Upload 9 files

__init__.py

@@ -0,0 +1,2 @@
+from .model import DebertaV3SequenceClassifier
+__all__ = ["DebertaV3SequenceClassifier"]

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "DebertaV3SequenceClassifier"
+  ],
+  "auto_map": {
+    "AutoModel": "model.DebertV3SequenceClassifier",
+    "AutoModelForSequenceClassification":
+      "model.DebertaV3SequenceClassifier"
+  },
+  "attention_probs_dropout_prob": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-07,
+  "legacy": true,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

model.py

@@ -0,0 +1,29 @@
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from transformers import (                # everything stays “DeBERTa” under the hood
+    DebertaV2Model,                       #     – we just add a new forward pass
+    DebertaV2PreTrainedModel,
+    DebertaV2Config,
+)
+from transformers.modeling_outputs import SequenceClassifierOutput
+
+class DebertaV3SequenceClassifier(DebertaV2PreTrainedModel):
+    def __init__(self, config: DebertaV2Config):
+        super().__init__(config)
+        self.deberta = DebertaV2Model(config)
+        self.d_model = self.deberta.embeddings.LayerNorm.weight.shape[0]
+        self.head = nn.Linear(self.d_model, 1)
+        self.post_init()
+    
+    @property
+    def device(self):
+        return self.head.weight.device
+
+    def forward(self, input_ids=None, attention_mask=None, labels=None, **kwargs):
+        x = self.deberta(input_ids, attention_mask=attention_mask).last_hidden_state
+        
+        logits = self.head(x.mean(dim=-2))
+        probs = F.sigmoid(logits)
+        return {'logits': logits, 'probs': probs}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a2594e82f30f9bff6181653a97f75c64d1d9bcfd02d477a45d30100ad5070c0
+size 735353660

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}