Upload T5ForConditionalGeneration

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "outputs/flan-t5-xxl-outputs-all-train-processed",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "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": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": false,
+  "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": "4.26.1"
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5087923d13ff5b1112d72e59eb248983cf36036dfb8e0568c3de5920cbb4064d
+size 9452284099

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b003a21c68f7215a35f4e6844c6256c1da9cee285968890ac22d460f65ab83ae
+size 9597030149

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e872bc2fddbcff74fa05333d348fcf61f77454d86ec3f72abc49e6922fe1459
+size 9955673595

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55d56f2d682f1d2a20483bf68a7ff7a7be8ee44b5c32c46d7a587d35b90e9340
+size 9999740781

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b1efffd9eeee7773c330b127b7a438374aaa0ffdbd6e275dd255f8c16ad18f
+size 6063168980

pytorch_model.bin.index.json

@@ -0,0 +1,567 @@
+{
+  "metadata": {
+    "total_size": 45594099712
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "shared.weight": "pytorch_model-00001-of-00005.bin"
+  }
+}