Upload BertForSequenceClassification

config.json

@@ -1,7 +1,11 @@
 {
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
   "attention_probs_dropout_prob": 0.1,
   "auto_map": {
-    "AutoConfig": "configuration_bert.BertConfig"
+    "AutoConfig": "configuration_bert.BertConfig",
+    "AutoModelForSequenceClassification": "modeling_bert.BertForSequenceClassification"
   },
   "classifier_dropout": null,
   "hidden_act": "gelu",
@@ -16,6 +20,7 @@
   "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
   "transformers_version": "4.33.3",
   "type_vocab_size": 2,
   "use_cache": true,

modeling_bert.py

@@ -50,14 +50,14 @@ class BertPooler(nn.Module):
 
     def __init__(self, config):
         super().__init__()
-        self.affine = nn.Linear(config.hidden_size, config.hidden_size)
+        self.dense = nn.Linear(config.hidden_size, config.hidden_size)
         self.activation = nn.Tanh()
 
     def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
         # We "pool" the model by simply taking the hidden state corresponding
         # to the first token.
         first_token_tensor = hidden_states[:, 0]
-        pooled_output = self.affine(first_token_tensor)
+        pooled_output = self.dense(first_token_tensor)
         pooled_output = self.activation(pooled_output)
         return pooled_output
 

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a3b02788cfd1334be6bb658442941d4adce843058fd92515fc5f7de80ba8694
+oid sha256:31b5cff2bb6cce0d41eceb729d8660438d177910122749eca6916b3f404c0f80
 size 438000689