Upload ElectraForMaskedLM

.gitattributes

@@ -14,3 +14,4 @@
 *.pb filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
+model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1 +1,4 @@
+---
+{}
+---
 This is a tiny-electra random model to be used for basic testing.

config.json

@@ -1,27 +1,29 @@
-{
-  "architectures": [
-    "ElectraForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "embedding_size": 64,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 64,
-  "initializer_range": 0.02,
-  "intermediate_size": 64,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "electra",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
-  "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": "float16",
-  "transformers_version": "4.9.0.dev0",
-  "type_vocab_size": 2,
-  "vocab_size": 5120
-}
+{
+  "architectures": [
+    "ElectraForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 64,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 64,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "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": "4.52.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 5120
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1df74dfa8af290e22a4f617696eb01f5aba80b0631544ed480a0d4caaff7d12b
+size 1686904