Upload SPLADE-PT-BR model v1.0.0

README.md

@@ -9,6 +9,7 @@ tags:
 - bert
 datasets:
 - unicamp-dl/mmarco
+- unicamp-dl/mrobust
 base_model: neuralmind/bert-base-portuguese-cased
 ---
 
@@ -36,8 +37,10 @@ SPLADE is a neural retrieval model that learns to expand queries and documents w
 
 ### Training Data
 
-- **Primary Dataset**: mMARCO Portuguese (MS MARCO translated to Portuguese)
-- **Validation**: Portuguese query-document pairs
+- **Training Dataset**: mMARCO Portuguese (`unicamp-dl/mmarco`) - MS MARCO translated to Portuguese
+  - Used for training with triplets (query, positive document, negative document)
+- **Validation Dataset**: mRobust (`unicamp-dl/mrobust`) - TREC Robust04 translated to Portuguese
+  - Used for validation and evaluation during training
 - **Format**: Triplets (query, positive document, negative document)
 
 ### Training Configuration

model_metadata.json

@@ -13,7 +13,8 @@
   },
   
   "training": {
-    "dataset": "mMARCO Portuguese",
+    "training_dataset": "mMARCO Portuguese (unicamp-dl/mmarco)",
+    "validation_dataset": "mRobust (unicamp-dl/mrobust)",
     "num_iterations": 150000,
     "final_loss": 0.000047,
     "batch_size": 8,