Upload T5ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "/kaggle/working/output/outputs/simplet5-epoch-0-train-loss-0.7146-val-loss-0.6288/",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -7,11 +7,13 @@
   "d_kv": 64,
   "d_model": 768,
   "decoder_start_token_id": 0,
+  "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,
   "model_type": "t5",
   "n_positions": 512,
@@ -53,7 +55,7 @@
   },
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.16.2",
+  "transformers_version": "4.26.1",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:711b2dc33560ae722cdff067659d1ec98d1f055aaa498184ef7cc4e0c5f0d8fa
-size 990438349
+oid sha256:6b4aba14d4a6d8d1a994f93de865ce297fd832f9212c7d4112c274c40a3297b0
+size 990404917