Upload 8 files

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "dbmdz/bert-base-german-uncased",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "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": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8ae3e6010782af7a52f6a98ec3954090c03204295722bdad2d6a54f3f8cb49e
+size 439733088

model_script.py

@@ -0,0 +1,46 @@
+import torch
+from torch import nn
+from transformers import AutoModel
+
+class CustomModel(torch.nn.Module):
+    def __init__(self, model_path, dropout=0.1, hidden_dim=768):
+        super().__init__()
+        self.metric_names = ['valence', 'arousal', 'imageability']
+        self.dropout_rate = dropout
+        self.hidden_dim = hidden_dim
+
+        self.bert = AutoModel.from_pretrained(model_path)
+
+        for name in self.metric_names:
+            setattr(self, name, nn.Linear(hidden_dim, 1))
+            setattr(self, 'l_1_' + name, nn.Linear(hidden_dim, hidden_dim))
+
+        self.layer_norm = nn.LayerNorm(self.hidden_dim)
+        self.relu = nn.ReLU()
+        self.dropout = nn.Dropout(self.dropout_rate)
+        self.sigmoid = nn.Sigmoid()
+
+    def save_pretrained(self, save_directory):
+        self.bert.save_pretrained(save_directory)
+        torch.save(self.state_dict(), f'{save_directory}/pytorch_model.bin')
+
+    @classmethod
+    def from_pretrained(cls, model_dir, dropout=0.2, hidden_dim=768):
+        model = cls(model_dir, dropout, hidden_dim)
+        state_dict = torch.load(f'{model_dir}/pytorch_model.bin', map_location=torch.device('cpu'))
+        model.load_state_dict(state_dict)
+        return model
+
+    def forward(self, *args):
+        _, x = self.bert(*args, return_dict=False)
+        output = self.rate_embedding(x)
+        return output
+
+    def rate_embedding(self, x):
+        output_ratings = []
+        for name in self.metric_names:
+            first_layer = self.relu(self.dropout(self.layer_norm(getattr(self, 'l_1_' + name)(x) + x)))
+            second_layer = self.sigmoid(getattr(self, name)(first_layer))
+            output_ratings.append(second_layer)
+
+        return output_ratings

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03b34ab92fefd070a720ae9edf8879e36f73c40e4d148c061b046430998d4170
+size 446897118

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_len": 512,
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}