Update README.md
Browse files
README.md
CHANGED
|
@@ -24,6 +24,8 @@ datasets:
|
|
| 24 |
|
| 25 |
## Overview
|
| 26 |
|
|
|
|
|
|
|
| 27 |
**potion-code-16M** is a fast static code embedding model optimized for code retrieval tasks. It powers [Semble](https://github.com/MinishLab/semble), a code search library for agents. It is distilled from [nomic-ai/CodeRankEmbed](https://huggingface.co/nomic-ai/CodeRankEmbed) and trained on the [CornStack](https://huggingface.co/datasets/nomic-ai/cornstack-python-v1) code corpus using [Tokenlearn](https://github.com/MinishLab/tokenlearn) and contrastive fine-tuning.
|
| 28 |
|
| 29 |
It uses static embeddings, allowing text and code embeddings to be computed orders of magnitude faster than transformer-based models on both GPU and CPU.
|
|
@@ -65,8 +67,7 @@ Results on the [CoIR benchmark](https://github.com/CoIR-team/coir) on [MTEB](htt
|
|
| 65 |
| Model | Params | AVG | AppsRetrieval | COIRCodeSearchNet | CodeFeedbackMT | CodeFeedbackST | CodeSearchNetCC | CodeTransContest | CodeTransDL | CosQA | StackOverflow | Text2SQL |
|
| 66 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
| 67 |
| CodeRankEmbed | 137M | 59.14 | 23.46 | 94.70 | 42.61 | 78.11 | 76.39 | 66.43 | 34.84 | 35.92 | 80.53 | 58.37 |
|
| 68 |
-
|
|
| 69 |
-
| BM25 | — | 39.11 | 4.76 | 32.45 | 59.69 | 67.85 | 33.00 | 47.29 | 32.97 | 15.53 | 69.54 | 28.07 |
|
| 70 |
| **potion-code-16M** | **16M** | **37.05** | **3.97** | **42.99** | **36.26** | **50.27** | **43.40** | **39.76** | **31.72** | **21.37** | **57.47** | **43.34** |
|
| 71 |
| potion-retrieval-32M | 32M | 32.10 | 4.22 | 31.80 | 36.71 | 45.11 | 38.64 | 29.97 | 32.62 | 8.70 | 56.26 | 36.93 |
|
| 72 |
| potion-base-32M | 32M | 31.42 | 3.37 | 29.58 | 34.77 | 42.69 | 37.88 | 28.51 | 30.55 | 14.61 | 53.36 | 38.88 |
|
|
|
|
| 24 |
|
| 25 |
## Overview
|
| 26 |
|
| 27 |
+
**This model is superseded by [potion-code-16M-v2](https://huggingface.co/minishlab/potion-code-16M-v2). We recommend using that instead for better performance at the same size.**
|
| 28 |
+
|
| 29 |
**potion-code-16M** is a fast static code embedding model optimized for code retrieval tasks. It powers [Semble](https://github.com/MinishLab/semble), a code search library for agents. It is distilled from [nomic-ai/CodeRankEmbed](https://huggingface.co/nomic-ai/CodeRankEmbed) and trained on the [CornStack](https://huggingface.co/datasets/nomic-ai/cornstack-python-v1) code corpus using [Tokenlearn](https://github.com/MinishLab/tokenlearn) and contrastive fine-tuning.
|
| 30 |
|
| 31 |
It uses static embeddings, allowing text and code embeddings to be computed orders of magnitude faster than transformer-based models on both GPU and CPU.
|
|
|
|
| 67 |
| Model | Params | AVG | AppsRetrieval | COIRCodeSearchNet | CodeFeedbackMT | CodeFeedbackST | CodeSearchNetCC | CodeTransContest | CodeTransDL | CosQA | StackOverflow | Text2SQL |
|
| 68 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|
| 69 |
| CodeRankEmbed | 137M | 59.14 | 23.46 | 94.70 | 42.61 | 78.11 | 76.39 | 66.43 | 34.84 | 35.92 | 80.53 | 58.37 |
|
| 70 |
+
| BM25 | — | 42.31 | 4.76 | 40.86 | 59.19 | 68.15 | 53.97 | 47.78 | 34.42 | 18.75 | 70.26 | 24.94 |
|
|
|
|
| 71 |
| **potion-code-16M** | **16M** | **37.05** | **3.97** | **42.99** | **36.26** | **50.27** | **43.40** | **39.76** | **31.72** | **21.37** | **57.47** | **43.34** |
|
| 72 |
| potion-retrieval-32M | 32M | 32.10 | 4.22 | 31.80 | 36.71 | 45.11 | 38.64 | 29.97 | 32.62 | 8.70 | 56.26 | 36.93 |
|
| 73 |
| potion-base-32M | 32M | 31.42 | 3.37 | 29.58 | 34.77 | 42.69 | 37.88 | 28.51 | 30.55 | 14.61 | 53.36 | 38.88 |
|