Upload sentiment classifier trained on Amazon Reviews

README.md

@@ -32,7 +32,8 @@ This is a sentiment classification model fine-tuned on Amazon Reviews dataset.
 ## Model Description
 
 - **Base Model**: xlm-roberta-base
-- **Task**: Binary Sentiment Classification (negative/positive)
+- **Task**: Sentiment Classification (negative/neutral/positive)
+- **Architecture**: Sequence Classification (single-head)
 - **Languages**: Multilingual (100+ languages)
 - **Parameters**: 278M
 

config.json

@@ -14,10 +14,6 @@
     "LABEL_1": 1,
     "LABEL_2": 2
   },
-  "loss_weights": {
-    "classification": 0.7,
-    "regression": 0.3
-  },
   "model_type": "sentiment-classifier",
   "pretrained_model": "xlm-roberta-base",
   "torch_dtype": "float32",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cff6d329ea1fd580ef743a61fd813ecd78a1afec74644f402ad72c7a215dfe3
-size 1113391228
+oid sha256:25bcb5c098e6ee12a1982c57d0ae4af0e03db286684b66c37283561f7a7563c7
+size 1112208144