Upload ModernBertForSequenceClassification

config.json

@@ -18,14 +18,14 @@
   "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
   "hidden_activation": "gelu",
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "id2label": {
     "0": "Small language model",
     "1": "Large language model"
   },
   "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 2624,
+  "intermediate_size": 1152,
   "label2id": {
     "Large language model": 1,
     "Small language model": 0
@@ -39,8 +39,8 @@
   "model_type": "modernbert",
   "norm_bias": false,
   "norm_eps": 1e-05,
-  "num_attention_heads": 16,
-  "num_hidden_layers": 28,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
   "pad_token_id": 50283,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e849b8fb6f7844463a8547ca6dd9e31d4f132efc476e7ee0aecfa9fc3b041de8
-size 1583351632
+oid sha256:eb8b1142606b7031866f836c2452cf9638f689fed4bbf60ba5fddfcc6e39bea5
+size 598439784