Feature Extraction
sentence-transformers
Safetensors
Transformers
qwen3
text-generation
splade
sparse-encoder
code
custom_code
text-embeddings-inference
Instructions to use naver/splade-code-06B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use naver/splade-code-06B with sentence-transformers:
from sentence_transformers import SparseEncoder model = SparseEncoder("naver/splade-code-06B", trust_remote_code=True) queries = ["Which planet is known as the Red Planet?"] documents = [ "Venus is often called Earth's twin because of its similar size and proximity.", "Mars, known for its reddish appearance, is often referred to as the Red Planet.", "Jupiter, the largest planet in our solar system, has a prominent red spot.", ] query_embeddings = model.encode_query(queries) document_embeddings = model.encode_document(documents) similarities = model.similarity(query_embeddings, document_embeddings) print(similarities) - Transformers
How to use naver/splade-code-06B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="naver/splade-code-06B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("naver/splade-code-06B", trust_remote_code=True) model = AutoModelForCausalLM.from_pretrained("naver/splade-code-06B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,12 +2,15 @@
|
|
| 2 |
license: cc-by-nc-sa-4.0
|
| 3 |
---
|
| 4 |
|
|
|
|
|
|
|
|
|
|
| 5 |
```python
|
| 6 |
from transformers import AutoModelForCausalLM, AutoModel
|
| 7 |
import os
|
| 8 |
import torch
|
| 9 |
-
|
| 10 |
-
splade = AutoModelForCausalLM.from_pretrained("naver/splade-code-06B",
|
| 11 |
device = (torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu"))
|
| 12 |
splade.to(device)
|
| 13 |
splade.eval()
|
|
|
|
| 2 |
license: cc-by-nc-sa-4.0
|
| 3 |
---
|
| 4 |
|
| 5 |
+
SPLADE-Code-06B is a sparse retrieval model designed for code retrieval tasks. It is the top-performing models on MTEB for models below 1B (at time of writing, Feb 2026).
|
| 6 |
+
|
| 7 |
+
|
| 8 |
```python
|
| 9 |
from transformers import AutoModelForCausalLM, AutoModel
|
| 10 |
import os
|
| 11 |
import torch
|
| 12 |
+
|
| 13 |
+
splade = AutoModelForCausalLM.from_pretrained("naver/splade-code-06B", trust_remote_code=True)
|
| 14 |
device = (torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu"))
|
| 15 |
splade.to(device)
|
| 16 |
splade.eval()
|