Upload ModernBertForSequenceClassification

config.json

@@ -1,50 +1,64 @@
 {
-  "_name_or_path": "studio-ousia/luke-large",
+  "_name_or_path": "sbintuitions/modernbert-ja-130m",
   "architectures": [
-    "LukeForSequenceClassification"
+    "ModernBertForSequenceClassification"
   ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
   "attention_probs_dropout_prob": 0.2,
-  "bert_model_name": "roberta-large",
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "entity_emb_size": 256,
-  "entity_vocab_size": 500000,
+  "bos_token_id": 1,
+  "classifier_activation": "gelu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "cls",
+  "cls_token_id": 6,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "embedding_dropout": 0.0,
   "eos_token_id": 2,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
   "gradient_checkpointing": false,
-  "hidden_act": "gelu",
+  "hidden_activation": "gelu",
   "hidden_dropout_prob": 0.2,
-  "hidden_size": 1024,
+  "hidden_size": 512,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2",
     "3": "LABEL_3",
-    "4": "LABEL_4",
-    "5": "LABEL_5"
+    "4": "LABEL_4"
   },
+  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 2048,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
     "LABEL_2": 2,
     "LABEL_3": 3,
-    "LABEL_4": 4,
-    "LABEL_5": 5
+    "LABEL_4": 4
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "luke",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "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": 8,
+  "num_hidden_layers": 19,
+  "pad_token_id": 3,
+  "position_embedding_type": "rope",
   "problem_type": "single_label_classification",
+  "reference_compile": false,
+  "repad_logits_with_grad": false,
+  "sep_token_id": 4,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
   "torch_dtype": "float32",
   "transformers_version": "4.48.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "use_entity_aware_attention": true,
-  "vocab_size": 50267
+  "vocab_size": 102400
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2789271b3da8acf2ea0406c8a76c1d5883187284467614d93b5ce2300f8f28c7
-size 2238988792
+oid sha256:42b720ac6d4739949b66bd018596995f7946bbc316596ded94bb3ba31cb6d791
+size 529635372