Update model and code

app.py

@@ -6,7 +6,6 @@ import pymarc
 
 from marcai.predict import predict
 from marcai.process import process
-from marcai.utils import load_config
 from marcai.utils.parsing import record_dict
 from marcai.pl import SimilarityVectorModel
 
@@ -23,12 +22,9 @@ def compare(file1, file2):
 
     df = process(df1, df2)
 
-    # Load config
-    config = load_config(os.path.join(root, "config.yaml"))
-
     model = SimilarityVectorModel.from_pretrained("cdlib/marc-match-ai")
 
-    input_df = df[config["model"]["features"]]
+    input_df = df[model.features]
 
     # Run model
     prediction = predict(model, input_df).item()

config.json

@@ -0,0 +1,15 @@
+{
+  "batch_size": 512,
+  "features": [
+    "title_tokenset",
+    "title_agg",
+    "author",
+    "publisher",
+    "pub_date",
+    "pub_place",
+    "pagination"
+  ],
+  "lr": 0.006,
+  "optimizer": "Adam",
+  "weight_decay": 0.0
+}

config.yaml

@@ -1,27 +0,0 @@
-model:
-  # Inputs features
-  features:
-    - title_tokenset
-    - title_agg
-    - author
-    - publisher
-    - pub_date
-    - pub_place
-    - pagination
-  
-  # Training
-  batch_size: 512
-  weight_decay: 0.0
-  max_epochs: -1
-
-  # Disable early stopping with -1
-  patience: 20
-  
-  lr: 0.006
-  optimizer: Adam
-  saved_models_dir: saved_models
-
-  # Paths to dataset splits
-  test_processed_path: data/test_processed.csv
-  train_processed_path: data/train_processed.csv
-  val_processed_path: data/val_processed.csv

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a2798326955686b9da8b88245e6c9f5f9ab34027a956d9eaac0c125a2751fc
+size 10180