Added the rest

added_tokens.json

@@ -0,0 +1,103 @@
+{
+  "<extra_id_0>": 256099,
+  "<extra_id_10>": 256089,
+  "<extra_id_11>": 256088,
+  "<extra_id_12>": 256087,
+  "<extra_id_13>": 256086,
+  "<extra_id_14>": 256085,
+  "<extra_id_15>": 256084,
+  "<extra_id_16>": 256083,
+  "<extra_id_17>": 256082,
+  "<extra_id_18>": 256081,
+  "<extra_id_19>": 256080,
+  "<extra_id_1>": 256098,
+  "<extra_id_20>": 256079,
+  "<extra_id_21>": 256078,
+  "<extra_id_22>": 256077,
+  "<extra_id_23>": 256076,
+  "<extra_id_24>": 256075,
+  "<extra_id_25>": 256074,
+  "<extra_id_26>": 256073,
+  "<extra_id_27>": 256072,
+  "<extra_id_28>": 256071,
+  "<extra_id_29>": 256070,
+  "<extra_id_2>": 256097,
+  "<extra_id_30>": 256069,
+  "<extra_id_31>": 256068,
+  "<extra_id_32>": 256067,
+  "<extra_id_33>": 256066,
+  "<extra_id_34>": 256065,
+  "<extra_id_35>": 256064,
+  "<extra_id_36>": 256063,
+  "<extra_id_37>": 256062,
+  "<extra_id_38>": 256061,
+  "<extra_id_39>": 256060,
+  "<extra_id_3>": 256096,
+  "<extra_id_40>": 256059,
+  "<extra_id_41>": 256058,
+  "<extra_id_42>": 256057,
+  "<extra_id_43>": 256056,
+  "<extra_id_44>": 256055,
+  "<extra_id_45>": 256054,
+  "<extra_id_46>": 256053,
+  "<extra_id_47>": 256052,
+  "<extra_id_48>": 256051,
+  "<extra_id_49>": 256050,
+  "<extra_id_4>": 256095,
+  "<extra_id_50>": 256049,
+  "<extra_id_51>": 256048,
+  "<extra_id_52>": 256047,
+  "<extra_id_53>": 256046,
+  "<extra_id_54>": 256045,
+  "<extra_id_55>": 256044,
+  "<extra_id_56>": 256043,
+  "<extra_id_57>": 256042,
+  "<extra_id_58>": 256041,
+  "<extra_id_59>": 256040,
+  "<extra_id_5>": 256094,
+  "<extra_id_60>": 256039,
+  "<extra_id_61>": 256038,
+  "<extra_id_62>": 256037,
+  "<extra_id_63>": 256036,
+  "<extra_id_64>": 256035,
+  "<extra_id_65>": 256034,
+  "<extra_id_66>": 256033,
+  "<extra_id_67>": 256032,
+  "<extra_id_68>": 256031,
+  "<extra_id_69>": 256030,
+  "<extra_id_6>": 256093,
+  "<extra_id_70>": 256029,
+  "<extra_id_71>": 256028,
+  "<extra_id_72>": 256027,
+  "<extra_id_73>": 256026,
+  "<extra_id_74>": 256025,
+  "<extra_id_75>": 256024,
+  "<extra_id_76>": 256023,
+  "<extra_id_77>": 256022,
+  "<extra_id_78>": 256021,
+  "<extra_id_79>": 256020,
+  "<extra_id_7>": 256092,
+  "<extra_id_80>": 256019,
+  "<extra_id_81>": 256018,
+  "<extra_id_82>": 256017,
+  "<extra_id_83>": 256016,
+  "<extra_id_84>": 256015,
+  "<extra_id_85>": 256014,
+  "<extra_id_86>": 256013,
+  "<extra_id_87>": 256012,
+  "<extra_id_88>": 256011,
+  "<extra_id_89>": 256010,
+  "<extra_id_8>": 256091,
+  "<extra_id_90>": 256009,
+  "<extra_id_91>": 256008,
+  "<extra_id_92>": 256007,
+  "<extra_id_93>": 256006,
+  "<extra_id_94>": 256005,
+  "<extra_id_95>": 256004,
+  "<extra_id_96>": 256003,
+  "<extra_id_97>": 256002,
+  "<extra_id_98>": 256001,
+  "<extra_id_99>": 256000,
+  "<extra_id_9>": 256090,
+  "<pad>": 256100
+}

config.json

@@ -0,0 +1,33 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 8192,
+  "d_kv": 128,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 256,
+  "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,
+  "task_specific_params": {},
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

