Upload RobertaForSequenceClassification

config.json

@@ -1,32 +1,29 @@
 {
-  "_name_or_path": "checkpoint-6000",
+  "_name_or_path": "checkpoint-23000",
   "architectures": [
-    "DebertaForSequenceClassification"
+    "RobertaForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-07,
-  "max_position_embeddings": 512,
-  "max_relative_positions": -1,
-  "model_type": "deberta",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 24,
-  "pad_token_id": 0,
-  "pooler_dropout": 0,
-  "pooler_hidden_act": "gelu",
-  "pooler_hidden_size": 1024,
-  "pos_att_type": [
-    "c2p",
-    "p2c"
-  ],
-  "position_biased_input": false,
-  "relative_attention": true,
+  "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": "4.30.0",
-  "type_vocab_size": 0,
+  "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:eaa3d89770510021e65d1819b508cd3ad43dca4bf188dbfbb3220df54224910c
-size 1624993073
+oid sha256:a24ce1777329370e76eea9886c534275af6c354961832301130293f65e7a7500
+size 498659253