Duplicate from kalpeshk2011/dipper-paraphraser-xxl

Co-authored-by: Kalpesh Krishna <kalpeshk2011@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,99 @@
+---
+language: 
+  - en
+tags:
+- t5
+- xxl
+- rewriting
+- paraphrase
+- paraphrase-generation
+- paraphrasing
+- pytorch
+- text-generation
+- text2text-generation
+license: "apache-2.0"
+---
+
+This is the HuggingFace model release of our paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense".
+
+## Paper and Github Repository
+
+Paper: https://arxiv.org/abs/2303.13408  
+Code: https://github.com/martiansideofthemoon/ai-detection-paraphrases  
+Usage instructions: https://github.com/martiansideofthemoon/ai-detection-paraphrases#running-the-paraphraser-model-dipper
+
+## What is DIPPER?
+
+DIPPER ("**Di**scourse **P**ara**p**hras**er**") is a 11B parameter paraphrase generation model built by fine-tuning T5-XXL. DIPPER possesses two unique features that help its outputs evade AI-generated text detectors:
+
+* *Paraphrasing long-form text in context*: Most modern paraphrasers are exclusively trained on sentence-level data, ignoring discourse-level information. However, many critical use cases of LLMs involve generating long-form text in responses to detailed userspecified prompts. Thus, we train DIPPER to paraphrase paragraph-length texts, re-order content, and optionally leverage context such as input prompts.
+
+* *Controlling output diversity*: Another weakness of existing paraphrasers is that they lack an easy way to control output diversity. An attacker may want to apply just the minimum amount of lexical and syntactic modifications necessary to evade a detection algorithm. DIPPER provides users with two intuitive scalar control knobs at inference time that are trained end-to-end: one controls the lexical diversity of the paraphrase, and the other controls the amount of content re-ordering.
+
+We leverage the PAR3 dataset publicly released by Thai et al. (2022) to train DIPPER. This dataset contains multiple translations of non-English novels into English aligned at a paragraph level (e.g., it contains both the Henry Morley and Robert Adams translations of Voltaire’s Candide), which we treat as paragraphlevel paraphrases and use to train our paraphraser.
+
+## Using DIPPER
+
+Full instructions: https://github.com/martiansideofthemoon/ai-detection-paraphrases#running-the-paraphraser-model-dipper
+
+We suggest using the code below to use the model correctly:
+
+```
+class DipperParaphraser(object):
+    def __init__(self, model="kalpeshk2011/dipper-paraphraser-xxl", verbose=True):
+        time1 = time.time()
+        self.tokenizer = T5Tokenizer.from_pretrained('google/t5-v1_1-xxl')
+        self.model = T5ForConditionalGeneration.from_pretrained(model)
+        if verbose:
+            print(f"{model} model loaded in {time.time() - time1}")
+        self.model.cuda()
+        self.model.eval()
+
+    def paraphrase(self, input_text, lex_diversity, order_diversity, prefix="", sent_interval=3, **kwargs):
+        """Paraphrase a text using the DIPPER model.
+
+        Args:
+            input_text (str): The text to paraphrase. Make sure to mark the sentence to be paraphrased between <sent> and </sent> blocks, keeping space on either side.
+            lex_diversity (int): The lexical diversity of the output, choose multiples of 20 from 0 to 100. 0 means no diversity, 100 means maximum diversity.
+            order_diversity (int): The order diversity of the output, choose multiples of 20 from 0 to 100. 0 means no diversity, 100 means maximum diversity.
+            **kwargs: Additional keyword arguments like top_p, top_k, max_length.
+        """
+        assert lex_diversity in [0, 20, 40, 60, 80, 100], "Lexical diversity must be one of 0, 20, 40, 60, 80, 100."
+        assert order_diversity in [0, 20, 40, 60, 80, 100], "Order diversity must be one of 0, 20, 40, 60, 80, 100."
+
+        lex_code = int(100 - lex_diversity)
+        order_code = int(100 - order_diversity)
+
+        input_text = " ".join(input_text.split())
+        sentences = sent_tokenize(input_text)
+        prefix = " ".join(prefix.replace("\n", " ").split())
+        output_text = ""
+
+        for sent_idx in range(0, len(sentences), sent_interval):
+            curr_sent_window = " ".join(sentences[sent_idx:sent_idx + sent_interval])
+            final_input_text = f"lexical = {lex_code}, order = {order_code}"
+            if prefix:
+                final_input_text += f" {prefix}"
+            final_input_text += f" <sent> {curr_sent_window} </sent>"
+
+            final_input = self.tokenizer([final_input_text], return_tensors="pt")
+            final_input = {k: v.cuda() for k, v in final_input.items()}
+
+            with torch.inference_mode():
+                outputs = self.model.generate(**final_input, **kwargs)
+            outputs = self.tokenizer.batch_decode(outputs, skip_special_tokens=True)
+            prefix += " " + outputs[0]
+            output_text += " " + outputs[0]
+
+        return output_text
+
+if __name__ == "__main__":
+    dp = DipperParaphraser()
+
+    prompt = "In a shocking finding, scientist discovered a herd of unicorns living in a remote valley."
+    input_text = "They have never been known to mingle with humans. Today, it is believed these unicorns live in an unspoilt environment which is surrounded by mountains. Its edge is protected by a thick wattle of wattle trees, giving it a majestic appearance. Along with their so-called miracle of multicolored coat, their golden coloured feather makes them look like mirages. Some of them are rumored to be capable of speaking a large amount of different languages. They feed on elk and goats as they were selected from those animals that possess a fierceness to them, and can \"eat\" them with their long horns."
+
+    print(f"Input = {prompt} <sent> {input_text} </sent>\n")
+    output_l60_sample = dp.paraphrase(input_text, lex_diversity=60, order_diversity=0, prefix=prompt, do_sample=True, top_p=0.75, top_k=None, max_length=512)
+    print(f"Output (Lexical diversity = 60, Sample p = 0.75) = {output_l60_sample}\n")
+```

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/t5-v1_1-xxl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e345f0532f9650d4393cd57e708d97006e61d9085635c4585a1f2b33fc3224c8
+size 9452284099

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12536494befe1a5e47ea1d879fffb7d5cb58c9ae6fc1cea6e7fe07c27ba24b50
+size 9597030149

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f4d02fc520ad920fa17d34bae0ccf89d17bc20ec06d271bf2274f0c42d06da
+size 9955673595

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e39f869c04183226716a0d637696251c1c3073d056b1bc93f8f840c9fc0f7b4
+size 9999740781

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f2562a6ed67e380825829d50896ccacc04b181775bb39883c6be65214c57a94
+size 6063168980

pytorch_model.bin.index.json

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