Upload BertForSequenceClassification

config.json

@@ -1,26 +1,22 @@
 {
   "_name_or_path": "ft-models",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "BertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0,
-  "bos_token_id": 2,
-  "classifier_dropout_prob": 0.1,
-  "down_scale_factor": 1,
-  "embedding_size": 128,
-  "eos_token_id": 3,
-  "gap_size": 0,
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0,
-  "hidden_size": 312,
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
     "0": "LABEL_0",
     "1": "LABEL_1",
     "2": "LABEL_2"
   },
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 1248,
+  "intermediate_size": 3072,
   "label2id": {
     "LABEL_0": 0,
     "LABEL_1": 1,
@@ -28,17 +24,20 @@
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
+  "model_type": "bert",
   "num_attention_heads": 12,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 4,
-  "num_memory_blocks": 0,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
   "transformers_version": "4.26.0",
   "type_vocab_size": 2,
-  "vocab_size": 31000
+  "use_cache": true,
+  "vocab_size": 48871
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3489f08cb589b72907ee08749bcea605d48dc31ee8a9b78fb5f2cadabff68bc2
-size 21393285
+oid sha256:9f00cb3b3655d3dc1cf0209359bc23571c3abe91f05e4e8f2d3892f980cb2bfb
+size 494376309