Upload with huggingface_hub

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": "float16",
+  "transformers_version": "4.25.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

handler.py

@@ -0,0 +1,33 @@
+from typing import Dict, List, Any
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+import torch
+
+class EndpointHandler:
+    def __init__(self, path=""):
+        # load model and processor from path
+        self.model =  AutoModelForSeq2SeqLM.from_pretrained(path, device_map="auto", load_in_8bit=True)
+        self.tokenizer = AutoTokenizer.from_pretrained(path)
+
+    def __call__(self, data: Dict[str, Any]) -> Dict[str, str]:
+        """
+        Args:
+            data (:obj:):
+                includes the deserialized image file as PIL.Image
+        """
+        # process input
+        inputs = data.pop("inputs", data)
+        parameters = data.pop("parameters", None)
+
+        # preprocess
+        input_ids = self.tokenizer(inputs, return_tensors="pt").input_ids
+
+        # pass inputs with all kwargs in data
+        if parameters is not None:
+            outputs = self.model.generate(input_ids, **parameters)
+        else:
+            outputs = self.model.generate(input_ids)
+
+        # postprocess the prediction
+        prediction = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+
+        return [{"generated_text": prediction}]

pytorch_model-00001-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d88c064b5ab4a755f4074b7e436a59aeb3f283875ce4897ce917c52f76f71db
+size 1810667120

pytorch_model-00002-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:068936f7a52342643bb03abbc21fea5491b26b8c5b77f75453d5189a71c3bdd5
+size 1979741427

pytorch_model-00003-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d3897a23415ccaa69108b9c3039afaddd437470b93b555eddaca5f0ac8940a
+size 1979743792

pytorch_model-00004-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf1ed41b2ccfff9fcb6f41009adbdb5b983cd5159802ea11e4036305c6b9e3b2
+size 1979743792

pytorch_model-00005-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec813f29ed1a48a6977f8e067c2af723f65768cc1a20321da2165c35ba30dbce
+size 1979746157

pytorch_model-00006-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:baaa721bb3f64707afb3a441246a4798ac22ce21a8f70f47bdddd09836612822
+size 1944892748

pytorch_model-00007-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1499c61ef48677120f2c604e33a5238914ff0631a8bc93bee99a4be8fca6dd00
+size 1979745758

pytorch_model-00008-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887630c9c648417102f14230c70eb044836937031357475571e97d8d10fe4962
+size 1912639576

pytorch_model-00009-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d0a875023aed75e180c2949233feace793d4b70eb942e0047d9af642d4bcdec
+size 1979749138

pytorch_model-00010-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:240b99ef73676d797634e15bd0ac219f1f3955041037a3d9f2cac445145b3f7b
+size 1979748123

pytorch_model-00011-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39478b40703003c7bda9360bc968023841c8eed2f035f7ebda376dfe8bceff2b
+size 1946194389

pytorch_model-00012-of-00012.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18987c2797c79a6f4ca6542605a8115f65f772c614df6867eabc16753139e888
+size 1273782987

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-00006-of-00012.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00009-of-00012.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00012.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi.weight": "pytorch_model-00011-of-00012.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00012.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00008-of-00012.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00006-of-00012.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00012-of-00012.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00012.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00012.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00012.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00012.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00005-of-00012.bin",
+    "lm_head.weight": "pytorch_model-00012-of-00012.bin",
+    "shared.weight": "pytorch_model-00001-of-00012.bin"
+  }
+}