Upload RobertaForSequenceClassification

config.json

@@ -1,37 +1,40 @@
 {
-  "_name_or_path": "distilbert-base-uncased",
-  "activation": "gelu",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "DistilBertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "attention_dropout": 0.1,
-  "dim": 768,
-  "dropout": 0.1,
-  "hidden_dim": 3072,
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
   "id2label": {
-    "0": "expository",
+    "0": "procedural",
     "1": "probing_exploring",
-    "2": "procedural",
-    "3": "other"
+    "2": "other",
+    "3": "expository"
   },
   "initializer_range": 0.02,
+  "intermediate_size": 3072,
   "label2id": {
-    "expository": 0,
-    "other": 3,
+    "expository": 3,
+    "other": 2,
     "probing_exploring": 1,
-    "procedural": 2
+    "procedural": 0
   },
-  "max_position_embeddings": 512,
-  "model_type": "distilbert",
-  "n_heads": 12,
-  "n_layers": 6,
-  "pad_token_id": 0,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
-  "qa_dropout": 0.1,
-  "seq_classif_dropout": 0.2,
-  "sinusoidal_pos_embds": false,
-  "tie_weights_": true,
   "torch_dtype": "float32",
   "transformers_version": "4.25.1",
-  "vocab_size": 30522
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d30c4642c65dbccc92ff258fae6377761585bd0602126059507c92efb5f08d2
-size 267861677
+oid sha256:b558c1a2ade1823a7238bcdf068b4a282c77e1690f14914a52b71af0dff25644
+size 498668213