alessandropisent
/

DSI

Text2Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

alessandropisent commited on 29 days ago

Commit

5b4a7aa

•

1 Parent(s): af03fee

Upload T5ForConditionalGeneration

Files changed (2) hide show

config.json +6 -6
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -1,12 +1,12 @@
 {
-  "_name_or_path": "google-t5/t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
   "d_kv": 64,
-  "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": 12,
-  "num_heads": 12,
-  "num_layers": 12,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,

 {
+  "_name_or_path": "google-t5/t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
+  "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,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:185537a7defe66d3d601b13ae1f0e05f079aa454847cbce9e49224ab9566f941
-size 891644712

 version https://git-lfs.github.com/spec/v1
+oid sha256:332261a22982e4ad213908c31c054c68daf24d2e6eed3533ca978cb5c1e4af74
+size 242041896