Add checkpoint_1010000

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-xl",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 250112
+}

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cded4ece5122b52af01c8606cc98a621da6fb59189ad87e6a5682d5cd0487b2
+size 7938340473

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7bc19684b9eb3b9a62294fc284967a7cc7744fd5021eb97410e4e443fe3c56a
+size 7032322681

pytorch_model.bin.index.json

@@ -0,0 +1,566 @@
+{
+  "metadata": {
+    "total_size": 17019396096
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "lm_head.weight": "pytorch_model-00002-of-00002.bin",
+    "shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-large",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}