Upload ModernBertForSequenceClassification

config.json

@@ -1,14 +1,25 @@
 {
-  "activation": "gelu",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "ModernBertForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50281,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
   "dtype": "float32",
-  "finetuning_task": "sst-2",
-  "hidden_dim": 3072,
+  "embedding_dropout": 0.0,
+  "eos_token_id": 50282,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -25,7 +36,9 @@
     "12": "LABEL_12",
     "13": "LABEL_13"
   },
+  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
+  "intermediate_size": 2624,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -42,16 +55,23 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "output_past": true,
-  "pad_token_id": 0,
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "pad_token_id": 50283,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
   "transformers_version": "4.56.1",
-  "vocab_size": 30522
+  "vocab_size": 50368
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d23e6beaca44e57cc4cdd14c9259eaa91ad62a392d65213dd941396f881767
-size 267869480
+oid sha256:171183e718f70b99486a2f4ab5a2df10698296792aa8780e17d0d08b5bcec4d3
+size 1583400840