add Aleph-Alpha-GermanWeb-Grammar-Classifier-BERT model

README.md

@@ -0,0 +1,26 @@
+# Aleph-Alpha-GermanWeb-Classifier-BERT
+
+## Example Snippet
+
+```python
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification
+
+device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')
+
+model = BertForSequenceClassification.from_pretrained("Aleph-Alpha/Aleph-Alpha-GermanWeb-Grammar-Classifier-BERT", num_labels=2).to(device)
+
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+
+# disclaimer: short text is not in the model distribution
+text = 'Das ist ein Beispieltext, um die Grammatik zu überprüfen.'
+
+target_names = ['Low Quality', 'High Quality']
+
+with torch.no_grad():
+    prediction = torch.argmax(
+                    model(**tokenizer(text, return_tensors='pt', truncation=True, padding=True).to(device)).logits
+                ).item()
+print(target_names[prediction])
+
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d45b4eefc547d7752ed074fd4699ddfcfd98e7245be8596bc5ac663b60e47df
+size 437958648