Upload folder using huggingface_hub
Browse files- README.md +61 -0
- config.json +46 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: de
|
| 3 |
+
license: cc-by-4.0
|
| 4 |
+
base_model: lkonle/fiction-gbert-large
|
| 5 |
+
pipeline_tag: text-classification
|
| 6 |
+
tags:
|
| 7 |
+
- german
|
| 8 |
+
- literature
|
| 9 |
+
- digital-humanities
|
| 10 |
+
- narratology
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# de-setting-classifier
|
| 14 |
+
|
| 15 |
+
Satzweiser Klassifikator für die räumliche Darstellung in deutschsprachiger Prosa.
|
| 16 |
+
Feinabgestimmt auf [`lkonle/fiction-gbert-large`](https://huggingface.co/lkonle/fiction-gbert-large)
|
| 17 |
+
(BERT-large, für deutschsprachige erzählende Prosa vortrainiert).
|
| 18 |
+
|
| 19 |
+
## Kategorien
|
| 20 |
+
|
| 21 |
+
| Label | Deutsche Bezeichnung | Beschreibung |
|
| 22 |
+
|---------------------|-----------------------|------------------------------------------------------------------------|
|
| 23 |
+
| `action_space` | Aktionsraum | Raum, der durch Bewegung und direkten Kontakt einer Figur erfasst wird |
|
| 24 |
+
| `visual_space` | Anschauungsraum | Raum, wie er von einer Figur aus der Distanz wahrgenommen wird |
|
| 25 |
+
| `perceived_space` | gestimmter Raum | Raum, wie er Stimmung und Atmosphäre widerspiegelt |
|
| 26 |
+
| `descriptive_space` | Raumbeschreibung | Dinge/Objekte im Raum, ohne Bezug zu einer Figur |
|
| 27 |
+
| `no_space` | kein Raum | kein Raumbezug |
|
| 28 |
+
|
| 29 |
+
## Training
|
| 30 |
+
|
| 31 |
+
⟨Trainingskorpus (Umfang, Herkunft, Zeitraum), Annotationsverfahren, Anzahl Annotator:innen
|
| 32 |
+
und Inter-Annotator-Übereinstimmung ergänzen.⟩
|
| 33 |
+
|
| 34 |
+
## Evaluation
|
| 35 |
+
|
| 36 |
+
⟨Gütemaß (z. B. F1 pro Klasse und makro-gemittelt) auf zurückgehaltenem Testset ergänzen.⟩
|
| 37 |
+
|
| 38 |
+
## Verwendung
|
| 39 |
+
|
| 40 |
+
Über das begleitende Python-Paket [`de-setting-classifier`](⟨GitHub-URL ergänzen⟩):
|
| 41 |
+
|
| 42 |
+
```python
|
| 43 |
+
from de_setting_classifier import SpaceClassifier
|
| 44 |
+
|
| 45 |
+
clf = SpaceClassifier.from_pretrained("katrohrb/de-setting-classifier")
|
| 46 |
+
clf.predict("Er trat durch die Tür und schloss sie hinter sich.")
|
| 47 |
+
# → "action_space"
|
| 48 |
+
```
|
| 49 |
+
|
| 50 |
+
Oder direkt über `transformers`:
|
| 51 |
+
|
| 52 |
+
```python
|
| 53 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 54 |
+
|
| 55 |
+
tok = AutoTokenizer.from_pretrained("katrohrb/de-setting-classifier")
|
| 56 |
+
model = AutoModelForSequenceClassification.from_pretrained("katrohrb/de-setting-classifier")
|
| 57 |
+
```
|
| 58 |
+
|
| 59 |
+
## Zitation
|
| 60 |
+
|
| 61 |
+
⟨Bibliographische Angabe der zugrundeliegenden Studie ergänzen.⟩
|
config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "lkonle/fiction-gbert-large",
|
| 3 |
+
"adapters": {
|
| 4 |
+
"adapters": {},
|
| 5 |
+
"config_map": {},
|
| 6 |
+
"fusion_config_map": {},
|
| 7 |
+
"fusions": {}
|
| 8 |
+
},
|
| 9 |
+
"architectures": [
|
| 10 |
+
"BertForSequenceClassification"
|
| 11 |
+
],
|
| 12 |
+
"attention_probs_dropout_prob": 0.1,
|
| 13 |
+
"classifier_dropout": null,
|
| 14 |
+
"hidden_act": "gelu",
|
| 15 |
+
"hidden_dropout_prob": 0.1,
|
| 16 |
+
"hidden_size": 1024,
|
| 17 |
+
"id2label": {
|
| 18 |
+
"0": "perceived_space",
|
| 19 |
+
"1": "action_space",
|
| 20 |
+
"2": "visual_space",
|
| 21 |
+
"3": "descriptive_space",
|
| 22 |
+
"4": "no_space"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 4096,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"perceived_space": 0,
|
| 28 |
+
"action_space": 1,
|
| 29 |
+
"visual_space": 2,
|
| 30 |
+
"descriptive_space": 3,
|
| 31 |
+
"no_space": 4
|
| 32 |
+
},
|
| 33 |
+
"layer_norm_eps": 1e-12,
|
| 34 |
+
"max_position_embeddings": 512,
|
| 35 |
+
"model_type": "bert",
|
| 36 |
+
"num_attention_heads": 16,
|
| 37 |
+
"num_hidden_layers": 24,
|
| 38 |
+
"pad_token_id": 0,
|
| 39 |
+
"position_embedding_type": "absolute",
|
| 40 |
+
"problem_type": "single_label_classification",
|
| 41 |
+
"torch_dtype": "float32",
|
| 42 |
+
"transformers_version": "4.35.2",
|
| 43 |
+
"type_vocab_size": 2,
|
| 44 |
+
"use_cache": true,
|
| 45 |
+
"vocab_size": 31102
|
| 46 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b575a4610b6d0e51bce0920bc4eb805e34d39b9ed8a331b3259b387bd2ef3c9
|
| 3 |
+
size 1343010740
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"is_local": false,
|
| 7 |
+
"local_files_only": false,
|
| 8 |
+
"mask_token": "[MASK]",
|
| 9 |
+
"max_len": 512,
|
| 10 |
+
"model_max_length": 512,
|
| 11 |
+
"never_split": null,
|
| 12 |
+
"pad_token": "[PAD]",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"strip_accents": false,
|
| 15 |
+
"tokenize_chinese_chars": true,
|
| 16 |
+
"tokenizer_class": "BertTokenizer",
|
| 17 |
+
"unk_token": "[UNK]"
|
| 18 |
+
}
|