Feature Extraction
sentence-transformers
ONNX
Safetensors
English
code
roberta
python
code-search
code-embeddings
unixcoder
matryoshka
mteb
Eval Results (legacy)
text-embeddings-inference
Instructions to use divakantpandey/code-embed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use divakantpandey/code-embed with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("divakantpandey/code-embed") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3] - Notebooks
- Google Colab
- Kaggle
Upload CodeEmbed model weights and configuration
Browse files
README.md
CHANGED
|
@@ -10,6 +10,7 @@ tags:
|
|
| 10 |
- unixcoder
|
| 11 |
- matryoshka
|
| 12 |
- onnx
|
|
|
|
| 13 |
license: cc-by-nc-4.0
|
| 14 |
pipeline_tag: feature-extraction
|
| 15 |
library_name: sentence-transformers
|
|
@@ -17,6 +18,41 @@ metrics:
|
|
| 17 |
- mrr
|
| 18 |
- ndcg
|
| 19 |
- recall
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
---
|
| 21 |
|
| 22 |
# 💻 code-embed
|
|
|
|
| 10 |
- unixcoder
|
| 11 |
- matryoshka
|
| 12 |
- onnx
|
| 13 |
+
- mteb
|
| 14 |
license: cc-by-nc-4.0
|
| 15 |
pipeline_tag: feature-extraction
|
| 16 |
library_name: sentence-transformers
|
|
|
|
| 18 |
- mrr
|
| 19 |
- ndcg
|
| 20 |
- recall
|
| 21 |
+
model-index:
|
| 22 |
+
- name: Code-Embed
|
| 23 |
+
results:
|
| 24 |
+
- task:
|
| 25 |
+
type: feature-extraction
|
| 26 |
+
name: Code Search
|
| 27 |
+
dataset:
|
| 28 |
+
name: CodeSearchNet (Python)
|
| 29 |
+
type: code_search_net
|
| 30 |
+
config: python
|
| 31 |
+
split: test
|
| 32 |
+
metrics:
|
| 33 |
+
- type: mrr@10
|
| 34 |
+
value: 0.7514
|
| 35 |
+
name: MRR@10 (100-pool)
|
| 36 |
+
- type: mrr@10
|
| 37 |
+
value: 0.8241
|
| 38 |
+
name: MRR@10 (15k-corpus)
|
| 39 |
+
- type: recall@10
|
| 40 |
+
value: 0.9230
|
| 41 |
+
name: Recall@10 (15k-corpus)
|
| 42 |
+
- task:
|
| 43 |
+
type: feature-extraction
|
| 44 |
+
name: Code Question Answering
|
| 45 |
+
dataset:
|
| 46 |
+
name: CoSQA
|
| 47 |
+
type: cosqa
|
| 48 |
+
split: validation
|
| 49 |
+
metrics:
|
| 50 |
+
- type: mrr@10
|
| 51 |
+
value: 0.7509
|
| 52 |
+
name: MRR@10
|
| 53 |
+
- type: recall@10
|
| 54 |
+
value: 0.8600
|
| 55 |
+
name: Recall@10
|
| 56 |
---
|
| 57 |
|
| 58 |
# 💻 code-embed
|