smaller model

modular_graph_and_candidates.py

@@ -96,7 +96,7 @@ def similarity_clusters(bags: Dict[str, List[Set[str]]], thr: float) -> Dict[Tup
 
 @spaces.GPU
 def embedding_similarity_clusters(models_root: Path, missing: List[str], thr: float) -> Dict[Tuple[str, str], float]:
-    model = SentenceTransformer("nomic-ai/nomic-embed-code")
+    model = SentenceTransformer("codesage/codesage-large-v2", trust_remote_code=True)
     model.max_seq_length = 4096  # truncate overly long modeling files
     texts = {}