Upload MT5ForConditionalGeneration

config.json

@@ -1,63 +1,33 @@
 {
   "architectures": [
-    "T5ForConditionalGeneration"
+    "MT5ForConditionalGeneration"
   ],
+  "bos_token_id": null,
   "classifier_dropout": 0.0,
-  "d_ff": 3072,
+  "d_ff": 1024,
   "d_kv": 64,
-  "d_model": 768,
+  "d_model": 512,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
   "dtype": "float32",
   "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "feed_forward_proj": "gated-gelu",
   "initializer_factor": 1.0,
   "is_decoder": false,
   "is_encoder_decoder": true,
-  "is_gated_act": false,
+  "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,
-  "output_past": true,
+  "model_type": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
   "pad_token_id": 0,
   "relative_attention_max_distance": 128,
   "relative_attention_num_buckets": 32,
-  "scale_decoder_outputs": true,
-  "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": true,
-  "transformers_version": "5.0.0",
+  "tokenizer_class": "T5Tokenizer",
+  "transformers_version": "5.2.0",
   "use_cache": false,
-  "vocab_size": 32128
+  "vocab_size": 250112
 }

generation_config.json

@@ -29,7 +29,7 @@
   "temperature": 1.0,
   "top_k": 50,
   "top_p": 1.0,
-  "transformers_version": "5.0.0",
+  "transformers_version": "5.2.0",
   "typical_p": 1.0,
   "use_cache": true
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22016cd906ea90e70ec567de45e184d89825343f8a55870699c0d13644a36087
-size 891644712
+oid sha256:a8c7ad8e49979a91e3cfc7afc37ea1a4f5234d71f553190387a6f4f6235e1f95
+size 2225188480