Upload T5ForSequenceClassification

config.json

@@ -1,29 +1,33 @@
 {
-  "_name_or_path": "xlm-roberta-base",
+  "_name_or_path": "VietAI/vit5-base",
   "architectures": [
-    "XLMRobertaForSequenceClassification"
+    "T5ForSequenceClassification"
   ],
-  "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,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "xlm-roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "classifier_dropout": 0.0,
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
   "problem_type": "single_label_classification",
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
   "torch_dtype": "float32",
-  "transformers_version": "4.32.0",
-  "type_vocab_size": 1,
+  "transformers_version": "4.32.1",
   "use_cache": true,
-  "vocab_size": 250002
+  "vocab_size": 36096
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873a50891333c3aa2e2d4beabd87c8bd864c2502a96a28f453c0c7299347fd5c
-size 1112249713
+oid sha256:2f747feee642b1a37c5b6d76788ab86dadfac34de7e986dd79bfda8e3f9b8b23
+size 906265441