Upload with huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/flan-ul2",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 16384,
+  "d_kv": 256,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "silu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-silu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 32,
+  "num_heads": 16,
+  "num_layers": 32,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

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": "4.27.1"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23f041731ecf70729c16f440e7307798f2e83de487e4084ae52fc3e72bb66484
+size 9385063505

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74cdbf225ac17c3f4788d78b3c0c70100cc2bbc92fb97c3d866f9cb75ed7f5d8
+size 9932435647

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5f795d76d13041559766ea0e8e82ad265fb84e8c5ca604133adeb459ccac619
+size 9932435599

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d29a29c07ca439b36cd6965d91ed56e555490cd76e0322f5f94aa609a463a78
+size 9921987407

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fef0d7fa5ff62b6eca1dad75debcc13f93207adf929bf678d15ecf1f80d215fa
+size 9999634821

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91668906e584985f0aa01bdb2c96accb0e77533e987a2277df97a00ff81c1a22
+size 9865399696

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd35bc96dfbcbe77c3ed6b306996ae41f7275f99b5142d69a5893aaedd89a069
+size 9999617133

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2066251633ef953ca3d71e7e4e27447ec8c0e6d993a3c05d8386bbf6981a3e
+size 9854912445

pytorch_model.bin.index.json

@@ -0,0 +1,751 @@
+{
+  "metadata": {
+    "total_size": 79417610240
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00008.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.24.layer.2.layer_norm.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00008.bin",
+    "decoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.25.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.26.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.27.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.28.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.29.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.30.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.31.layer.2.layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00005-of-00008.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00004-of-00008.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00008-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00008.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00008.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00004-of-00008.bin",
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "shared.weight": "pytorch_model-00001-of-00008.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}