Upload T5ForConditionalGeneration

config.json

@@ -3,29 +3,59 @@
     "T5ForConditionalGeneration"
   ],
   "classifier_dropout": 0.0,
-  "d_ff": 64,
-  "d_kv": 2,
-  "d_model": 16,
-  "decoder_layers": 2,
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 24,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
-  "encoder_layers": 2,
+  "dtype": "float32",
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
-  "num_decoder_layers": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "n_positions": 512,
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "torch_dtype": "float32",
-  "transformers_version": "4.55.0.dev0",
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0.dev0",
   "use_cache": true,
-  "vocab_size": 32203
+  "vocab_size": 32128
 }

generation_config.json

@@ -3,5 +3,5 @@
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.55.0.dev0"
+  "transformers_version": "4.57.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12489bb86d1727a3bec9677c05481516806e593d27ad2a27ee0ee0d449dda3dd
-size 2251488
+oid sha256:1bb692c184df542894fdaa46560ce0dc3d06db0c2ff51d79a4f155aee4ce44fd
+size 14453368