Upload T5ForConditionalGeneration

config.json

@@ -1,22 +1,26 @@
 {
+  "_name_or_path": "google/flan-t5-small",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 2048,
+  "classifier_dropout": 0.0,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "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,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
@@ -51,7 +55,8 @@
     }
   },
   "tie_word_embeddings": false,
-  "transformers_version": "4.23.1",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
   "use_cache": true,
   "vocab_size": 32128
 }

generation_config.json

@@ -1,7 +1,6 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.27.0.dev0"
+  "transformers_version": "4.35.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dfb70afdcedceb9f9fae2f9b68e004ad934361fb35b9b2bd50b45ea90790fc8
-size 990345061
+oid sha256:e7fb40c6be901a7d46b384898cd502fbb198c98dec2a827ced9406db4919ab0f
+size 307867048