Upload NorbertForSequenceClassification

config.json

@@ -0,0 +1,83 @@
+{
+  "_name_or_path": "/cluster/work/projects/ec30/liljacs_/models/joint/norpac_titles_42",
+  "architectures": [
+    "NorbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "auto_map": {
+    "AutoConfig": "configuration_norbert.NorbertConfig",
+    "AutoModel": "modeling_norbert.NorbertModel",
+    "AutoModelForMaskedLM": "modeling_norbert.NorbertForMaskedLM",
+    "AutoModelForMultipleChoice": "modeling_norbert.NorbertForMultipleChoice",
+    "AutoModelForQuestionAnswering": "modeling_norbert.NorbertForQuestionAnswering",
+    "AutoModelForSequenceClassification": "modeling_norbert.NorbertForSequenceClassification",
+    "AutoModelForTokenClassification": "modeling_norbert.NorbertForTokenClassification"
+  },
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24"
+  },
+  "intermediate_size": 2730,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_all_encoded_layers": true,
+  "position_bucket_size": 32,
+  "problem_type": "multi_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "vocab_size": 50000
+}

configuration_norbert.py

@@ -0,0 +1,34 @@
+from transformers.configuration_utils import PretrainedConfig
+
+
+class NorbertConfig(PretrainedConfig):
+    """Configuration class to store the configuration of a `NorbertModel`.
+    """
+    def __init__(
+        self,
+        vocab_size=50000,
+        attention_probs_dropout_prob=0.1,
+        hidden_dropout_prob=0.1,
+        hidden_size=768,
+        intermediate_size=2048,
+        max_position_embeddings=512,
+        position_bucket_size=32,
+        num_attention_heads=12,
+        num_hidden_layers=12,
+        layer_norm_eps=1.0e-7,
+        output_all_encoded_layers=True,
+        **kwargs,
+    ):
+        super().__init__(**kwargs)
+
+        self.vocab_size = vocab_size
+        self.hidden_size = hidden_size
+        self.num_hidden_layers = num_hidden_layers
+        self.num_attention_heads = num_attention_heads
+        self.intermediate_size = intermediate_size
+        self.hidden_dropout_prob = hidden_dropout_prob
+        self.attention_probs_dropout_prob = attention_probs_dropout_prob
+        self.max_position_embeddings = max_position_embeddings
+        self.output_all_encoded_layers = output_all_encoded_layers
+        self.position_bucket_size = position_bucket_size
+        self.layer_norm_eps = layer_norm_eps

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699dc7b0b83e8d081856dcf814651024605ec1e9db71f7332b72a3f21bf3c0ce
+size 1417749580