Initial commit for all files

config.json

@@ -0,0 +1,20 @@
+{
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "megatron-bert",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_type": "BertWordPieceCase",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 50176
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e732e5850c6e5c2e4867c3d323571ced0faaaf4934327596c14afa688ff86b5a
+size 3246067143

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "TurkuNLP/bert-base-finnish-cased-v1",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}