Upload LukeForSequenceClassification

config.json

@@ -1,27 +1,19 @@
 {
-  "_name_or_path": "sbintuitions/modernbert-ja-130m",
+  "_name_or_path": "studio-ousia/luke-japanese-large-lite",
   "architectures": [
-    "ModernBertForSequenceClassification"
+    "LukeForSequenceClassification"
   ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "attention_probs_dropout_prob": 0.3,
-  "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,
+  "attention_probs_dropout_prob": 0.2,
+  "bert_model_name": "models/luke-japanese-large/hf_xlm_roberta",
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "cls_entity_prediction": false,
+  "entity_emb_size": 256,
+  "entity_vocab_size": 4,
   "eos_token_id": 2,
-  "global_attn_every_n_layers": 3,
-  "global_rope_theta": 160000.0,
-  "gradient_checkpointing": false,
-  "hidden_activation": "gelu",
+  "hidden_act": "gelu",
   "hidden_dropout_prob": 0.2,
-  "hidden_size": 512,
+  "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -29,9 +21,8 @@
     "3": "LABEL_3",
     "4": "LABEL_4"
   },
-  "initializer_cutoff_factor": 2.0,
   "initializer_range": 0.02,
-  "intermediate_size": 2048,
+  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -40,25 +31,17 @@
     "LABEL_4": 4
   },
   "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": 8,
-  "num_hidden_layers": 19,
-  "pad_token_id": 3,
-  "position_embedding_type": "rope",
+  "max_position_embeddings": 514,
+  "model_type": "luke",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "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",
-  "vocab_size": 102400
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "use_entity_aware_attention": true,
+  "vocab_size": 32772
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c3420356f50ad06107472c3f09919ab283b73240e49bad5714e57d4704b8459
-size 529635372
+oid sha256:d07776bbc41d1b0afc0c4fceb6dd9401eb42d5323ec71911f24775f897634c19
+size 1655329220