fine-tuned on train sets of CoIR using the [nv-retriever](https://arxiv.org/abs/2407.15831) methodology to mine hard negatives while preventing false negatives. |
|
|
|
|
|
We started from the two best ColBERT models on the BEIR benchmark for their respective sizes. The first one, [LateOn-Code](https://huggingface.co/lightonai/LateOn-Code) is based on in-house LateOn model, a new version of [GTE-ModernColBERT-v1](https://huggingface.co/lightonai/GTE-ModernColBERT-v1) built on ModernBERT-base (also developed at LightOn). This version underwent significantly deeper training, crossing the 57 mark on BEIR, almost a 2.5-point improvement and is thus SOTA by a large margin. We'll release this base model along with training data and boilerplates in the near future, so stay tuned\! The second, [LateOn-Code-edge](https://huggingface.co/lightonai/LateOn-Code-edge) is a smaller model based on the [edge-colbert model family from mixedbread](https://www.mixedbread.com/blog/edge-v0), using the [smallest variant (Ettin-17M)](https://huggingface.co/mixedbread-ai/mxbai-edge-colbert-v0-17m) for maximum efficiency. For more details on the training setup, please refer to our [blogpost](https://huggingface.co/blog/lightonai/colgrep-lateon-code). |
|
|
|
|
|
The original [CoRNStack data](https://huggingface.co/collections/nomic-ai/cornstack) in a format compatible with PyLate can be found [here](https://huggingface.co/datasets/lightonai/cornstack) while the fine-tuning data can be found [here](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code). Training boilerplates can be found [here in the PyLate repository](https://github.com/lightonai/pylate/tree/main/examples/train/lateon_code) |
|
|
|
|
|
## MTEB (Code, v1) benchmark results |
|
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/609bbe2f4932693ca2009d6a/Dw9JADjB5tdiSsv4wiDbe.png" width="1000" height="auto"> |
|
|
|
|
|
Pre-trained models achieve very competitive results as the 17M model outperforms the very strong granite-embedding-small-english-r2 by an average of 1.7. This is truly impressive, as the granite model is almost three times bigger (17M vs 48M), but is also a beast on its own in the <100M parameters range. It also outperforms the larger granite variant (149M). The larger version nicely scales by improving over the performance of its little sibling by 6.5 on average. |
|
|
|
|
|
Although the pre-training results are already very impressive given that they are mostly out-of-domain, running a proper fine-tuning using the training data of CoIR significantly boost the performance of the models. Notably, the 17M model increases from 57.50 to 66.64 (+9.14), getting pretty close to EmbeddingGemma-300M while being 17 times smaller. The larger one increases from 63.77 to 74.12 (+10.35), strongly outperforming EmbeddingGemma-300M and getting closer to strong LLM models such as Qwen3-Embedding-0.6B and C2LLM-0.5B while being much smaller. |
|
|
|
|
|
| Model | Params | Type | **Avg** | Apps | COIR CSNet | CodeEdit | CodeFB MT | CodeFB ST | CSNet CC | CSNet | CodeTrans Contest | CodeTrans DL | CosQA | StackOF QA | Synth T2SQL | |
|
|
|:---|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:|:---:| |
|
|
| **Baseline** | | | | | | | | | | | | | | | | |
|
|
| BM25 | - | Lexical | 44.41 | 4.76 | 40.86 | 49.85 | 59.19 | 68.15 | 53.97 | 60.01 | 47.78 | 34.42 | 18.75 | 70.26 | 24.94 | |
|
|
| **Small (≤50M)** | | | | | | | | | | | | | | | | |
|
|
| granite-embedding-small-english-r2 | 47M | Single vector | 55.84 | 13.54 | 60.46 | 57.16 | 52.19 | 76.85 | 48.42 | 78.28 | **77.63** | 33.63 | 35.58 | **90.04** | 46.33 | |
|
|
| [LateOn-Code-edge-pretrain](https://huggingface.co/lightonai/LateOn-Code-edge-pretrain) | 17M | Multi vector | 57.50 | 10.81 | 73.78 | 62.07 | 51.92 | 76.65 | 63.22 | **88.03** | 71.31 | 33.16 | 30.53 | 74.63 | 53.83 | |
|
|
| [LateOn-Code-edge](https://huggingface.co/lightonai/LateOn-Code-edge) | 17M | Multi vector | **66.64** | **26.22** | **81.60** | **62.21** | **74.25** | **87.12** | **79.26** | 87.85 | 75.36 | **37.08** | **40.54** | 85.63 | **62.57** | |
|
|
| *Δ (fine-tune - pretrain)* | | | *+9.14* | *+15.41* | *+7.82* | *+0.14* | *+22.33* | *+10.47* | *+16.04* | *-0.18* | *+4.05* | *+3.92* | *+10.01* | *+11.00* | *+8.74* | |
|
|
| **Medium (100M–300M)** | | | | | | | | | | | | | | | | |
|
|
| granite-embedding-english-r2 | 149M | Single vector | 57.22 | 13.96 | 64.65 | 59.35 | 52.54 | 77.18 | 47.67 | 80.79 | 77.07 | 35.03 | 37.01 | 91.80 | 49.55 | |
|
|
| CodeRankEmbed | 137M | Single vector | 60.47 | 23.45 | 83.20 | 59.98 | 42.61 | 78.10 | 68.89 | 89.50 | 66.43 | 34.49 | 35.17 | 80.53 | 63.27 | |
|
|
| GTE-ModernBERT | 149M | Single vector | 71.66 | 57.72 | 83.10 | 55.83 | **86.15** | 86.00 | **93.61** | 88.76 | 72.35 | 37.27 | 43.36 | 91.14 | **64.61** | |
|
|
| embeddinggemma-300m | 300M | Single vector | 68.76 | **<u>84.39</u>** | 75.54 | 62.10 | 51.42 | 80.26 | 73.71 | 90.15 | 85.51 | 33.52 | 43.60 | 86.47 | 58.42 | |
|
|
| [LateOn-Code-pretrain](https://huggingface.co/lightonai/LateOn-Code-pretrain) | 149M | Multi vector | 63.77 | 23.09 | 80.27 | **68.74** | 50.21 | 82.66 | 71.47 | **<u>91.05</u>** | 82.20 | 34.46 | 34.15 | 85.61 | 61.34 | |
|
|
| [LateOn-Code](https://huggingface.co/lightonai/LateOn-Code) | 149M | Multi vector | **74.12** | 54.76 | **86.57** | 64.99 | 82.22 | **<u>90.40</u>** | 89.32 | 90.40 | **<u>87.44</u>** | **<u>41.00</u>** | **<u>45.23</u>** | **<u>93.43</u>** | 63.67 | |
