Add vendor-classification

README.md

@@ -16,18 +16,15 @@ You can install it with `pip install adaptive-classifier`.
 ## Model Details
 
 - Base Model: answerdotai/ModernBERT-base
-- Number of Classes: 5
-- Total Examples: 25
+- Number of Classes: 2
+- Total Examples: 161
 - Embedding Dimension: 768
 
 ## Class Distribution
 
 ```
-blacklisted: 5 examples (20.0%)
-established_vendor: 5 examples (20.0%)
-high_risk: 5 examples (20.0%)
-new_vendor: 5 examples (20.0%)
-trusted_partner: 5 examples (20.0%)
+new_vendor: 81 examples (50.3%)
+trusted_partner: 80 examples (49.7%)
 ```
 
 ## Usage
@@ -51,7 +48,7 @@ classifier.add_examples(texts, labels)
 
 ## Training Details
 
-- Training Steps: 13
+- Training Steps: 6
 - Examples per Class: See distribution above
 - Prototype Memory: Active
 - Neural Adaptation: Active

config.json

@@ -33,18 +33,12 @@
   "embedding_dim": 768,
   "id_to_label": {
     "0": "new_vendor",
-    "1": "established_vendor",
-    "2": "trusted_partner",
-    "3": "high_risk",
-    "4": "blacklisted"
+    "1": "trusted_partner"
   },
   "label_to_id": {
-    "blacklisted": 4,
-    "established_vendor": 1,
-    "high_risk": 3,
     "new_vendor": 0,
-    "trusted_partner": 2
+    "trusted_partner": 1
   },
   "model_name": "answerdotai/ModernBERT-base",
-  "train_steps": 13
+  "train_steps": 6
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7de0dc8b8270f483f76564a7170bc300713e79183818988e4896772757f9b6ec
-size 3567620
+oid sha256:3c32887843cdbc3430fab106e26284f8f01411de3a17f47b601c18ef8b18fda7
+size 3553520