Initial commit

.gitattributes

@@ -32,3 +32,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00002-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00003-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00004-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+pytorch_model-00001-of-00004.bin filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+spiece.model filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|sep|>": 250100
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/mt0-xxl-mt",
+  "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,
+  "num_beams": 3,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.27.3",
+  "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": "4.27.3"
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fdef8bf1a283b71f7c90d5cec12fb1c2abf620e0b4937909cc92112077beddd
+size 9867428718

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d5b9f3fdd8da03cd0c1a7fea8aea28fdc0083f59d510f0541bfdd6cd9b0403f
+size 9968139973

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb140319839bc918161e483f9f311eea3e814f5ad3192942a751d949ca2ff7dd
+size 9865485135

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c39ddd277499e570aaf3c15c900426388dd1a53014494a6497afbd807a3230
+size 2216707933

pytorch_model.bin.index.json

@@ -0,0 +1,566 @@
+{
+  "metadata": {
+    "total_size": 31917563904
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
+    "shared.weight": "pytorch_model-00001-of-00004.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "<|sep|>",
+  "unk_token": "<unk>"
+}

spiece.model

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6e91cce244397ff135b91035b0bc1f3188f99d7db810dab53af797c15fc886a
+size 16315305

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}