Add model files

added_tokens.json

@@ -0,0 +1,109 @@
+{
+  "<LM>": 50357,
+  "<SC1>": 50358,
+  "<SC2>": 50359,
+  "<SC3>": 50360,
+  "<SC4>": 50361,
+  "<SC5>": 50362,
+  "<SC6>": 50363,
+  "<extra_id_0>": 50257,
+  "<extra_id_10>": 50267,
+  "<extra_id_11>": 50268,
+  "<extra_id_12>": 50269,
+  "<extra_id_13>": 50270,
+  "<extra_id_14>": 50271,
+  "<extra_id_15>": 50272,
+  "<extra_id_16>": 50273,
+  "<extra_id_17>": 50274,
+  "<extra_id_18>": 50275,
+  "<extra_id_19>": 50276,
+  "<extra_id_1>": 50258,
+  "<extra_id_20>": 50277,
+  "<extra_id_21>": 50278,
+  "<extra_id_22>": 50279,
+  "<extra_id_23>": 50280,
+  "<extra_id_24>": 50281,
+  "<extra_id_25>": 50282,
+  "<extra_id_26>": 50283,
+  "<extra_id_27>": 50284,
+  "<extra_id_28>": 50285,
+  "<extra_id_29>": 50286,
+  "<extra_id_2>": 50259,
+  "<extra_id_30>": 50287,
+  "<extra_id_31>": 50288,
+  "<extra_id_32>": 50289,
+  "<extra_id_33>": 50290,
+  "<extra_id_34>": 50291,
+  "<extra_id_35>": 50292,
+  "<extra_id_36>": 50293,
+  "<extra_id_37>": 50294,
+  "<extra_id_38>": 50295,
+  "<extra_id_39>": 50296,
+  "<extra_id_3>": 50260,
+  "<extra_id_40>": 50297,
+  "<extra_id_41>": 50298,
+  "<extra_id_42>": 50299,
+  "<extra_id_43>": 50300,
+  "<extra_id_44>": 50301,
+  "<extra_id_45>": 50302,
+  "<extra_id_46>": 50303,
+  "<extra_id_47>": 50304,
+  "<extra_id_48>": 50305,
+  "<extra_id_49>": 50306,
+  "<extra_id_4>": 50261,
+  "<extra_id_50>": 50307,
+  "<extra_id_51>": 50308,
+  "<extra_id_52>": 50309,
+  "<extra_id_53>": 50310,
+  "<extra_id_54>": 50311,
+  "<extra_id_55>": 50312,
+  "<extra_id_56>": 50313,
+  "<extra_id_57>": 50314,
+  "<extra_id_58>": 50315,
+  "<extra_id_59>": 50316,
+  "<extra_id_5>": 50262,
+  "<extra_id_60>": 50317,
+  "<extra_id_61>": 50318,
+  "<extra_id_62>": 50319,
+  "<extra_id_63>": 50320,
+  "<extra_id_64>": 50321,
+  "<extra_id_65>": 50322,
+  "<extra_id_66>": 50323,
+  "<extra_id_67>": 50324,
+  "<extra_id_68>": 50325,
+  "<extra_id_69>": 50326,
+  "<extra_id_6>": 50263,
+  "<extra_id_70>": 50327,
+  "<extra_id_71>": 50328,
+  "<extra_id_72>": 50329,
+  "<extra_id_73>": 50330,
+  "<extra_id_74>": 50331,
+  "<extra_id_75>": 50332,
+  "<extra_id_76>": 50333,
+  "<extra_id_77>": 50334,
+  "<extra_id_78>": 50335,
+  "<extra_id_79>": 50336,
+  "<extra_id_7>": 50264,
+  "<extra_id_80>": 50337,
+  "<extra_id_81>": 50338,
+  "<extra_id_82>": 50339,
+  "<extra_id_83>": 50340,
+  "<extra_id_84>": 50341,
+  "<extra_id_85>": 50342,
+  "<extra_id_86>": 50343,
+  "<extra_id_87>": 50344,
+  "<extra_id_88>": 50345,
+  "<extra_id_89>": 50346,
+  "<extra_id_8>": 50265,
+  "<extra_id_90>": 50347,
+  "<extra_id_91>": 50348,
+  "<extra_id_92>": 50349,
+  "<extra_id_93>": 50350,
+  "<extra_id_94>": 50351,
+  "<extra_id_95>": 50352,
+  "<extra_id_96>": 50353,
+  "<extra_id_97>": 50354,
+  "<extra_id_98>": 50355,
+  "<extra_id_99>": 50356,
+  "<extra_id_9>": 50266
+}

config (2).json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "ai-forever/FRED-T5-1.7B",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "bos_token_id": 1,
+  "classifier_dropout": 0.0,
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1536,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 24,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.1",
+  "use_cache": true,
+  "vocab_size": 50364
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.38.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:539b37a9498cf8870dea0a8e66b1ea58dba3f5ac87bfc1e8bb078296a77430b6
+size 4990875920

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c8a5c3bca5363ad315a0553c2229bf9649a4dbbe7278e49b44dc5710e8dc5bf
+size 1970608832

model.safetensors.index.json

@@ -0,0 +1,565 @@
+{
+  "metadata": {
+    "total_size": 6961416192
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.0.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.1.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.10.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.11.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.12.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.19.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.2.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.20.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.21.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.22.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.0.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.1.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.23.layer.2.layer_norm.weight": "model-00002-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.3.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.4.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.5.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.6.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.7.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.8.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "decoder.block.9.layer.2.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "decoder.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00001-of-00002.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00001-of-00002.safetensors",
+    "encoder.final_layer_norm.weight": "model-00001-of-00002.safetensors",
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "shared.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,913 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50295": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50296": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50297": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50299": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50300": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50301": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50302": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50303": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50304": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50305": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50306": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50307": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50308": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50309": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50310": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50311": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50312": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50313": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50314": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50315": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50316": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50317": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50318": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50319": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50320": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50321": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50322": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50323": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50324": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50325": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50326": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50327": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50328": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50329": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50330": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50331": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50332": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50333": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50334": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50335": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50336": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50337": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50338": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50339": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50340": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50341": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50342": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50343": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50344": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50345": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50346": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50347": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50348": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50349": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50350": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50351": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50352": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50353": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50354": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50355": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50356": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50357": {
+      "content": "<LM>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50358": {
+      "content": "<SC1>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50359": {
+      "content": "<SC2>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50360": {
+      "content": "<SC3>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50361": {
+      "content": "<SC4>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50362": {
+      "content": "<SC5>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50363": {
+      "content": "<SC6>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:383dc835caa130b04224e429a1dd4ddfae0a6be88c8dec1f1606f3ee7972abd0
+size 5048