minishlab/tokenlearn-cornstack-queries-coderankembed-v2
Viewer • Updated • 600k • 32 • 1
How to use Takara-DS1/miru-codev3-tokenlearn with Model2Vec:
from model2vec import StaticModel
model = StaticModel.from_pretrained("Takara-DS1/miru-codev3-tokenlearn")Owned Tokenlearn static code embedding bag (256-d, Model2Vec) — branch A of miru-codev3-dual.
Trained with Zipf-SIF Tokenlearn on CornStack coderankembed-v2 features (code_static.train_miru_codev3).
CoIR / MTEB NDCG@10 (×100), dense retrieval only. Scores are self-reported from the training repo eval harness.
from model2vec import StaticModel
model = StaticModel.from_pretrained("Takara-DS1/miru-codev3-tokenlearn")
emb = model.encode(["def add(a, b): return a + b"])
For the 512-d dual (this bag ⊕ distill_fuse), use Takara-DS1/miru-codev3-dual.
See the dual repo reproduce/REPRODUCE.md (step 1: train_miru_codev3).
MIT