|
|
| *Δ (fine-tune - pretrain)* | | | *+10.35* | *+31.67* | *+6.30* | *-3.75* | *+32.01* | *+7.74* | *+17.85* | *-0.65* | *+5.24* | *+6.54* | *+11.08* | *+7.82* | *+2.33* | |
|
|
| **Large (≥500M)** | | | | | | | | | | | | | | | | |
|
|
| C2LLM-0.5B | 500M | Single vector | **<u>75.46</u>** | 61.02 | **<u>86.71</u>** | **<u>71.39</u>** | **<u>92.29</u>** | 88.63 | **<u>96.29</u>** | 89.20 | 84.27 | **33.99** | **38.30** | 89.40 | 74.08 | |
|
|
| Qwen3-Embedding-0.6B | 600M | Single vector | 75.42 | **75.34** | 84.69 | 64.42 | 90.82 | **86.39** | 91.72 | **91.01** | **86.05** | 31.36 | 36.48 | **89.99** | **<u>76.74</u>** | |
|
|
|
|
|
Best result across all sizes is <u>underlined</u>. Best within each size category is **bolded**. |
|
|
|
|
|
# Colgrep |
|
|
|
|
|
The LateOn-Code family model can easily be used within ColGrep, an easy-to-use search tool that give their powerful search capabilities to coding agent. It has been designed to extend grep capabilities to get the best of both world and is very effective to enhance the quality of the answer while diminishing answer time and tokens consumption. Given the performance of the very light-weight 17M model, it can easily run quickly on any computer. |
|
|
|
|
|
## Install ColGrep |
|
|
```bash |
|
|
# macOS / Linux |
|
|
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/lightonai/next-plaid/releases/latest/download/colgrep-installer.sh | sh |
|
|
|
|
|
# Windows (PowerShell) |
|
|
powershell -c "irm https://github.com/lightonai/next-plaid/releases/latest/download/colgrep-installer.ps1 | iex" |
|
|
``` |
|
|
|
|
|
## Search |
|
|
|
|
|
```bash |
|
|
# Semantic search — find code by meaning |
|
|
colgrep "function that retries HTTP requests" |
|
|
|
|
|
# Regex search |
|
|
colgrep -e "async fn\s+\w+" |
|
|
|
|
|
# Hybrid — regex narrows candidates, semantics ranks them |
|
|
colgrep -e "Result<" "error handling" --include="*.rs" |
|
|
``` |
|
|
|
|
|
## Install for Claude Code |
|
|
|
|
|
```bash |
|
|
colgrep --install-claude-code |
|
|
``` |
|
|
|
|
|
## Choose a Model |
|
|
|
|
|
```bash |
|
|
# Set the model |
|
|
colgrep set-model lightonai/LateOn-Code # default: lightonai/LateOn-Code-edge |
|
|
``` |
|
|
For more information about ColGrep, please refer to the [official documentation](https://github.com/lightonai/next-plaid/tree/main/colgrep) |
|
|
|
|
|
|
|
|
# PyLate |
|
|
|
|
|
This is a [PyLate](https://github.com/lightonai/pylate) model finetuned from [lightonai/LateOn-Code-edge-pretrain](https://huggingface.co/lightonai/LateOn-Code-edge-pretrain) on the [apps](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [synthetictext2sql](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [cosqa](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [codefeedbackst](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [codefeedbackmt](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [stackoverflowqa](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [codetranscontest](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [codetransdl](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_go](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_java](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_javascript](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_php](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_python](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_ruby](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_ccr_go](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_ccr_java](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_ccr_javascript](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_ccr_php](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code), [CodeSearchNet_ccr_python](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) and [CodeSearchNet_ccr_ruby](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) datasets. It maps sentences & paragraphs to sequences of 48-dimensional dense vectors and can be used for semantic textual similarity using the MaxSim operator. |
|
|
|
|
|
## Model Details |
|
|
|
|
|
### Model Description |
|
|
- **Model Type:** PyLate model |
|
|
<!-- - **Base model:** [Unknown](https://huggingface.co/unknown) --> |
|
|
- **Document Length:** 2048 tokens |
|
|
- **Query Length:** 256 tokens |
|
|
- **Output Dimensionality:** 48 tokens |
|
|
- **Similarity Function:** MaxSim |
|
|
- **Training Datasets:** |
|
|
- [apps](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [synthetictext2sql](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [cosqa](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [codefeedbackst](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [codefeedbackmt](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [stackoverflowqa](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [codetranscontest](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [codetransdl](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_go](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_java](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_javascript](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_php](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_python](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ruby](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ccr_go](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ccr_java](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ccr_javascript](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ccr_php](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ccr_python](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- [CodeSearchNet_ccr_ruby](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) |
