Upload NorbertForSequenceClassification

config.json

@@ -0,0 +1,167 @@
+{
+  "_name_or_path": "/cluster/work/projects/ec30/liljacs_/models/joint_full/norpac_46",
+  "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": "act_mixed",
+    "1": "act_neg",
+    "2": "act_pos",
+    "3": "cp_mixed",
+    "4": "cp_neg",
+    "5": "cp_pos",
+    "6": "dur_neg",
+    "7": "dur_pos",
+    "8": "excos_neg",
+    "9": "excos_pos",
+    "10": "ftc_neg",
+    "11": "ftc_pos",
+    "12": "gd_neg",
+    "13": "gd_pos",
+    "14": "incc_neg",
+    "15": "incc_pos",
+    "16": "iop_neg",
+    "17": "iop_pos",
+    "18": "irr_mixed",
+    "19": "irr_neg",
+    "20": "irr_pos",
+    "21": "isp_neg",
+    "22": "isp_pos",
+    "23": "lang_neg",
+    "24": "lang_pos",
+    "25": "med_mixed",
+    "26": "med_neg",
+    "27": "med_pos",
+    "28": "no-asp",
+    "29": "oits_mixed",
+    "30": "oits_neg",
+    "31": "oits_pos",
+    "32": "pip_mixed",
+    "33": "pip_neg",
+    "34": "pip_pos",
+    "35": "ppe_mixed",
+    "36": "ppe_neg",
+    "37": "ppe_pos",
+    "38": "ppr_mixed",
+    "39": "ppr_neg",
+    "40": "ppr_pos",
+    "41": "qfm_mixed",
+    "42": "qfm_neg",
+    "43": "qfm_pos",
+    "44": "sct_mixed",
+    "45": "sct_neg",
+    "46": "sct_pos",
+    "47": "slohs_mixed",
+    "48": "slohs_neg",
+    "49": "slohs_pos",
+    "50": "sr_mixed",
+    "51": "sr_neg",
+    "52": "sr_pos",
+    "53": "td_mixed",
+    "54": "td_neg",
+    "55": "td_pos",
+    "56": "tshp_mixed",
+    "57": "tshp_neg",
+    "58": "tshp_pos",
+    "59": "wol_neg",
+    "60": "wol_pos",
+    "61": "wtc_mixed",
+    "62": "wtc_neg",
+    "63": "wtc_pos",
+    "64": "wtp_mixed",
+    "65": "wtp_neg",
+    "66": "wtp_pos"
+  },
+  "intermediate_size": 2730,
+  "label2id": {
+    "act_mixed": 0,
+    "act_neg": 1,
+    "act_pos": 2,
+    "cp_mixed": 3,
+    "cp_neg": 4,
+    "cp_pos": 5,
+    "dur_neg": 6,
+    "dur_pos": 7,
+    "excos_neg": 8,
+    "excos_pos": 9,
+    "ftc_neg": 10,
+    "ftc_pos": 11,
+    "gd_neg": 12,
+    "gd_pos": 13,
+    "incc_neg": 14,
+    "incc_pos": 15,
+    "iop_neg": 16,
+    "iop_pos": 17,
+    "irr_mixed": 18,
+    "irr_neg": 19,
+    "irr_pos": 20,
+    "isp_neg": 21,
+    "isp_pos": 22,
+    "lang_neg": 23,
+    "lang_pos": 24,
+    "med_mixed": 25,
+    "med_neg": 26,
+    "med_pos": 27,
+    "no-asp": 28,
+    "oits_mixed": 29,
+    "oits_neg": 30,
+    "oits_pos": 31,
+    "pip_mixed": 32,
+    "pip_neg": 33,
+    "pip_pos": 34,
+    "ppe_mixed": 35,
+    "ppe_neg": 36,
+    "ppe_pos": 37,
+    "ppr_mixed": 38,
+    "ppr_neg": 39,
+    "ppr_pos": 40,
+    "qfm_mixed": 41,
+    "qfm_neg": 42,
+    "qfm_pos": 43,
+    "sct_mixed": 44,
+    "sct_neg": 45,
+    "sct_pos": 46,
+    "slohs_mixed": 47,
+    "slohs_neg": 48,
+    "slohs_pos": 49,
+    "sr_mixed": 50,
+    "sr_neg": 51,
+    "sr_pos": 52,
+    "td_mixed": 53,
+    "td_neg": 54,
+    "td_pos": 55,
+    "tshp_mixed": 56,
+    "tshp_neg": 57,
+    "tshp_pos": 58,
+    "wol_neg": 59,
+    "wol_pos": 60,
+    "wtc_mixed": 61,
+    "wtc_neg": 62,
+    "wtc_pos": 63,
+    "wtp_mixed": 64,
+    "wtp_neg": 65,
+    "wtp_pos": 66
+  },
+  "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:f7520b60d429ad82e43aeb05cde7a05cf2a95a2025d73319eb215fc1d382637c
+size 1417921780