Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+language:
+- da
+license: apache-2.0
+tags:
+- token-classification
+- ner
+- danish
+- modernbert
+datasets:
+- alexandrainst/dane
+metrics:
+- f1
+- precision
+- recall
+pipeline_tag: token-classification
+widget:
+- text: "Jens Peter Hansen bor i København og arbejder hos Novo Nordisk."
+---
+
+# ModernBERT Danish NER (Base)
+
+Danish Named Entity Recognition model fine-tuned from [`AI-Sweden-Models/ModernBERT-base`](https://huggingface.co/AI-Sweden-Models/ModernBERT-base) on the [DaNE](https://huggingface.co/datasets/alexandrainst/dane) dataset.
+
+## Benchmark: DaNE Test Set
+
+| Entity | Precision | Recall | F1 | Support |
+|--------|-----------|--------|----|---------|
+| PER | 0.8962 | 0.9061 | 0.9011 | 181 |
+| ORG | 0.6929 | 0.6299 | 0.6599 | 154 |
+| LOC | 0.7500 | 0.8969 | 0.8169 | 97 |
+| MISC | 0.4878 | 0.6316 | 0.5505 | 95 |
+| **micro avg** | **0.7260** | **0.7742** | **0.7493** | |
+
+## Entity Types
+
+- **PER**: Person names
+- **ORG**: Organizations
+- **LOC**: Locations
+- **MISC**: Miscellaneous entities
+
+## Usage
+
+```python
+from transformers import pipeline
+
+ner = pipeline("ner", model="thomasbeste/modernbert-da-ner-base", aggregation_strategy="simple")
+results = ner("Jens Peter Hansen bor i København og arbejder hos Novo Nordisk.")
+for entity in results:
+    print(f"{entity['word']}: {entity['entity_group']} ({entity['score']:.3f})")
+```
+
+## Training Details
+
+- **Base model**: AI-Sweden-Models/ModernBERT-base
+- **Dataset**: DaNE (alexandrainst/dane) — 4,383 train / 564 val / 565 test sentences
+- **Epochs**: 10
+- **Learning rate**: 2e-5
+- **Batch size**: 16
+- **Optimizer**: AdamW (weight decay 0.01, warmup ratio 0.1)
+- **Precision**: bf16
+- **Max sequence length**: 256

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "ModernBertForTokenClassification"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "classifier_activation": "silu",
+  "classifier_bias": false,
+  "classifier_dropout": 0.0,
+  "classifier_pooling": "mean",
+  "cls_token_id": 50281,
+  "decoder_bias": true,
+  "deterministic_flash_attn": false,
+  "dtype": "float32",
+  "embedding_dropout": 0.0,
+  "eos_token_id": null,
+  "global_attn_every_n_layers": 3,
+  "global_rope_theta": 160000.0,
+  "gradient_checkpointing": false,
+  "hidden_activation": "gelu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "B-PER",
+    "2": "I-PER",
+    "3": "B-ORG",
+    "4": "I-ORG",
+    "5": "B-LOC",
+    "6": "I-LOC",
+    "7": "B-MISC",
+    "8": "I-MISC"
+  },
+  "initializer_cutoff_factor": 2.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 1152,
+  "label2id": {
+    "B-LOC": 5,
+    "B-MISC": 7,
+    "B-ORG": 3,
+    "B-PER": 1,
+    "I-LOC": 6,
+    "I-MISC": 8,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "local_attention": 128,
+  "local_rope_theta": 10000.0,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "mlp_dropout": 0.0,
+  "model_type": "modernbert",
+  "norm_bias": false,
+  "norm_eps": 1e-05,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 22,
+  "pad_token_id": 5,
+  "position_embedding_type": "absolute",
+  "repad_logits_with_grad": false,
+  "sep_token_id": 50282,
+  "sparse_pred_ignore_index": -100,
+  "sparse_prediction": false,
+  "transformers_version": "4.57.6",
+  "vocab_size": 50368
+}

dane_test_results.json

@@ -0,0 +1,30 @@
+{
+  "LOC": {
+    "precision": 0.75,
+    "recall": 0.8969072164948454,
+    "f1": 0.8169014084507044,
+    "number": 97.0
+  },
+  "MISC": {
+    "precision": 0.4878048780487805,
+    "recall": 0.631578947368421,
+    "f1": 0.5504587155963302,
+    "number": 95.0
+  },
+  "ORG": {
+    "precision": 0.6928571428571428,
+    "recall": 0.6298701298701299,
+    "f1": 0.6598639455782312,
+    "number": 154.0
+  },
+  "PER": {
+    "precision": 0.8961748633879781,
+    "recall": 0.9060773480662984,
+    "f1": 0.9010989010989011,
+    "number": 181.0
+  },
+  "overall_precision": 0.7259786476868327,
+  "overall_recall": 0.7741935483870968,
+  "overall_f1": 0.7493112947658401,
+  "overall_accuracy": 0.9662182912597507
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f11228e598204cf04f36f0f8da3f4dacf11681e62fc81529630d1e02e3a7fd9
+size 598461316

special_tokens_map.json

@@ -0,0 +1,41 @@
+{
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>"
+  ],
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,73 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|padding|>",
+    "<|endoftext|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a854acade4c13a56793e29242ac351ee2134cd05c84043363a5b9cfe70d98471
+size 5841