|
|
- **Language:** English, code |
|
|
- **License:** Apache 2.0 |
|
|
|
|
|
### Model Sources |
|
|
|
|
|
- **Documentation:** [PyLate Documentation](https://lightonai.github.io/pylate/) |
|
|
- **Repository:** [PyLate on GitHub](https://github.com/lightonai/pylate) |
|
|
- **Hugging Face:** [PyLate models on Hugging Face](https://huggingface.co/models?library=PyLate) |
|
|
|
|
|
### Full Model Architecture |
|
|
|
|
|
``` |
|
|
ColBERT( |
|
|
(0): Transformer({'max_seq_length': 2047, 'do_lower_case': True, 'architecture': 'ModernBertModel'}) |
|
|
(1): Dense({'in_features': 256, 'out_features': 512, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False}) |
|
|
(2): Dense({'in_features': 512, 'out_features': 48, 'bias': False, 'activation_function': 'torch.nn.modules.linear.Identity', 'use_residual': False}) |
|
|
) |
|
|
``` |
|
|
|
|
|
## Usage |
|
|
First install the PyLate library: |
|
|
|
|
|
```bash |
|
|
pip install -U pylate |
|
|
``` |
|
|
|
|
|
### Retrieval |
|
|
|
|
|
Use this model with PyLate to index and retrieve documents. The index uses [FastPLAID](https://github.com/lightonai/fast-plaid) for efficient similarity search. |
|
|
|
|
|
#### Indexing documents |
|
|
|
|
|
Load the ColBERT model and initialize the PLAID index, then encode and index your documents: |
|
|
|
|
|
```python |
|
|
from pylate import indexes, models, retrieve |
|
|
|
|
|
# Step 1: Load the ColBERT model |
|
|
model = models.ColBERT( |
|
|
model_name_or_path="pylate_model_id", |
|
|
) |
|
|
|
|
|
# Step 2: Initialize the PLAID index |
|
|
index = indexes.PLAID( |
|
|
index_folder="pylate-index", |
|
|
index_name="index", |
|
|
override=True, # This overwrites the existing index if any |
|
|
) |
|
|
|
|
|
# Step 3: Encode the documents |
|
|
documents_ids = ["1", "2", "3"] |
|
|
documents = ["document 1 text", "document 2 text", "document 3 text"] |
|
|
|
|
|
documents_embeddings = model.encode( |
|
|
documents, |
|
|
batch_size=32, |
|
|
is_query=False, # Ensure that it is set to False to indicate that these are documents, not queries |
|
|
show_progress_bar=True, |
|
|
) |
|
|
|
|
|
# Step 4: Add document embeddings to the index by providing embeddings and corresponding ids |
|
|
index.add_documents( |
|
|
documents_ids=documents_ids, |
|
|
documents_embeddings=documents_embeddings, |
|
|
) |
|
|
``` |
|
|
|
|
|
Note that you do not have to recreate the index and encode the documents every time. Once you have created an index and added the documents, you can re-use the index later by loading it: |
|
|
|
|
|
```python |
|
|
# To load an index, simply instantiate it with the correct folder/name and without overriding it |
|
|
index = indexes.PLAID( |
|
|
index_folder="pylate-index", |
|
|
index_name="index", |
|
|
) |
|
|
``` |
|
|
|
|
|
#### Retrieving top-k documents for queries |
|
|
|
|
|
Once the documents are indexed, you can retrieve the top-k most relevant documents for a given set of queries. |
|
|
To do so, initialize the ColBERT retriever with the index you want to search in, encode the queries and then retrieve the top-k documents to get the top matches ids and relevance scores: |
|
|
|
|
|
```python |
|
|
# Step 1: Initialize the ColBERT retriever |
|
|
retriever = retrieve.ColBERT(index=index) |
|
|
|
|
|
# Step 2: Encode the queries |
|
|
queries_embeddings = model.encode( |
|
|
["query for document 3", "query for document 1"], |
|
|
batch_size=32, |
|
|
is_query=True, # # Ensure that it is set to False to indicate that these are queries |
|
|
show_progress_bar=True, |
|
|
) |
|
|
|
|
|
# Step 3: Retrieve top-k documents |
|
|
scores = retriever.retrieve( |
|
|
queries_embeddings=queries_embeddings, |
|
|
k=10, # Retrieve the top 10 matches for each query |
|
|
) |
|
|
``` |
|
|
|
|
|
### Reranking |
|
|
If you only want to use the ColBERT model to perform reranking on top of your first-stage retrieval pipeline without building an index, you can simply use rank function and pass the queries and documents to rerank: |
|
|
|
|
|
```python |
|
|
from pylate import rank, models |
|
|
|
|
|
queries = [ |
|
|
"query A", |
|
|
"query B", |
|
|
] |
|
|
|
|
|
documents = [ |
|
|
["document A", "document B"], |
|
|
["document 1", "document C", "document B"], |
|
|
] |
|
|
|
|
|
documents_ids = [ |
|
|
[1, 2], |
|
|
[1, 3, 2], |
|
|
] |
|
|
|
|
|
model = models.ColBERT( |
|
|
model_name_or_path="pylate_model_id", |
|
|
) |
|
|
|
|
|
queries_embeddings = model.encode( |
|
|
queries, |
|
|
is_query=True, |
|
|
) |
|
|
|
|
|
documents_embeddings = model.encode( |
|
|
documents, |
|
|
is_query=False, |
|
|
) |
|
|
|
|
|
reranked_documents = rank.rerank( |
|
|
documents_ids=documents_ids, |
|
|
queries_embeddings=queries_embeddings, |
|
|
documents_embeddings=documents_embeddings, |
|
|
) |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
### Direct Usage (Transformers) |
|
