initial commit

config.json

@@ -0,0 +1,45 @@
+{
+ "_name_or_path": "pdelobelle/robbert-v2-dutch-base",
+ "architectures": [
+ "RobertaForTokenClassification"
+ ],
+ "attention_probs_dropout_prob": 0.1,
+ "bos_token_id": 0,
+ "classifier_dropout": null,
+ "eos_token_id": 2,
+ "gradient_checkpointing": false,
+ "hidden_act": "gelu",
+ "hidden_dropout_prob": 0.1,
+ "hidden_size": 768,
+ "id2label": {
+ "0": "LABEL_0",
+ "1": "LABEL_1",
+ "2": "LABEL_2",
+ "3": "LABEL_3",
+ "4": "LABEL_4",
+ "5": "LABEL_5"
+ },
+ "initializer_range": 0.02,
+ "intermediate_size": 3072,
+ "label2id": {
+ "LABEL_0": 0,
+ "LABEL_1": 1,
+ "LABEL_2": 2,
+ "LABEL_3": 3,
+ "LABEL_4": 4,
+ "LABEL_5": 5
+ },
+ "layer_norm_eps": 1e-05,
+ "max_position_embeddings": 514,
+ "model_type": "roberta",
+ "num_attention_heads": 12,
+ "num_hidden_layers": 12,
+ "output_past": true,
+ "pad_token_id": 1,
+ "position_embedding_type": "absolute",
+ "torch_dtype": "float32",
+ "transformers_version": "4.18.0",
+ "type_vocab_size": 1,
+ "use_cache": true,
+ "vocab_size": 40000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:963feaf2d672866a16ad0fa717c6345473de1a45214ef35c143820ba897d11e2
+size 464775601

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "trim_offsets": true, "special_tokens_map_file": "./robbert-v2-dutch-base/special_tokens_map.json", "name_or_path": "pdelobelle/robbert-v2-dutch-base", "strip_accent": false, "tokenizer_class": "RobertaTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8005347e86c2b1fec202ac4958898c9551be64f3a767b150be8c72894b3d5754
+size 3119