Upload FlaxBertForPreTraining

config.json

@@ -1,43 +1,23 @@
 {
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
   "architectures": [
-    "BartModel"
+    "BertForPreTraining"
   ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 14,
-  "classifier_dropout": 0.0,
-  "d_model": 1024,
-  "decoder_attention_heads": 4,
-  "decoder_ffn_dim": 1024,
-  "decoder_layerdrop": 0.0,
-  "decoder_layers": 6,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "encoder_attention_heads": 4,
-  "encoder_ffn_dim": 1024,
-  "encoder_layerdrop": 0.0,
-  "encoder_layers": 6,
-  "eos_token_id": 82,
-  "forced_eos_token_id": 82,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "label2id": {
-    "LABEL_0": 0,
-    "LABEL_1": 1,
-    "LABEL_2": 2
-  },
-  "max_position_embeddings": 1024,
-  "model_type": "bart",
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
   "num_hidden_layers": 6,
-  "pad_token_id": 18,
-  "scale_embedding": false,
-  "transformers_version": "4.21.2",
+  "pad_token_id": 4,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.25.1",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 84
+  "vocab_size": 473
 }

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f30905e2a787c470160818dc6924585c26cc59f06586ae8d6d889fbc8e24c60
-size 412066738
+oid sha256:d3b476a0ba630169b9d88d7723db6c410c71c2eebad5dab92695661d7db5e345
+size 545494790