Upload RobertaForSequenceClassification

config.json

@@ -1,34 +1,28 @@
 {
-  "_name_or_path": "albert-large-v2",
+  "_name_or_path": "roberta-base",
   "architectures": [
-    "AlbertForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
-  "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,
-  "hidden_act": "gelu_new",
-  "hidden_dropout_prob": 0,
-  "hidden_size": 1024,
+  "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,
   "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "albert",
-  "net_structure_type": 0,
-  "num_attention_heads": 16,
-  "num_hidden_groups": 1,
-  "num_hidden_layers": 24,
-  "num_memory_blocks": 0,
-  "pad_token_id": 0,
+  "intermediate_size": 3072,
+  "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",
   "torch_dtype": "float32",
   "transformers_version": "4.34.0",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
+  "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:c4b2655cf1f26c1b321eaff4220f7b0fc7d9f00d7b1bfc6f07d40d620b4c7c57
-size 70753346
+oid sha256:adc8aa7f48d48ee9bebe183698a44bdd96466b033786da86d601bdeae7d11cd2
+size 498657649