|
|
|
|
<details><summary>Click to see the direct usage in Transformers</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Downstream Usage (Sentence Transformers) |
|
|
|
|
|
You can finetune this model on your own dataset. |
|
|
|
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
</details> |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Out-of-Scope Use |
|
|
|
|
|
*List how the model may foreseeably be misused and address what users ought not to do with the model.* |
|
|
--> |
|
|
|
|
|
## Evaluation |
|
|
|
|
|
### Metrics |
|
|
|
|
|
#### Py Late Information Retrieval |
|
|
* Dataset: `['CodeSearchNetPython', 'CodeSearchNetJavascript', 'CodeSearchNetGo', 'CodeSearchNetRuby', 'CodeSearchNetJava', 'CodeSearchNetPhp']` |
|
|
* Evaluated with `pylate.evaluation.pylate_information_retrieval_evaluator.PyLateInformationRetrievalEvaluator` |
|
|
|
|
|
| Metric | CodeSearchNetPython | CodeSearchNetJavascript | CodeSearchNetGo | CodeSearchNetRuby | CodeSearchNetJava | CodeSearchNetPhp | |
|
|
|:--------------------|:--------------------|:------------------------|:----------------|:------------------|:------------------|:-----------------| |
|
|
| MaxSim_accuracy@1 | 0.855 | 0.707 | 0.92 | 0.737 | 0.755 | 0.802 | |
|
|
| MaxSim_accuracy@3 | 0.958 | 0.815 | 0.978 | 0.87 | 0.914 | 0.91 | |
|
|
| MaxSim_accuracy@5 | 0.972 | 0.845 | 0.987 | 0.899 | 0.937 | 0.932 | |
|
|
| MaxSim_accuracy@10 | 0.98 | 0.877 | 0.991 | 0.921 | 0.951 | 0.953 | |
|
|
| MaxSim_precision@1 | 0.855 | 0.707 | 0.92 | 0.737 | 0.755 | 0.802 | |
|
|
| MaxSim_precision@3 | 0.3193 | 0.2717 | 0.326 | 0.29 | 0.3047 | 0.3033 | |
|
|
| MaxSim_precision@5 | 0.1944 | 0.169 | 0.1974 | 0.1798 | 0.1874 | 0.1864 | |
|
|
| MaxSim_precision@10 | 0.098 | 0.0877 | 0.0991 | 0.0921 | 0.0951 | 0.0953 | |
|
|
| MaxSim_recall@1 | 0.855 | 0.707 | 0.92 | 0.737 | 0.755 | 0.802 | |
|
|
| MaxSim_recall@3 | 0.958 | 0.815 | 0.978 | 0.87 | 0.914 | 0.91 | |
|
|
| MaxSim_recall@5 | 0.972 | 0.845 | 0.987 | 0.899 | 0.937 | 0.932 | |
|
|
| MaxSim_recall@10 | 0.98 | 0.877 | 0.991 | 0.921 | 0.951 | 0.953 | |
|
|
| **MaxSim_ndcg@10** | **0.9244** | **0.7937** | **0.9607** | **0.8357** | **0.8655** | **0.8824** | |
|
|
| MaxSim_mrr@10 | 0.9058 | 0.7668 | 0.9505 | 0.8076 | 0.8367 | 0.8592 | |
|
|
| MaxSim_map@100 | 0.9064 | 0.7696 | 0.9508 | 0.8095 | 0.8379 | 0.86 | |
|
|
|
|
|
#### Code Search Network |
|
|
* Dataset: `CodeSearchNet_mean` |
|
|
* Evaluated with `pylate.evaluation.code_search_network_evaluator.CodeSearchNetworkEvaluator` |
|
|
|
|
|
| Metric | Value | |
|
|
|:--------------------|:-----------| |
|
|
| MaxSim_accuracy@1 | 0.796 | |
|
|
| MaxSim_accuracy@3 | 0.9075 | |
|
|
| MaxSim_accuracy@5 | 0.9287 | |
|
|
| MaxSim_accuracy@10 | 0.9455 | |
|
|
| MaxSim_precision@1 | 0.796 | |
|
|
| MaxSim_precision@3 | 0.3025 | |
|
|
| MaxSim_precision@5 | 0.1857 | |
|
|
| MaxSim_precision@10 | 0.0946 | |
|
|
| MaxSim_recall@1 | 0.796 | |
|
|
| MaxSim_recall@3 | 0.9075 | |
|
|
| MaxSim_recall@5 | 0.9287 | |
|
|
| MaxSim_recall@10 | 0.9455 | |
|
|
| **MaxSim_ndcg@10** | **0.8771** | |
|
|
| MaxSim_mrr@10 | 0.8544 | |
|
|
| MaxSim_map@100 | 0.8557 | |
|
|
|
|
|
<!-- |
|
|
## Bias, Risks and Limitations |
|
|
|
|
|
*What are the known or foreseeable issues stemming from this model? You could also flag here known failure cases or weaknesses of the model.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
### Recommendations |
|
|
|
|
|
*What are recommendations with respect to the foreseeable issues? For example, filtering explicit content.* |
|
|
--> |
|
|
|
|
|
## Training Details |
|
|
|
|
|
### Training Datasets |
|
|
|
|
|
#### apps |
|
|
|
|
|
* Dataset: [apps](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 4,985 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'Polycarp has $n$ different binary words. A word called binary if it contains only charact...` | `{'document': "for _ in range(int(input())):\n n = int(input())\n mass = []\n zo = 0\n oz...` | `{'document': "t=int(input())\nfor _ in range(t):\n n=int(input())\n l=list(map(int,input().split()))...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### synthetictext2sql |
|
|
|
|
|
* Dataset: [synthetictext2sql](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 99,996 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'What is the total volume of timber sold by each salesperson, sorted by salesperson?', 'qu...` | `{'document': 'SELECT salesperson_id, name, SUM(volume) as total_volume FROM timber_sales JOIN salesp...` | `{'document': 'SELECT salesperson_id, SUM(volume) as total_volume FROM timber_sales JOIN salesperson ...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### cosqa |
|
|
|
|
|
* Dataset: [cosqa](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 9,018 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': '1d array in char datatype in python', 'query_id': 9}` | `{'document': 'def _convert_to_array(array_like, dtype):\n """\n Convert Matrix attribu...` | `{'document': 'def astype(array, y):\n """A functional form of the `astype` method.\n\n Args:\n ...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### codefeedbackst |
|
|
|
|
|
