flan

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "google/flan-t5-xl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 5120,
+  "d_kv": 64,
+  "d_model": 2048,
+  "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": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 32,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.0",
+  "use_cache": true,
+  "vocab_size": 58240
+}

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": "4.36.0"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e35992ff5d60b7a84db0c87e3c730dbc9817736fee0dceeb3d6917eb06c229f5
+size 4982200024

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571264911c09413117ee0fa1d8fc90682d45124e24cc128d53f1166e83ef0b1d
+size 4983345552

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad41c489a6055c1f21510ad534be94a4e02bcff1eada9f12d9aa9879bd2bf18
+size 1861370840

model.safetensors.index.json

@@ -0,0 +1,565 @@
+{
+  "metadata": {
+    "total_size": 11826847744
+  },
+  "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-00003-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.18.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.19.layer.2.layer_norm.weight": "model-00003-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-00003-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.20.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.21.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.22.layer.2.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.0.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.1.layer_norm.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00003-of-00003.safetensors",
+    "decoder.block.23.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.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-00002-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "encoder.block.23.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.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 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,1231 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58104": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58105": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58106": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58107": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58108": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58109": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58110": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58111": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58112": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58113": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58114": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58115": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58116": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58117": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58118": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58119": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58120": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58121": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58122": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58123": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58124": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58125": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58126": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58127": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58128": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58129": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58130": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58131": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58132": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58133": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58134": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58135": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58136": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58137": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58138": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58139": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58140": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58141": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58142": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58143": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58144": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58145": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58146": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58147": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58148": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58149": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58150": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58151": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58152": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58153": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58154": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58155": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58156": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58157": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58158": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58159": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58160": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58161": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58162": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58163": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58164": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58165": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58166": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58167": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58168": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58169": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58170": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58171": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58172": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58173": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58174": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58175": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58176": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58177": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58178": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58179": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58180": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58181": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58182": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58183": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58184": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58185": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58186": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58187": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58188": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58189": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58190": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58191": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58192": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58193": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58194": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58195": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58196": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58197": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58198": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58199": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58200": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58201": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58202": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58203": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58204": {
+      "content": "<|future_token_0|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58205": {
+      "content": "<|future_token_1|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58206": {
+      "content": "<|future_token_2|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58207": {
+      "content": "<|future_token_3|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58208": {
+      "content": "<|future_token_4|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58209": {
+      "content": "<|future_token_5|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58210": {
+      "content": "<|future_token_6|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58211": {
+      "content": "<|future_token_7|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58212": {
+      "content": "<|future_token_8|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58213": {
+      "content": "<|future_token_9|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58214": {
+      "content": "<|future_token_10|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58215": {
+      "content": "<|future_token_11|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58216": {
+      "content": "<|future_token_12|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58217": {
+      "content": "<|future_token_13|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58218": {
+      "content": "<|future_token_14|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58219": {
+      "content": "<|future_token_15|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58220": {
+      "content": "<|future_token_16|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58221": {
+      "content": "<|future_token_17|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58222": {
+      "content": "<|future_token_18|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58223": {
+      "content": "<|future_token_19|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58224": {
+      "content": "<|future_token_20|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58225": {
+      "content": "<|future_token_21|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58226": {
+      "content": "<|future_token_22|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58227": {
+      "content": "<|future_token_23|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58228": {
+      "content": "<|future_token_24|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58229": {
+      "content": "<|future_token_25|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58230": {
+      "content": "<|future_token_26|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58231": {
+      "content": "<|future_token_27|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58232": {
+      "content": "<|future_token_28|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58233": {
+      "content": "<|future_token_29|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58234": {
+      "content": "<|future_token_30|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58235": {
+      "content": "<|future_token_31|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58236": {
+      "content": "<|future_token_32|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58237": {
+      "content": "<|future_token_33|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58238": {
+      "content": "<|future_token_34|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "58239": {
+      "content": "<|future_token_35|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "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,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}