Upload T5ForConditionalGeneration

config.json

@@ -1,60 +1,32 @@
 {
-  "_name_or_path": "t5-small",
+  "_name_or_path": "ai-forever/FRED-T5-large",
   "architectures": [
     "T5ForConditionalGeneration"
   ],
-  "d_ff": 2048,
+  "d_ff": 2816,
   "d_kv": 64,
-  "d_model": 512,
+  "d_model": 1024,
   "decoder_start_token_id": 0,
-  "dense_act_fn": "relu",
+  "dense_act_fn": "gelu_new",
   "dropout_rate": 0.1,
-  "eos_token_id": 1,
-  "feed_forward_proj": "relu",
+  "eos_token_id": 2,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
   "initializer_factor": 1.0,
   "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": 6,
-  "num_heads": 8,
-  "num_layers": 6,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "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": "4.28.0",
   "use_cache": true,
-  "vocab_size": 32128
+  "vocab_size": 50364
 }

generation_config.json

@@ -1,7 +1,7 @@
 {
   "_from_model_config": true,
   "decoder_start_token_id": 0,
-  "eos_token_id": 1,
+  "eos_token_id": 2,
   "pad_token_id": 0,
   "transformers_version": "4.28.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a89105e464d0b9f15888499285bff3be5059cd4fe5f143a204ef35321a1b314
-size 242071641
+oid sha256:753a3b22bbf064b9cd9d5853d757a006174030a5f120560ff2ee9e7f95aa15b0
+size 3282182981