commit 2 from juno

config.json

@@ -1,11 +1,10 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "TurkuNLP/bert-base-finnish-uncased-v1",
   "architectures": [
     "BertForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "classifier_dropout": null,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
@@ -163,5 +162,5 @@
   "transformers_version": "4.12.3",
   "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "vocab_size": 50101
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdd456fdcf738176d9c28ae0501dfe73be3d4336512bb5804f65c9eb5e2c1f8e
-size 438222253
+oid sha256:edbf7edcee68d4d23b9fb313c1d91393f4cc6a1fb8deb4b7646514ea636a1cfb
+size 498368941

rust_model.ot

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac83d4fb4ec24b3fc1f341905a628b1192f3725e58f09839af24728c973cc793
-size 438203765
+oid sha256:844dd955ffa92ae773150abb1be18d5e7614a0c4674ac909c2c2fecd0728d616
+size 498350453

tokenizer_config.json

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