first release

README.md

@@ -0,0 +1,31 @@
+---
+language: da
+tags:
+- danish
+- bert
+- sentiment
+- polarity
+license: cc-by-4.0
+widget:
+- text: "Sikke en dejlig dag det er i dag"
+---
+# Danish BERT fine-tuned for Sentiment Analysis <img src="https://raw.githubusercontent.com/ebanalyse/NERDA/main/logo.png" align="right" height=150/>
+
+This model detects polarity ('positive', 'neutral', 'negative') of danish texts.
+
+It is trained and tested on Tweets annotated by [Alexandra Institute](https://github.com/alexandrainst). The model is trained with the [`senda`](https://github.com/ebanalyse/senda) package.
+
+Here is an example of how to load the model in PyTorch using the [🤗Transformers](https://github.com/huggingface/transformers) library:
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+tokenizer = AutoTokenizer.from_pretrained("pin/senda")
+model = AutoModelForSequenceClassification.from_pretrained("pin/senda")
+
+# create 'senda' sentiment analysis pipeline 
+senda_pipeline = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
+
+text = "Sikke en dejlig dag det er i dag"
+# 'what a lovely day'
+senda_pipeline("Sikke en dejlig dag det er i dag")
+```

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "./results/checkpoint-900",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "negativ",
+    "1": "neutral",
+    "2": "positiv"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "negativ": 0,
+    "neutral": 1,
+    "positiv": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.5.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf99d3a3c56e417ed3d4fb10d51a4fba9fbc008545b296336dbfe911c981cfc
+size 442566130

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +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, "special_tokens_map_file": null, "name_or_path": "Maltehb/danish-bert-botxo", "do_basic_tokenize": true, "never_split": null}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde9e18bd59ab66453c2401ac48131b3281dc7cfd5aadb705a53803fc702abef
+size 2351