* Dataset: [codefeedbackst](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 125,124 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'You are tasked with implementing a Python class that extends a base class and overrides i...` | `{'document': '```python\nclass TestsslFinding(VSFinding):\n def process_finding(self, finding):\n...` | `{'document': '```python\nfrom googlecloudsdk.calliope import base\nfrom googlecloudsdk.api_lib.sql i...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### codefeedbackmt |
|
|
|
|
|
* Dataset: [codefeedbackmt](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 52,941 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': "'user': Embark on a comprehensive journey through the intricate realm of quantum computin...` | `{'document': "Regrettably, there are no standard Python libraries available for quantum computing th...` | `{'document': "The provided code block constructs a quantum circuit with a Hadamard gate (which allow...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### stackoverflowqa |
|
|
|
|
|
* Dataset: [stackoverflowqa](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 13,934 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'sphinxsearch-0.9 in mediawiki-1.32.0 error 2019/01/14 12:04:51 [error] 21549#21549: *3558...` | `{'document': 'The SearchDatabase class that SphinxSearch extends was changed from REL1_31 to REL1_32...` | `{'document': 'I was running MediaWiki 1.16.0. I upgraded to MediaWiki 1.16.2 and this resolved the ...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### codetranscontest |
|
|
|
|
|
* Dataset: [codetranscontest](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 561 training samples |
|
|
* Approximate statistics based on the first 561 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'Julia set from __future__ import division\n\ncX = -0.7\ncY = 0.27015\nmaxIter = 300\n\nde...` | `{'document': '#include <windows.h>\n#include <string>\n#include <complex>\n\nconst int BMP_SIZE = 60...` | `{'document': '#include <windows.h>\n#include <ctime>\n#include <string>\n\nconst int BMP_SIZE = 600,...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### codetransdl |
|
|
|
|
|
* Dataset: [codetransdl](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [68d15dc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/68d15dc382d1ab682bb3435318eece8d49949b9f) |
|
|
* Size: 564 training samples |
|
|
* Approximate statistics based on the first 564 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'x = tf.range(12)\ntf.size(x)\nX = tf.reshape(x, (3, 4))\ntf.zeros((2, 3, 4))\ntf.ones((2,...` | `{'document': "x = paddle.arange(12)\nx.numel()\nX = paddle.reshape(x, (3, 4))\npaddle.zeros((2, 3, 4...` | `{'document': 'x = torch.arange(12)\nx.numel()\nX = x.reshape(3, 4)\ntorch.zeros((2, 3, 4))\ntorch.on...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_go |
|
|
|
|
|
* Dataset: [CodeSearchNet_go](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 166,972 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'getStringValue func getStringValue(b []rune) (int, error) {\n\tif b[0] != \'"\' {\n\t\tre...` | `{'document': '// getStringValue will return a quoted string and the amount\n// of bytes read\n//\n//...` | `{'document': '// stringValue returns the string value of string literal e.', 'document_id': 18454}` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_java |
|
|
|
|
|
* Dataset: [CodeSearchNet_java](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 162,773 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'SCryptUtil.check public static boolean check(String passwd, String hashed) {\n try...` | `{'document': 'Compare the supplied plaintext password to a hashed password.\n\n@param passwd Plai...` | `{'document': 'Compute the the hash value for the String.\n\n@param passwd\nthe password String\n@ret...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_javascript |
|
|
|
|
|
* Dataset: [CodeSearchNet_javascript](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 56,734 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'function (state, action) {\n return _.defaults({\n isValidating: action.isValidat...` | `{'document': 'Update is validating result\n@param {State} state - state to update\n@param {Action} a...` | `{'document': 'Updates state with newsletter settings submit error\nHolds information only for latest...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_php |
|
|
|
|
|
* Dataset: [CodeSearchNet_php](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 240,327 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'BreadcrumbCollection.addOne public function addOne($title, $url, array $data = [])\n {...` | `{'document': 'Add a breadcrumb item to collection.\n\n@param string $title\n@param string $url\n...` | `{'document': 'Add a breadcrumb to the collection.\n\n@param string $title\n@param string $url\n@...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_python |
|
|
|
|
|
* Dataset: [CodeSearchNet_python](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 251,063 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'AbstractElement.settext def settext(self, text, cls=\'current\'):\n """Set the tex...` | `{'document': 'Set the text for this element.\n\n Arguments:\n text (str): The text...` | `{'document': 'Set text value as sole Text child node of element; any existing\n Text nodes ar...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ruby |
|
|
|
|
|
