Upload with huggingface_hub

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/flan-ul2",
+  "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": "float16",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.26.1"
+}

pytorch_model-00001-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d27cfea29f3f79a14f5fbc1bb8e7c0df861299ecf7582b5acfb4184e82cc6ca3
+size 1706075053

pytorch_model-00002-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7562d2c6fa8bfa172d228ac44799c2f4f10c4695904158acaf6638378c7a3967
+size 1979769635

pytorch_model-00003-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8809eb478265d23c4b90df7efbab3a4e659f147a63722bcb560de69e9ea064c7
+size 1979769635

pytorch_model-00004-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f570105fa4247f71107cd93154c2e605f390284b67801b8555bf3a53c50107b3
+size 1979769635

pytorch_model-00005-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:529e81624cd94bd317f202411d3275c5e5dbb5e625f5c270d06173ba746dbf4a
+size 1744880145

pytorch_model-00006-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e10b60fc5d9e9e5d6f516976d9381f96345da77dbc90f48d6402753d38858d8
+size 1879106339

pytorch_model-00007-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04dba2cf3ed7aba76dd08e72fa3276655102cc7b080beb65fa8595be7f45b7bf
+size 1879106339

pytorch_model-00008-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb6ce7a9047857573a0d2e2ada59dc63d9e47df2506a73bb12eeccfbcef77db8
+size 1979761169

pytorch_model-00009-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60866d63c457e20e03c960f7906d2487be707694aab299ce7ec5a605daeb28e
+size 1979769635

pytorch_model-00010-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0685485cc0d24efad3e50af06611ce585664fdc0746a10dab30ac5f7d2ad0bd7
+size 1979769635

pytorch_model-00011-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17164efad1ed5e6efb0a603cf4ded65037ef057c44aa393cbc7a347d102e8fd1
+size 1979769635

pytorch_model-00012-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c22a49d83a73f06638aecf3ddd37d6399e41cd9f224dd8030a3116ced2c6c3
+size 1974538611

pytorch_model-00013-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71f928154d9cc6f6249c9913966c7c753a626c084d081654ba9d75ff8bc92bd
+size 1912670927

pytorch_model-00014-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23bd94ae59d6c8c5d3c9a31ac9107b6acf7a51f3f978c6abd31ec1e1dd201252
+size 1979780129

pytorch_model-00015-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08928cbe261fd2aeea74bc5195872514bab535348c1c0a4586e5e3af8bf39121
+size 1912680471

pytorch_model-00016-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3575aa895f178010189171faf41c734ea6172aa8e175f4d2f9dce16eb4f593e8
+size 1744889561

pytorch_model-00017-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa14011b87138ad79a4ac1de527b0aac0e64212ef804368c3e2d38906651beb7
+size 1979780129

pytorch_model-00018-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d3d2987e231968cacc63c3def889ec90e59c884088e96a29e6aa2239ea780d4
+size 1912680535

pytorch_model-00019-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37ba31d60b3267fa148a74b773ecb09b86aacca60d1a76b95a0c9cfc28941721
+size 1744889625

pytorch_model-00020-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e171d8db43c219c82224cee54bb585b6c2a8b23764e6728fd52111c2d8aa791f
+size 1979780129

pytorch_model-00021-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d61ecb1258ddde7863ae3a27858584dd7c647c9c77e972ab661e0b37c7fe2c9f
+size 1912680535

pytorch_model-00022-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b25ea6433e23f359b6dce119de75244a78e71900eaf1103b9311d64660d11a38
+size 1744889625

pytorch_model-00023-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85f95bf2e735eac897ce27add512f7010ca2b1830f621afac5db9fbab656d324
+size 1979780129

pytorch_model-00024-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6ddd2bd06ef3d1c0d3f642fcd74e3a204a37adbe6466e17b9adb0e23c97872
+size 1912680535

pytorch_model-00025-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7dfb45232147d4ea6d2fea997ca8cff02e97c7e066c7e07487e7c5b7500bccb
+size 1744889625

pytorch_model-00026-of-00026.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077997a8b10995619348241bb2933464ecc4890b14a7a756192ce14414ae6942
+size 531646301

