Upload T5ForConditionalGeneration

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "T5_model_full_dataset_10epoch_training/checkpoint-26500",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 2,
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 2,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "max_length": 100,
+  "model_type": "t5",
+  "num_beams": 5,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 30000
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 2,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 1,
+  "max_length": 100,
+  "num_beams": 5,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c975fb1573863fd0916a43178ca702de55b7aa44d16e97bad2053fda3c49fa80
+size 977270632