32k (2048)

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "data/plms/danish-legal-longformer-base",
+  "architectures": [
+    "LongformerForMaskedLM"
+  ],
+  "attention_mode": "longformer",
+  "attention_probs_dropout_prob": 0.1,
+  "attention_window": [
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128,
+    128
+  ],
+  "bos_token_id": 1,
+  "classifier_dropout": null,
+  "cls_token_id": 1,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "ignore_attention_mask": false,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2050,
+  "model_max_length": 2048,
+  "model_type": "longformer",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "sep_token_id": 2,
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26b0fa794cfc2bdb59f9415b7dc43d19067b3cb4d5cb8549dcda979c99863d2f
+size 532480795

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": "<mask>"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"model_max_length": 2048, "bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "special_tokens_map_file": "data/PLMs/danish-lm/danish-lex-lm-base/special_tokens_map.json", "name_or_path": "data/plms/danish-legal-longformer-base", "tokenizer_class": "PreTrainedTokenizerFast"}