add pytorch model

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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": "mt5",
+  "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,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

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": "4.28.0"
+}

pytorch_model-00001-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38c682c8af53b76f6693d15898a8375958917c35332e95cac47d43bafad14c5a
+size 9936585273

pytorch_model-00002-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1423f0a93a510bd1af2a308683309ecc9b9cc8530d4ef4dd2540493f16b1759a
+size 9865469787

pytorch_model-00003-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89e583dc76d04f3c698cdd6cb8938e7830e8dffd61f9f7d499a4bb1c18da3144
+size 9869493707

pytorch_model-00004-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ef42279e83b6e0496dad37cfca9f72f8b9f36cf5fe8a30f5058d6bfb511f0ca
+size 9999743807

pytorch_model-00005-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c8152468f8ec8aa4281b81e703ec9accc26003d89a049de6b631cfc46a51e4
+size 9999742830

pytorch_model-00006-of-00006.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5785ddd74d094670d852afacd280f90c43bf0ba7b76a1f8b6571c53bfb48a26
+size 6111225601

pytorch_model.bin.index.json

@@ -0,0 +1,566 @@
+{
+  "metadata": {
+    "total_size": 55782064128
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00006.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00004-of-00006.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00003-of-00006.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00006-of-00006.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00006.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00006.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00003-of-00006.bin",
+    "lm_head.weight": "pytorch_model-00006-of-00006.bin",
+    "shared.weight": "pytorch_model-00001-of-00006.bin"
+  }
+}