yeye776/KcElectra-ft

README.md

@@ -1,5 +1,6 @@
 ---
-base_model: monologg/distilkobert
+license: mit
+base_model: beomi/KcELECTRA-base
 tags:
 - generated_from_trainer
 model-index:
@@ -12,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # bert
 
-This model is a fine-tuned version of [monologg/distilkobert](https://huggingface.co/monologg/distilkobert) on an unknown dataset.
+This model is a fine-tuned version of [beomi/KcELECTRA-base](https://huggingface.co/beomi/KcELECTRA-base) on an unknown dataset.
 
 ## Model description
 

config.json

@@ -1,13 +1,14 @@
 {
-  "_name_or_path": "monologg/distilkobert",
-  "activation": "gelu",
+  "_name_or_path": "beomi/KcELECTRA-base",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "ElectraForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
@@ -16,6 +17,7 @@
     "4": "LABEL_4"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -23,17 +25,22 @@
     "LABEL_3": 3,
     "LABEL_4": 4
   },
+  "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 3,
-  "pad_token_id": 1,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 3,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "tokenizer_class": "PreTrainedTokenizerFast",
   "torch_dtype": "float32",
   "transformers_version": "4.41.2",
-  "vocab_size": 8002
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f354a702d62c2bba8f8c346b38be09c807fe0270516518f7607278ee278ea598
-size 113599948
+oid sha256:4f386166ae7924783bbdacf5ffea47185d066bfa77cd83ae7c7d90f99d4a66a2
+size 436364884