Upload T5ForConditionalGeneration

config.json

@@ -1,26 +1,26 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "gauravkoradiya/T5-Finetuned-Summarization-DialogueDataset",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
   "d_ff": 2048,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "gelu_new",
+  "dense_act_fn": "relu",
   "dropout_rate": 0.1,
   "eos_token_id": 1,
-  "feed_forward_proj": "gated-gelu",
+  "feed_forward_proj": "relu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": true,
+  "is_gated_act": false,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
   "n_positions": 512,
-  "num_decoder_layers": 12,
-  "num_heads": 12,
-  "num_layers": 12,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
   "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
@@ -54,7 +54,6 @@
       "prefix": "translate English to Romanian: "
     }
   },
-  "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.38.1",
   "use_cache": true,

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2be6378a9414814ccd8369f856572bd12f0b8854b4423a08fcf8c602037e198
-size 495192780
+oid sha256:735d34a9fc1e120a9b59965c2627fef99a1d40ec6abc05a4997683872f74d831
+size 121030860