minwooeom
/

t5-qg

Text2Text Generation

Generated from Trainer

Inference Endpoints

text-generation-inference

Model card Files Files and versions Metrics Training metrics Community

minwooeom commited on Feb 24, 2023

Commit

8fb2a54

•

1 Parent(s): 2a1fa47

t5-qg

Files changed (2) hide show

config.json +6 -6
pytorch_model.bin +2 -2

config.json CHANGED Viewed

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 3072,
   "d_kv": 64,
-  "d_model": 768,
   "decoder_start_token_id": 0,
   "dense_act_fn": "relu",
   "dropout_rate": 0.1,
@@ -17,9 +17,9 @@
   "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": 0,
   "relative_attention_max_distance": 128,

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

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:145414a7e4c60cad9ada1bc978c9dc3d109acea373cd4253f0c5d1e9b2165423
-size 891619985

 version https://git-lfs.github.com/spec/v1
+oid sha256:1bf89d706cb55d313380832d29f11164bc9b1ba462705db3d49cbfd208677876
+size 242016345