Upload model

config.json

@@ -1,13 +1,20 @@
 {
-  "_name_or_path": "google-bert/bert-large-uncased",
   "architectures": [
-    "BertForSequenceClassification"
+    "OptILMPreTrainedModel"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
+  "base_model_config": {
+    "_name_or_path": "google-bert/bert-large-uncased",
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "gradient_checkpointing": false,
+    "hidden_size": 1024,
+    "intermediate_size": 4096,
+    "model_type": "bert",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24
+  },
+  "base_model_name": "google-bert/bert-large-uncased",
   "hidden_size": 1024,
   "id2label": {
     "0": "LABEL_0",
@@ -24,8 +31,6 @@
     "11": "LABEL_11",
     "12": "LABEL_12"
   },
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -41,16 +46,7 @@
     "LABEL_8": 8,
     "LABEL_9": 9
   },
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "model_type": "optillm",
   "torch_dtype": "float32",
-  "transformers_version": "4.44.2",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 30522
+  "transformers_version": "4.44.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9c2f1a2d09f4f2b934bbed85b126dd03a2434506593b63974101b71e58d0cec
-size 1340691036
+oid sha256:6b82179e3e256e7aa033527825ba93e69881453bad96c45f51905e6126b2e31b
+size 1340691068