Splade-Code
Collection
Learned Sparse Retrieval Models for Code β’ 3 items β’ Updated β’ 6
SPLADE-Code-8B is a sparse retrieval model designed for code retrieval tasks.
Usage
Using Sentence Transformers
Install Sentence Transformers:
pip install sentence_transformers
from sentence_transformers import SparseEncoder
model = SparseEncoder("naver/splade-code-8B", trust_remote_code=True)
queries = [
"SELECT *\nFROM Student\nWHERE Age = (\nSELECT MAX(Age)\nFROM Student\nWHERE Group = 'specific_group'\n)\nAND Group = 'specific_group';"
]
query_embeddings = model.encode(queries)
print(query_embeddings.shape)
# torch.Size([1, 151936])
sparsity = model.sparsity(query_embeddings)
print(sparsity)
# {'active_dims': 1120.0, 'sparsity_ratio': 0.9926284751474305}
decoded = model.decode(query_embeddings, top_k=10)
print(decoded)
# [[
# ('Δ group', 2.34375),
# ('Δ oldest', 2.28125),
# ('Δ age', 2.25),
# ('_group', 2.25),
# ('Δ Group', 2.171875),
# ('Δ Age', 2.109375),
# ('Δ MAX', 2.0625),
# ('Δ Student', 2.046875),
# ('Δ specific', 2.03125),
# ('Δ student', 2.0),
# ]]
Using Transformers
pip install transformers
from transformers import AutoModelForCausalLM, AutoModel
import os
import torch
splade = AutoModelForCausalLM.from_pretrained("naver/splade-code-8B", trust_remote_code=True)
device = (torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu"))
splade.to(device)
splade.eval()
queries = ["SELECT *\nFROM Student\nWHERE Age = (\nSELECT MAX(Age)\nFROM Student\nWHERE Group = 'specific_group'\n)\nAND Group = 'specific_group';"]
bow_dict = splade.encode(queries, prompt_type="query", top_k_q=10, return_dict=True, print_dict=True)
+--------------------------------------------------------------------+
| TOP ACTIVATED WORDS |
+--------------------------------------------------------------------+
* INPUT: SELECT *
FROM Student
WHERE Age = (
SELECT MAX(Age)
FROM Student
WHERE Group = 'specific_group'
)
AND Group = 'specific_group';
Δ group | ββββββββββββββββββββ 2.34
Δ oldest | βββββββββββββββββββ 2.28
Δ age | βββββββββββββββββββ 2.25
_group | βββββββββββββββββββ 2.25
Δ Group | ββββββββββββββββββ 2.17
Δ Age | ββββββββββββββββββ 2.11
Δ MAX | βββββββββββββββββ 2.06
Δ Student | βββββββββββββββββ 2.05
Δ specific | βββββββββββββββββ 2.03
Δ student | βββββββββββββββββ 2.00
- Downloads last month
- 103
from sentence_transformers import SparseEncoder model = SparseEncoder("naver/splade-code-8B", 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)