T5-base-first

config.json

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 2048,
+  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -18,9 +18,9 @@
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61b231709218d49f636789b725c505d499af38b43c503043fa187c65c30bdd06
-size 242041896
+oid sha256:54aacc04afb2a3a9ecda09428c3be14b03c92e69a9379b43319d385d5925f6e4
+size 891644712

tokenizer_config.json

@@ -928,11 +928,11 @@
     "<extra_id_98>",
     "<extra_id_99>"
   ],
-  "clean_up_tokenization_spaces": true,
+  "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "extra_ids": 100,
   "legacy": false,
-  "model_max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},
   "tokenizer_class": "T5Tokenizer",