* Dataset: [CodeSearchNet_ruby](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 24,731 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'CelluloidPubsub.Reactor.handle_parsed_websocket_message def handle_parsed_websocket_messa...` | `{'document': 'method that checks if the data is a Hash\n\n if the data is a hash then will stringify...` | `{'document': "If the message can be parsed into a Hash it will respond to the reactor's websocket co...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ccr_go |
|
|
|
|
|
* Dataset: [CodeSearchNet_ccr_go](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 167,278 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'getStringValue func getStringValue(b []rune) (int, error) {\n\tif b[0] != \'"\' {\n\t\tre...` | `{'document': ' nil {\n\t\t\t\treturn 0, err\n\t\t\t}\n\n\t\t\tb[i-1] = c\n\t\t\tb = append(b[:i], b[...` | `{'document': '\t\t\treturn 0, "", fmt.Errorf("nothing following final escape in %q", s)\n\t\t\t}\n\t...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ccr_java |
|
|
|
|
|
* Dataset: [CodeSearchNet_ccr_java](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 164,900 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'SCryptUtil.check public static boolean check(String passwd, String hashed) {\n try...` | `{'document': ' int r = (int) params >> 8 & 0xff;\n int p = (int) params & 0...` | `{'document': '\n } catch (Exception e) {\n throw new IllegalStateException("Validity checks ...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ccr_javascript |
|
|
|
|
|
* Dataset: [CodeSearchNet_ccr_javascript](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 58,017 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'function (state, action) {\n return _.defaults({\n ', 'query_id': 0}` | `{'document': ' isValidating: action.isValidating,\n lastAction: IS_VALIDATING\n }, state)\n ...` | `{'document': ' baz: action.payload,\n };\n default:\n return state;\n }\n}', 'd...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ccr_php |
|
|
|
|
|
* Dataset: [CodeSearchNet_ccr_php](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 241,177 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'BreadcrumbCollection.addOne public function addOne($title, $url, array $data = [])\n {...` | `{'document': ' return $this->addBreadcrumb(\n BreadcrumbItem::make($title, $url, $data)\n...` | `{'document': ' $this->breadcrumbs->push(new Breadcrumb($title, $url));\n }', 'document_id': 135...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ccr_python |
|
|
|
|
|
* Dataset: [CodeSearchNet_ccr_python](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 251,758 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'AbstractElement.settext def settext(self, text, cls=\'current\'):\n """Set the tex...` | `{'document': ' only one text content element of each class associated with the element.\n """...` | `{'document': '\n Jython and has been superseded by the \'ast\' module in Python 2.6 and\n ...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
#### CodeSearchNet_ccr_ruby |
|
|
|
|
|
* Dataset: [CodeSearchNet_ccr_ruby](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code) at [9f89bdc](https://huggingface.co/datasets/lightonai/nv-embed-supervised-distill-dedup-code/tree/9f89bdc63567c5d86771d9e92c024625d59e13b0) |
|
|
* Size: 24,918 training samples |
|
|
* Approximate statistics based on the first 1000 samples: |
|
|
| | query | positive | negative_0 | negative_1 | negative_2 | negative_3 | negative_4 | negative_5 | negative_6 | negative_7 | negative_8 | negative_9 | negative_10 | negative_11 | negative_12 | negative_13 | negative_14 | negative_15 | negative_16 | negative_17 | negative_18 | negative_19 | negative_20 | negative_21 | negative_22 | negative_23 | negative_24 | negative_25 | negative_26 | negative_27 | negative_28 | negative_29 | negative_30 | negative_31 | negative_32 | negative_33 | negative_34 | negative_35 | negative_36 | negative_37 | negative_38 | negative_39 | negative_40 | negative_41 | negative_42 | negative_43 | negative_44 | negative_45 | negative_46 | negative_47 | negative_48 | negative_49 | |
|
|
|:--------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------|:-------------------| |
|
|
| type | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | dict | |
|
|
| details | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | |
|
|
* Samples: |
|
|
| query | positive | negative_0 | |
|
|
|:------|:---------|:-----------| |
|
|
| `{'query': 'CelluloidPubsub.Reactor.handle_parsed_websocket_message def handle_parsed_websocket_messa...` | `{'document': " delegate_action(data) if data['client_action'].present?\n else\n han...` | `{'document': ' elsif data[\'method\']\n # RPC notice.\n event = { name: data[\'method\'], ...` | |
|
|
* Loss: `pylate.losses.contrastive.Contrastive` |
|
|
|
|
|
### Training Hyperparameters |
|
|
#### Non-Default Hyperparameters |
|
|
|
|
|
- `eval_strategy`: steps |
|
|
- `per_device_train_batch_size`: 128 |
|
|
- `per_device_eval_batch_size`: 128 |
|
|
- `learning_rate`: 3e-05 |
|
|
- `num_train_epochs`: 1 |
|
|
- `bf16`: True |
|
|
- `dataloader_num_workers`: 8 |
|
|
- `accelerator_config`: {'split_batches': True, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
|
|
|
|
#### All Hyperparameters |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
- `overwrite_output_dir`: False |
|
|
