add model

README.md

@@ -1,3 +1,61 @@
----
-license: apache-2.0
----
+
+# Unofficial port of the 20B model from Unifying Language Learning Paradigms
+
+requires transformers==4.20
+
+
+
+# Loading the model
+
+```python
+from transformers import T5ForConditionalGeneration, AutoTokenizer
+model = T5ForConditionalGeneration.from_pretrained("Seledorn/ul2", low_cpu_mem_usage=True, torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained("Seledorn/ul2")
+```
+# Example usage  
+
+
+```python
+inps = ["""
+Mr. and Mrs. Dursley, of number four, Privet Drive, <extra_id_0> the last people you'd expect to be involved in anything strange or mysterious, because they just didn't hold with such nonsense.
+
+Mr. Dursley was the director of a firm called Grunnings, which made drills. He was a big, <extra_id_1>. Mrs. Dursley was thin and blonde and had nearly twice the usual amount of neck, which came in very useful as she spent so much of her time craning over garden fences, spying on the neighbours. The Dursleys had a small son called Dudley and in their opinion there was no finer boy anywhere.
+
+The Dursleys had everything they wanted, but they also had a secret, and their greatest fear was that somebody would discover it. They didn't think they could bear it if anyone found out about the Potters. Mrs. Potter was Mrs. Dursley's sister, but they hadn't met for several years; in fact, Mrs. Dursley pretended she didn't have a sister, because her sister and her good-for-nothing husband were as unDursleyish as it was possible to be. The Dursleys shuddered to think what the neighbours would say if the Potters arrived in the street. The Dursleys knew that the Potters had a small son, too, but they had never even seen him. This boy was another good reason for keeping the Potters away; they didn't want Dudley mixing with a child like that."""
+]
+
+Note use `[NLG]` for X-denoisers, `[NLU]` for R-denoisers and `[S2S]` for S-Denoisers.
+
+
+model.cuda()
+model.eval()
+
+with torch.no_grad():
+    for inp in inps:
+        inputs = tokenizer(inp, return_tensors="pt").input_ids
+
+        inputs_ = inputs.cuda()
+        outputs = model.generate(inputs_, max_length = 200, do_sample=True, temperature = 0.9, num_return_sequences=4)
+        for output in outputs:
+            out = tokenizer.decode(output)
+            
+            inps = re.split(pattern, inp)
+            outs = re.split(pattern, out)
+
+            l = [z for (x,y) in zip(inps, outs[1:len(inps)]+ [""]) for z in (x,"*"+y+"*" if y != "" else "")]
+            print("".join(l))
+            print("-------------------------------")
+```
+
+
+Example output
+
+Mr. and Mrs. Dursley, of number four, Privet Drive, **were** the last people you'd expect to be involved in anything strange or mysterious, because they just didn't hold with such nonsense.
+
+Mr. Dursley was the director of a firm called Grunnings, which made drills. He was a big, **solid man with a short, brown beard, an enormous head full of brains and a round, fat face. He had a voice, too, that was so deep that it was nearly always accompanied by a slight tremor..**. Mrs. Dursley was thin and blonde and had nearly twice the usual amount of neck, which came in very useful as she spent so much of her time craning over garden fences, spying on the neighbours. The Dursleys had a small son called Dudley and in their opinion there was no finer boy anywhere.
+
+The Dursleys had everything they wanted, but they also had a secret, and their greatest fear was that somebody would discover it. They didn't think they could bear it if anyone found out about the Potters. Mrs. Potter was Mrs. Dursley's sister, but they hadn't met for several years; in fact, Mrs. Dursley pretended she didn't have a sister, because her sister and her good-for-nothing husband were as unDursleyish as it was possible to be. The Dursleys shuddered to think what the neighbours would say if the Potters arrived in the street. The Dursleys knew that the Potters had a small son, too, but they had never even seen him. This boy was another good reason for keeping the Potters away; they didn't want Dudley mixing with a child like that.
+
+Where bold is the completion of the model.
+
+

added_tokens.json

@@ -0,0 +1 @@
+{"[new_id_17]": 32117, "[new_id_20]": 32120, "[new_id_13]": 32113, "[new_id_2]": 32102, "[new_id_16]": 32116, "[new_id_7]": 32107, "[new_id_5]": 32105, "[new_id_1]": 32101, "[new_id_15]": 32115, "[new_id_12]": 32112, "[new_id_0]": 32100, "[new_id_11]": 32111, "[new_id_25]": 32125, "[new_id_24]": 32124, "[new_id_10]": 32110, "[new_id_27]": 32127, "[new_id_23]": 32123, "[new_id_14]": 32114, "[new_id_22]": 32122, "[new_id_21]": 32121, "[new_id_19]": 32119, "[new_id_3]": 32103, "[new_id_4]": 32104, "[new_id_18]": 32118, "[new_id_9]": 32109, "[new_id_8]": 32108, "[new_id_26]": 32126, "[new_id_6]": 32106}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ul2_model",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 16384,
+  "d_kv": 256,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "silu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-silu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 32,
+  "num_heads": 16,
+  "num_layers": 32,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.20.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6226f933c6950d796635e243250c47fca09411a8a540903064708301b7ab8b64
+size 9658776767

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:289235de6beafb7c9cbf145f8b54e183bb7cb681c74438807250584c1606fe6f
+size 9927240513

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83c197cfd5d5a61ee159ea101a22e3fa61861a0d94ee19cabb49648a34061a2f
+size 9932552699

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2c3713a749f368d6d5465a6bf38d524de7f192b9794e20dbc43d094bac3d36
+size 9927298907

pytorch_model.bin.index.json

@@ -0,0 +1,751 @@
+{
+  "metadata": {
+    "total_size": 39708805120
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.24.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.25.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.26.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.27.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.28.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.29.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.30.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.31.layer.2.layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00003-of-00004.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00002-of-00004.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00004-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00004.bin",
+    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
+    "shared.weight": "pytorch_model-00001-of-00004.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-3b", "tokenizer_class": "T5Tokenizer"}