Upload T5ForConditionalGeneration

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/t5-v1_1-base",
+  "_name_or_path": "google/flan-t5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -17,6 +17,7 @@
   "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,
@@ -24,8 +25,37 @@
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
+  "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,
-  "torch_dtype": "float32",
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.34.1",
   "use_cache": true,
   "vocab_size": 32128

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74e1ff33b8e6e56420ada8ce274b158c770040cf7acf86c6bd891c8ca1b9069f
-size 990405362
+oid sha256:d67332e5cdb2f8320c50056d7a8f4bb42944e7ac3dbc087f1fc02d3f04337c89
+size 495249650