Model save

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "google/flan-t5-base",
+  "_name_or_path": "google/mt5-base",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
@@ -16,7 +16,6 @@
   "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,
@@ -24,38 +23,10 @@
   "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,
+  "tokenizer_class": "T5Tokenizer",
   "torch_dtype": "float32",
   "transformers_version": "4.29.2",
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 250112
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa647a1bad9116dee51f6487e89ca17795c06a2e920fdef16abb7c38611dcd06
-size 990408885
+oid sha256:8346845c088acb8beb30fac53d47ed6e53476e680818909b498815da2c86d645
+size 2329702581