naver / splade-code-06B

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).

from transformers import AutoModelForCausalLM, AutoModel
import os
import torch

splade = AutoModelForCausalLM.from_pretrained("naver/splade-code-06B", 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';

Ġgroup                    | ████████████████████ 2.34
ĠAge                      | ████████████████████ 2.34
Ġage                      | ███████████████████ 2.33
Ġspecific                 | ███████████████████ 2.30
_group                    | ███████████████████ 2.30
ĠStudent                  | ███████████████████ 2.30
Ġmax                      | ██████████████████ 2.22
ĠMax                      | ██████████████████ 2.22
Ġstudent                  | ██████████████████ 2.20
ĠGroup                    | ██████████████████ 2.20