splade-v3

config.yaml

@@ -40,8 +40,8 @@ models:
     language: ["multilingual"]
     repository: "https://huggingface.co/intfloat/multilingual-e5-small"
 
-  splade-pp-v1:
-    name: "prithivida/Splade_PP_en_v1"
+  splade-v3:
+    name: "naver/splade-v3"
     type: "sparse-embeddings"
     dimension: 1234   # must add this field
     max_tokens: 1234
@@ -52,7 +52,7 @@ models:
       Hereinafter efficiency is a short hand for retrieval efficiency unless explicitly qualified otherwise. 
       Not that inference efficiency is not important, we will address that subsequently.)
     language: ["multilingual"]
-    repository: "https://huggingface.co/prithivida/Splade_PP_en_v1"
+    repository: "https://huggingface.co/naver/splade-v3"
 
   splade-pp-v2:
     name: "prithivida/Splade_PP_en_v2"

core/embedding.py

@@ -81,7 +81,7 @@ class SparseEmbeddingModel:
     
     def _format_values(self, values: List[float]) -> List[float]:
         """Format float values to a fixed precision."""
-        return [round(float(v), 7) for v in values]
+        return [round(float(v), 8) for v in values]
     
     def load(self) -> None:
         """Load the sparse embedding model."""