Upload model

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "google/t5-v1_1-xxl",
+  "_name_or_path": "google/flan-t5-xl",
   "architectures": [
     "T5EncoderModel"
   ],
-  "d_ff": 10240,
+  "d_ff": 5120,
   "d_kv": 64,
-  "d_model": 4096,
+  "d_model": 2048,
   "decoder_start_token_id": 0,
   "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
@@ -16,13 +16,43 @@
   "is_gated_act": true,
   "layer_norm_epsilon": 1e-06,
   "model_type": "t5",
+  "n_positions": 512,
   "num_decoder_layers": 24,
-  "num_heads": 64,
+  "num_heads": 32,
   "num_layers": 24,
   "output_past": true,
   "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",
   "transformers_version": "4.23.1",

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9a1d296c137db2bdc9579e0bdf4ed488347d5d437fdb6b64631837c6fefac76
+size 4894182509