Upload model

README.md

@@ -1,3 +1,10 @@
----
-license: cc0-1.0
----
+# alephbertgimmel
+AlephBertGimmel - Modern Hebrew pretrained BERT model with a 128K token vocabulary.
+
+NOTE: This model was only trained with sequences of up to 128 tokens.
+
+When using AlephBertGimmel, please reference:
+
+Eylon Guetta, Avi Shmidman, Shaltiel Shmidman, Cheyn Shmuel Shmidman, Joshua Guedalia, Moshe Koppel, Dan Bareket, Amit Seker and Reut Tsarfaty, "Large Pre-Trained Models with Extra-Large Vocabularies: A Contrastive Analysis of Hebrew BERT Models and a New One to Outperform Them All", Nov 2022 [http://arxiv.org/abs/2211.15199]
+
+

config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 128000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8db77c3eed2371745af32d81daa029f382ff29eeaedd3b5918a732ea36812d91
+size 315233092