Upload DistilBertForMaskedLM

config.json

@@ -1,25 +1,33 @@
 {
+  "activation": "gelu",
   "architectures": [
-    "BertForMaskedLM"
+    "DistilBertForMaskedLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "output_past": true,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.55.3",
-  "type_vocab_size": 2,
-  "use_cache": true,
-  "vocab_size": 28996
+  "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:283b7b2e8fc1d79cfe3106fc4cdc44633798d4f94204a12ea614ed808269efba
-size 433386912
+oid sha256:70904d387a795d9ec9d07cc7552e90a2e7e1c9af2ffb0757a93cede65317c6f9
+size 267954768