upload

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "T5Coref"
+  ],
+  "asp_activation": "relu",
+  "asp_dropout_rate": 0.3,
+  "asp_feature_emb_size": 20,
+  "asp_hidden_dim": 4096,
+  "asp_init_std": 0.02,
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "mention_end_id": 32103,
+  "mention_start_id": 32102,
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "pretrained_name_or_path": "google/flan-t5-xl",
+  "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": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 32104
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.33.3"
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ef1bf71b8c880777396b8d734c8711cf0c8df71bef3a8f29b102255424ce64
+size 9969693258

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:826389dbfa27d80fcbf665781a56bd50830f27ebc53349b371925db85616bd81
+size 1334357342

pytorch_model.bin.index.json

@@ -0,0 +1,579 @@
+{
+  "metadata": {
+    "total_size": 11303838988
+  },
+  "weight_map": {
+    "action_head.0.bias": "pytorch_model-00002-of-00002.bin",
+    "action_head.0.weight": "pytorch_model-00002-of-00002.bin",
+    "action_head.3.bias": "pytorch_model-00002-of-00002.bin",
+    "action_head.3.weight": "pytorch_model-00002-of-00002.bin",
+    "emb_rr_distance.weight": "pytorch_model-00002-of-00002.bin",
+    "lr_scorer.0.bias": "pytorch_model-00002-of-00002.bin",
+    "lr_scorer.0.weight": "pytorch_model-00002-of-00002.bin",
+    "lr_scorer.3.bias": "pytorch_model-00002-of-00002.bin",
+    "lr_scorer.3.weight": "pytorch_model-00002-of-00002.bin",
+    "rr_scorer.0.bias": "pytorch_model-00002-of-00002.bin",
+    "rr_scorer.0.weight": "pytorch_model-00002-of-00002.bin",
+    "rr_scorer.3.bias": "pytorch_model-00002-of-00002.bin",
+    "rr_scorer.3.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "t5.encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "t5.shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}