Upload T5ForConditionalGeneration

config.json

@@ -1,28 +1,30 @@
 {
-  "_name_or_path": "google/t5-efficient-base-nl24",
+  "_name_or_path": "google/flan-t5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 3072,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
   "num_decoder_layers": 24,
-  "num_heads": 12,
+  "num_heads": 16,
   "num_layers": 24,
+  "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.22.2",
   "use_cache": true,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19849362d8d82d112ada8ece7ff17f098037f1470f6802745153c2f22f7c863a
-size 1684694407
+oid sha256:a3ae97706847f0c1b804fb22b36232808fbd6fb328f750a85e7afc642b1d458c
+size 3132781861