- `do_predict`: False |
|
|
- `eval_strategy`: steps |
|
|
- `prediction_loss_only`: True |
|
|
- `per_device_train_batch_size`: 128 |
|
|
- `per_device_eval_batch_size`: 128 |
|
|
- `per_gpu_train_batch_size`: None |
|
|
- `per_gpu_eval_batch_size`: None |
|
|
- `gradient_accumulation_steps`: 1 |
|
|
- `eval_accumulation_steps`: None |
|
|
- `torch_empty_cache_steps`: None |
|
|
- `learning_rate`: 3e-05 |
|
|
- `weight_decay`: 0.0 |
|
|
- `adam_beta1`: 0.9 |
|
|
- `adam_beta2`: 0.999 |
|
|
- `adam_epsilon`: 1e-08 |
|
|
- `max_grad_norm`: 1.0 |
|
|
- `num_train_epochs`: 1 |
|
|
- `max_steps`: -1 |
|
|
- `lr_scheduler_type`: linear |
|
|
- `lr_scheduler_kwargs`: {} |
|
|
- `warmup_ratio`: 0.0 |
|
|
- `warmup_steps`: 0 |
|
|
- `log_level`: passive |
|
|
- `log_level_replica`: warning |
|
|
- `log_on_each_node`: True |
|
|
- `logging_nan_inf_filter`: True |
|
|
- `save_safetensors`: True |
|
|
- `save_on_each_node`: False |
|
|
- `save_only_model`: False |
|
|
- `restore_callback_states_from_checkpoint`: False |
|
|
- `no_cuda`: False |
|
|
- `use_cpu`: False |
|
|
- `use_mps_device`: False |
|
|
- `seed`: 42 |
|
|
- `data_seed`: None |
|
|
- `jit_mode_eval`: False |
|
|
- `bf16`: True |
|
|
- `fp16`: False |
|
|
- `fp16_opt_level`: O1 |
|
|
- `half_precision_backend`: auto |
|
|
- `bf16_full_eval`: False |
|
|
- `fp16_full_eval`: False |
|
|
- `tf32`: None |
|
|
- `local_rank`: 0 |
|
|
- `ddp_backend`: None |
|
|
- `tpu_num_cores`: None |
|
|
- `tpu_metrics_debug`: False |
|
|
- `debug`: [] |
|
|
- `dataloader_drop_last`: True |
|
|
- `dataloader_num_workers`: 8 |
|
|
- `dataloader_prefetch_factor`: None |
|
|
- `past_index`: -1 |
|
|
- `disable_tqdm`: False |
|
|
- `remove_unused_columns`: True |
|
|
- `label_names`: None |
|
|
- `load_best_model_at_end`: False |
|
|
- `ignore_data_skip`: False |
|
|
- `fsdp`: [] |
|
|
- `fsdp_min_num_params`: 0 |
|
|
- `fsdp_config`: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False} |
|
|
- `fsdp_transformer_layer_cls_to_wrap`: None |
|
|
- `accelerator_config`: {'split_batches': True, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None} |
|
|
- `parallelism_config`: None |
|
|
- `deepspeed`: None |
|
|
- `label_smoothing_factor`: 0.0 |
|
|
- `optim`: adamw_torch_fused |
|
|
- `optim_args`: None |
|
|
- `adafactor`: False |
|
|
- `group_by_length`: False |
|
|
- `length_column_name`: length |
|
|
- `project`: huggingface |
|
|
- `trackio_space_id`: trackio |
|
|
- `ddp_find_unused_parameters`: None |
|
|
- `ddp_bucket_cap_mb`: None |
|
|
- `ddp_broadcast_buffers`: False |
|
|
- `dataloader_pin_memory`: True |
|
|
- `dataloader_persistent_workers`: False |
|
|
- `skip_memory_metrics`: True |
|
|
- `use_legacy_prediction_loop`: False |
|
|
- `push_to_hub`: False |
|
|
- `resume_from_checkpoint`: None |
|
|
- `hub_model_id`: None |
|
|
- `hub_strategy`: every_save |
|
|
- `hub_private_repo`: None |
|
|
- `hub_always_push`: False |
|
|
- `hub_revision`: None |
|
|
- `gradient_checkpointing`: False |
|
|
- `gradient_checkpointing_kwargs`: None |
|
|
- `include_inputs_for_metrics`: False |
|
|
- `include_for_metrics`: [] |
|
|
- `eval_do_concat_batches`: True |
|
|
- `fp16_backend`: auto |
|
|
- `push_to_hub_model_id`: None |
|
|
- `push_to_hub_organization`: None |
|
|
- `mp_parameters`: |
|
|
- `auto_find_batch_size`: False |
|
|
- `full_determinism`: False |
|
|
- `torchdynamo`: None |
|
|
- `ray_scope`: last |
|
|
- `ddp_timeout`: 1800 |
|
|
- `torch_compile`: False |
|
|
- `torch_compile_backend`: None |
|
|
- `torch_compile_mode`: None |
|
|
- `include_tokens_per_second`: False |
|
|
- `include_num_input_tokens_seen`: no |
|
|
- `neftune_noise_alpha`: None |
|
|
- `optim_target_modules`: None |
|
|
- `batch_eval_metrics`: False |
|
|
- `eval_on_start`: False |
|
|
- `use_liger_kernel`: False |
|
|
- `liger_kernel_config`: None |
|
|
- `eval_use_gather_object`: False |
|
|
- `average_tokens_across_devices`: True |
|
|
- `prompts`: None |
|
|
- `batch_sampler`: batch_sampler |
|
|
- `router_mapping`: {} |
|
|
- `learning_rate_mapping`: {} |
|
|
|
|
|
</details> |
|
|
|
|
|
### Training Logs |
|
|
<details><summary>Click to expand</summary> |
|
|
|
|
|
| Epoch | Step | Training Loss | CodeSearchNetPython_MaxSim_ndcg@10 | CodeSearchNetJavascript_MaxSim_ndcg@10 | CodeSearchNetGo_MaxSim_ndcg@10 | CodeSearchNetRuby_MaxSim_ndcg@10 | CodeSearchNetJava_MaxSim_ndcg@10 | CodeSearchNetPhp_MaxSim_ndcg@10 | CodeSearchNet_mean_MaxSim_ndcg@10 | |
|
|
|:------:|:-----:|:-------------:|:----------------------------------:|:--------------------------------------:|:------------------------------:|:--------------------------------:|:--------------------------------:|:-------------------------------:|:---------------------------------:| |
|
|
| 0.0000 | 1 | 6.4113 | - | - | - | - | - | - | - | |
|
|
| 0.0391 | 1250 | 3.2574 | - | - | - | - | - | - | - | |
|
|
| 0.0781 | 2500 | 19.7862 | 0.9377 | 0.7986 | 0.9622 | 0.8487 | 0.8837 | 0.8834 | 0.8857 | |
|
|
| 0.1172 | 3750 | 4.6875 | - | - | - | - | - | - | - | |
|
|
| 0.1562 | 5000 | 2.3691 | 0.9335 | 0.8001 | 0.9614 | 0.8435 | 0.8755 | 0.8818 | 0.8826 | |
|
|
| 0.1953 | 6250 | 1.4007 | - | - | - | - | - | - | - | |
|
|
| 0.2344 | 7500 | 2.5715 | 0.9311 | 0.7960 | 0.9611 | 0.8418 | 0.8730 | 0.8866 | 0.8816 | |
|
|
| 0.2734 | 8750 | 1.5546 | - | - | - | - | - | - | - | |
|
|