pytorch_model.bin.index.json

@@ -0,0 +1,751 @@
+{
+  "metadata": {
+    "total_size": 48298739712
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00017-of-00026.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00018-of-00026.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00019-of-00026.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00020-of-00026.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00021-of-00026.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.1.EncDecAttention.k.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.1.EncDecAttention.o.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.1.EncDecAttention.q.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.1.EncDecAttention.v.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00022-of-00026.bin",
+    "decoder.block.24.layer.2.DenseReluDense.wo.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.24.layer.2.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.1.EncDecAttention.k.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.1.EncDecAttention.o.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.1.EncDecAttention.q.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.1.EncDecAttention.v.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.2.DenseReluDense.wo.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.25.layer.2.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.1.EncDecAttention.k.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.1.EncDecAttention.o.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.1.EncDecAttention.q.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.1.EncDecAttention.v.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.2.DenseReluDense.wo.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.26.layer.2.layer_norm.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00023-of-00026.bin",
+    "decoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.1.EncDecAttention.k.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.1.EncDecAttention.o.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.1.EncDecAttention.q.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.1.EncDecAttention.v.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.2.DenseReluDense.wo.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.27.layer.2.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.1.EncDecAttention.k.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.1.EncDecAttention.o.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.1.EncDecAttention.q.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.1.EncDecAttention.v.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.2.DenseReluDense.wo.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.28.layer.2.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.1.EncDecAttention.k.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.1.EncDecAttention.o.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.1.EncDecAttention.q.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.1.EncDecAttention.v.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00024-of-00026.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.29.layer.2.DenseReluDense.wo.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.29.layer.2.layer_norm.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00013-of-00026.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.1.EncDecAttention.k.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.1.EncDecAttention.o.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.1.EncDecAttention.q.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.1.EncDecAttention.v.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.2.DenseReluDense.wo.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.30.layer.2.layer_norm.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.1.EncDecAttention.k.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.1.EncDecAttention.o.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.1.EncDecAttention.q.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.1.EncDecAttention.v.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00025-of-00026.bin",
+    "decoder.block.31.layer.2.DenseReluDense.wo.weight": "pytorch_model-00026-of-00026.bin",
+    "decoder.block.31.layer.2.layer_norm.weight": "pytorch_model-00026-of-00026.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00014-of-00026.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00015-of-00026.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00016-of-00026.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00012-of-00026.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00026-of-00026.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00026.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00006-of-00026.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00007-of-00026.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00008-of-00026.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.0.SelfAttention.o.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.0.SelfAttention.v.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.0.layer_norm.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.1.DenseReluDense.wo.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.24.layer.1.layer_norm.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.25.layer.0.SelfAttention.k.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.25.layer.0.SelfAttention.o.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.25.layer.0.SelfAttention.q.weight": "pytorch_model-00009-of-00026.bin",
+    "encoder.block.25.layer.0.SelfAttention.v.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.25.layer.0.layer_norm.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.25.layer.1.DenseReluDense.wo.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.25.layer.1.layer_norm.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.0.SelfAttention.k.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.0.SelfAttention.o.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.0.SelfAttention.v.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.0.layer_norm.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.1.DenseReluDense.wo.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.26.layer.1.layer_norm.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.0.SelfAttention.k.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.0.SelfAttention.o.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.0.SelfAttention.v.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.0.layer_norm.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.1.DenseReluDense.wo.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.27.layer.1.layer_norm.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.28.layer.0.SelfAttention.k.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.0.SelfAttention.q.weight": "pytorch_model-00010-of-00026.bin",
+    "encoder.block.28.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.0.layer_norm.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.1.DenseReluDense.wo.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.28.layer.1.layer_norm.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.0.SelfAttention.k.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.0.SelfAttention.q.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.0.layer_norm.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.1.DenseReluDense.wo.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.29.layer.1.layer_norm.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.30.layer.0.SelfAttention.k.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.0.SelfAttention.o.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.0.SelfAttention.q.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.0.SelfAttention.v.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.0.layer_norm.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.1.DenseReluDense.wo.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.30.layer.1.layer_norm.weight": "pytorch_model-00011-of-00026.bin",
+    "encoder.block.31.layer.0.SelfAttention.k.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.0.SelfAttention.o.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.0.SelfAttention.q.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.0.SelfAttention.v.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.0.layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.1.DenseReluDense.wo.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.31.layer.1.layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00026.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00026.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00004-of-00026.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00026.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00012-of-00026.bin",
+    "lm_head.weight": "pytorch_model-00026-of-00026.bin",
+    "shared.weight": "pytorch_model-00001-of-00026.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "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>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,112 @@
+{
+  "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>"
+  ],
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "name_or_path": "google/flan-ul2",
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}