pytorch_model.bin upload/update

config.json

@@ -1,35 +1,42 @@
 {
-  "_name_or_path": "google-bert/bert-base-uncased",
+  "_name_or_path": "google/mobilebert-uncased",
   "architectures": [
-    "BertForSequenceClassification"
+    "MobileBertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
   "id2label": {
     "0": "convo_ender",
     "1": "convo_starter"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
   "label2id": {
     "convo_ender": "0",
     "convo_starter": "1"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
   "pad_token_id": 0,
-  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.43.4",
+  "trigram_input": true,
+  "true_hidden_size": 128,
   "type_vocab_size": 2,
-  "use_cache": true,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
   "vocab_size": 30522
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1419fcaae6b8b84181b0098a08449df69af3c2a5167e5df6fbc4650a1a51d3d1
-size 437958648
+oid sha256:b0e601b26a035f04565d958a67439096290eb8adf6d1b32f61cfadff17e2ca19
+size 98470112