| 0.3125 | 10000 | 0.004 | 0.9332 | 0.7972 | 0.9620 | 0.8435 | 0.8730 | 0.8850 | 0.8823 | |
|
|
| 0.3515 | 11250 | 2.2819 | - | - | - | - | - | - | - | |
|
|
| 0.3906 | 12500 | 14.0214 | 0.9324 | 0.7986 | 0.9603 | 0.8409 | 0.8717 | 0.8855 | 0.8816 | |
|
|
| 0.4297 | 13750 | 2.0774 | - | - | - | - | - | - | - | |
|
|
| 0.4687 | 15000 | 1.7724 | 0.9272 | 0.7955 | 0.9592 | 0.8381 | 0.8733 | 0.8838 | 0.8795 | |
|
|
| 0.5078 | 16250 | 3.8234 | - | - | - | - | - | - | - | |
|
|
| 0.5468 | 17500 | 0.7029 | 0.9300 | 0.7959 | 0.9594 | 0.8371 | 0.8674 | 0.8832 | 0.8788 | |
|
|
| 0.5859 | 18750 | 1.5763 | - | - | - | - | - | - | - | |
|
|
| 0.6250 | 20000 | 2.3146 | 0.9294 | 0.7986 | 0.9589 | 0.8376 | 0.8704 | 0.8829 | 0.8796 | |
|
|
| 0.6640 | 21250 | 13.784 | - | - | - | - | - | - | - | |
|
|
| 0.7031 | 22500 | 1.4557 | 0.9252 | 0.7927 | 0.9617 | 0.8357 | 0.8661 | 0.8839 | 0.8775 | |
|
|
| 0.7421 | 23750 | 4.973 | - | - | - | - | - | - | - | |
|
|
| 0.7812 | 25000 | 2.206 | 0.9240 | 0.7939 | 0.9623 | 0.8354 | 0.8639 | 0.8857 | 0.8775 | |
|
|
| 0.8203 | 26250 | 0.7343 | - | - | - | - | - | - | - | |
|
|
| 0.8593 | 27500 | 0.727 | 0.9251 | 0.7926 | 0.9608 | 0.8362 | 0.8676 | 0.8829 | 0.8775 | |
|
|
| 0.8984 | 28750 | 1.7905 | - | - | - | - | - | - | - | |
|
|
| 0.9374 | 30000 | 0.7259 | 0.9244 | 0.7937 | 0.9607 | 0.8357 | 0.8655 | 0.8824 | 0.8771 | |
|
|
|
|
|
</details> |
|
|
|
|
|
|
|
|
### Framework Versions |
|
|
- Python: 3.12.12 |
|
|
- Sentence Transformers: 5.1.1 |
|
|
- PyLate: 1.3.4 |
|
|
- Transformers: 4.57.3 |
|
|
- PyTorch: 2.9.0+cu128 |
|
|
- Accelerate: 1.12.0 |
|
|
- Datasets: 4.4.2 |
|
|
- Tokenizers: 0.22.2 |
|
|
|
|
|
|
|
|
## Citation |
|
|
### BibTeX |
|
|
#### LateOn-Code |
|
|
```bibtex |
|
|
@misc{LateOn-Code, |
|
|
title = {LateOn-Code: a Family of State-Of-The-Art Late Interaction Code Retrieval Models}, |
|
|
author = {Chaffin, Antoine}, |
|
|
url = {https://huggingface.co/collections/lightonai/lateon-code}, |
|
|
year = {2026} |
|
|
} |
|
|
``` |
|
|
#### ColGrep |
|
|
```bibtex |
|
|
@software{next-plaid, |
|
|
title = {NextPlaid, ColGREP: Multi-vector search, from database to coding agents.}, |
|
|
url = {https://github.com/lightonai/next-plaid}, |
|
|
author = {Raphaël Sourty}, |
|
|
year = {2026}, |
|
|
} |
|
|
``` |
|
|
|
|
|
#### CoRNStack |
|
|
```bibtex |
|
|
@inproceedings{DBLP:conf/iclr/SureshRXNMDJ25, |
|
|
author = {Tarun Suresh and |
|
|
Revanth Gangi Reddy and |
|
|
Yifei Xu and |
|
|
Zach Nussbaum and |
|
|
Andriy Mulyar and |
|
|
Brandon Duderstadt and |
|
|
Heng Ji}, |
|
|
title = {CoRNStack: High-Quality Contrastive Data for Better Code Retrieval |
|
|
and Reranking}, |
|
|
booktitle = {The Thirteenth International Conference on Learning Representations, |
|
|
{ICLR} 2025, Singapore, April 24-28, 2025}, |
|
|
publisher = {OpenReview.net}, |
|
|
year = {2025}, |
|
|
url = {https://openreview.net/forum?id=iyJOUELYir}, |
|
|
timestamp = {Sun, 25 May 2025 21:25:19 +0200}, |
|
|
biburl = {https://dblp.org/rec/conf/iclr/SureshRXNMDJ25.bib}, |
|
|
bibsource = {dblp computer science bibliography, https://dblp.org} |
|
|
} |
|
|
``` |
|
|
|
|
|
#### CoIR |
|
|
```bibtex |
|
|
@inproceedings{li2025coir, |
|
|
title = {Coir: A comprehensive benchmark for code information retrieval models}, |
|
|
author = {Li, Xiangyang and Dong, Kuicai and Lee, Yi Quan and Xia, Wei and Zhang, Hao and Dai, Xinyi and Wang, Yasheng and Tang, Ruiming}, |
|
|
booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)}, |
|
|
pages = {22074--22091}, |
|
|
year = {2025} |
|
|
} |
|
|
``` |
|
|
|
|
|
#### Sentence Transformers |
|
|
```bibtex |
|
|
@inproceedings{reimers-2019-sentence-bert, |
|
|
title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks", |
|
|
author = "Reimers, Nils and Gurevych, Iryna", |
|
|
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing", |
|
|
month = "11", |
|
|
year = "2019", |
|
|
publisher = "Association for Computational Linguistics", |
|
|
url = "https://arxiv.org/abs/1908.10084" |
|
|
} |
|
|
``` |
|
|
|
|
|
#### PyLate |
|
|
```bibtex |
|
|
@inproceedings{DBLP:conf/cikm/ChaffinS25, |
|
|
author = {Antoine Chaffin and |
|
|
Rapha{"{e}}l Sourty}, |
|
|
editor = {Meeyoung Cha and |
|
|
Chanyoung Park and |
|
|
Noseong Park and |
|
|
Carl Yang and |
|
|
Senjuti Basu Roy and |
|
|
Jessie Li and |
|
|
Jaap Kamps and |
|
|
Kijung Shin and |
|
|
Bryan Hooi and |
|
|
Lifang He}, |
|
|
title = {PyLate: Flexible Training and Retrieval for Late Interaction Models}, |
|
|
booktitle = {Proceedings of the 34th {ACM} International Conference on Information |
|
|
and Knowledge Management, {CIKM} 2025, Seoul, Republic of Korea, November |
|
|
10-14, 2025}, |
|
|
pages = {6334--6339}, |
|
|
publisher = {{ACM}}, |
|
|
year = {2025}, |
|
|
url = {https://github.com/lightonai/pylate}, |
|
|
doi = {10.1145/3746252.3761608}, |
|
|
} |
|
|
``` |
|
|
|
|
|
<!-- |
|
|
## Glossary |
|
|
|
|
|
*Clearly define terms in order to be accessible across audiences.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Authors |
|
|
|
|
|
*Lists the people who create the model card, providing recognition and accountability for the detailed work that goes into its construction.* |
|
|
--> |
|
|
|
|
|
<!-- |
|
|
## Model Card Contact |
|
|
|
|
|
*Provides a way for people who have updates to the Model Card, suggestions, or questions, to contact the Model Card authors.* |
|
|
--> |