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": "4.35.0"
+}

model.safetensors.index.json

@@ -0,0 +1,749 @@
+{
+  "metadata": {
+    "total_size": 11761496064
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.2.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.24.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.25.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.26.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.27.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.27.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.27.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.28.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.29.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.3.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.30.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.30.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.31.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.4.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.5.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.6.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.7.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.8.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.9.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.final_layer_norm.weight": "model-00003-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.24.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.25.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.26.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.27.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.28.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.29.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.29.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.29.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.29.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.29.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.29.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.29.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.29.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.29.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.30.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.30.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.31.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.final_layer_norm.weight": "model-00002-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "shared.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,939 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "256000": {
+      "content": "<extra_id_99>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256001": {
+      "content": "<extra_id_98>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256002": {
+      "content": "<extra_id_97>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256003": {
+      "content": "<extra_id_96>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256004": {
+      "content": "<extra_id_95>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256005": {
+      "content": "<extra_id_94>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256006": {
+      "content": "<extra_id_93>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256007": {
+      "content": "<extra_id_92>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256008": {
+      "content": "<extra_id_91>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256009": {
+      "content": "<extra_id_90>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256010": {
+      "content": "<extra_id_89>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256011": {
+      "content": "<extra_id_88>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256012": {
+      "content": "<extra_id_87>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256013": {
+      "content": "<extra_id_86>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256014": {
+      "content": "<extra_id_85>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256015": {
+      "content": "<extra_id_84>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256016": {
+      "content": "<extra_id_83>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256017": {
+      "content": "<extra_id_82>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256018": {
+      "content": "<extra_id_81>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256019": {
+      "content": "<extra_id_80>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256020": {
+      "content": "<extra_id_79>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256021": {
+      "content": "<extra_id_78>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256022": {
+      "content": "<extra_id_77>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256023": {
+      "content": "<extra_id_76>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256024": {
+      "content": "<extra_id_75>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256025": {
+      "content": "<extra_id_74>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256026": {
+      "content": "<extra_id_73>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256027": {
+      "content": "<extra_id_72>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256028": {
+      "content": "<extra_id_71>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256029": {
+      "content": "<extra_id_70>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256030": {
+      "content": "<extra_id_69>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256031": {
+      "content": "<extra_id_68>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256032": {
+      "content": "<extra_id_67>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256033": {
+      "content": "<extra_id_66>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256034": {
+      "content": "<extra_id_65>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256035": {
+      "content": "<extra_id_64>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256036": {
+      "content": "<extra_id_63>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256037": {
+      "content": "<extra_id_62>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256038": {
+      "content": "<extra_id_61>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256039": {
+      "content": "<extra_id_60>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256040": {
+      "content": "<extra_id_59>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256041": {
+      "content": "<extra_id_58>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256042": {
+      "content": "<extra_id_57>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256043": {
+      "content": "<extra_id_56>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256044": {
+      "content": "<extra_id_55>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256045": {
+      "content": "<extra_id_54>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256046": {
+      "content": "<extra_id_53>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256047": {
+      "content": "<extra_id_52>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256048": {
+      "content": "<extra_id_51>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256049": {
+      "content": "<extra_id_50>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256050": {
+      "content": "<extra_id_49>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256051": {
+      "content": "<extra_id_48>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256052": {
+      "content": "<extra_id_47>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256053": {
+      "content": "<extra_id_46>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256054": {
+      "content": "<extra_id_45>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256055": {
+      "content": "<extra_id_44>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256056": {
+      "content": "<extra_id_43>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256057": {
+      "content": "<extra_id_42>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256058": {
+      "content": "<extra_id_41>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256059": {
+      "content": "<extra_id_40>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256060": {
+      "content": "<extra_id_39>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256061": {
+      "content": "<extra_id_38>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256062": {
+      "content": "<extra_id_37>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256063": {
+      "content": "<extra_id_36>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256064": {
+      "content": "<extra_id_35>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256065": {
+      "content": "<extra_id_34>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256066": {
+      "content": "<extra_id_33>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256067": {
+      "content": "<extra_id_32>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256068": {
+      "content": "<extra_id_31>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256069": {
+      "content": "<extra_id_30>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256070": {
+      "content": "<extra_id_29>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256071": {
+      "content": "<extra_id_28>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256072": {
+      "content": "<extra_id_27>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256073": {
+      "content": "<extra_id_26>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256074": {
+      "content": "<extra_id_25>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256075": {
+      "content": "<extra_id_24>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256076": {
+      "content": "<extra_id_23>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256077": {
+      "content": "<extra_id_22>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256078": {
+      "content": "<extra_id_21>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256079": {
+      "content": "<extra_id_20>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256080": {
+      "content": "<extra_id_19>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256081": {
+      "content": "<extra_id_18>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256082": {
+      "content": "<extra_id_17>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256083": {
+      "content": "<extra_id_16>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256084": {
+      "content": "<extra_id_15>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256085": {
+      "content": "<extra_id_14>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256086": {
+      "content": "<extra_id_13>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256087": {
+      "content": "<extra_id_12>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256088": {
+      "content": "<extra_id_11>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256089": {
+      "content": "<extra_id_10>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256090": {
+      "content": "<extra_id_9>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256091": {
+      "content": "<extra_id_8>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256092": {
+      "content": "<extra_id_7>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256093": {
+      "content": "<extra_id_6>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256094": {
+      "content": "<extra_id_5>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256095": {
+      "content": "<extra_id_4>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256096": {
+      "content": "<extra_id_3>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256097": {
+      "content": "<extra_id_2>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256098": {
+      "content": "<extra_id_1>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256099": {
+      "content": "<extra_id_0>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": true,
+      "special": true
+    },
+    "256100": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}