Upload ElectraForMaskedLM

config.json

@@ -1,33 +1,30 @@
 {
-  "add_cross_attentions": false,
+  "_name_or_path": "google/electra-small-discriminator",
   "architectures": [
-    "TextTransformer"
+    "ElectraForMaskedLM"
   ],
-  "attention_implementation": "sdpa",
-  "attention_probability_dropout_probability": 0.1,
-  "bos_token_id": null,
+  "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "dropout_probability": 0.1,
   "embedding_size": 128,
-  "eos_token_id": null,
-  "hidden_activation_function": "gelu",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
   "hidden_size": 256,
-  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
   "intermediate_size": 1024,
   "layer_norm_eps": 1e-12,
-  "mask_token_id": null,
   "max_position_embeddings": 512,
+  "model_type": "electra",
   "num_attention_heads": 4,
   "num_hidden_layers": 12,
-  "num_intermediate_layers": 1,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
   "torch_dtype": "float32",
   "transformers_version": "4.48.3",
   "type_vocab_size": 2,
-  "use_cache": false,
-  "vocab_size": 30522,
-  "wac_distribution_layers": [],
-  "wac_distribution_matrix": "none",
-  "wac_embedding_size": -1
+  "use_cache": true,
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7263e7181b95e64a360281c8981d10c140942215bbf9b810748f87751b0c9876
-size 54222832
+oid sha256:724ebb4524983284c2a1fa920d29ea2af2ce5fe6d1c4b3be035aa10cc5c5d739
+size 54210824