Upload T5ForConditionalGeneration

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "t5-11b",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 65536,
+  "d_kv": 128,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 128,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66b91f75dc2e88e7ee10172bdfac58b0d01f5fe690ede903722caa0181997467
+size 4931282409

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c057269864ea209e933c548286d4b86cbeeba1c1a788fc9f463891ee16a4fc
+size 4998396760

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1319204cc6d892ea9baabb2eb609ddd2855865e2f96be74c07151864d61b696c
+size 4966155533

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d12c9bd45944bc18cd768a578d89be23255dffea1d440927fa4b6cc743333382
+size 4966152217

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39a0de9f02add7bad5bbba52e3b3e3ae4964aee205c85c32d9bad5f2ab333950
+size 2884428969

pytorch_model.bin.index.json

@@ -0,0 +1,519 @@
+{
+  "metadata": {
+    "total_size": 22812037120
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-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.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.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.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.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.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.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.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.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.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.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.weight": "pytorch_model-00004-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.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.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.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.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.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.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.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.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.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.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.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.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-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-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-00003-of-00005.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi.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-00002-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.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.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.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.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-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-00001-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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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"
+  }
+}