Training in progress, step 100

config.json

@@ -0,0 +1,64 @@
+{
+  "_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_key_value_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": "4.46.0.dev0",
+  "use_cache": true,
+  "use_gqa": false,
+  "vocab_size": 32128
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:750937b058d201a9f73a525cfb55c6660cd17b0b32c62ebfad8bb62536b13fd4
+size 4994813208

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637e366bf49a2f7d5aae4f35e2b3b78a90f6cdde330b33615cab444226a926f2
+size 4974952864

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a01a883a6ac6f7f9f447d991f32362201e2466a4797ecb7de2575e9d74fd18c8
+size 1429331352

model.safetensors.index.json

@@ -0,0 +1,565 @@
+{
+  "metadata": {
+    "total_size": 11399028736
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00003.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00003.safetensors",
+    "decoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00001-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-00001-of-00003.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.0.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.1.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.10.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.11.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.12.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.13.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.14.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.15.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.16.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.17.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.18.layer.2.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.0.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.1.layer_norm.weight": "model-00002-of-00003.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-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-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00001-of-00003.safetensors",
+    "encoder.block.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-00001-of-00003.safetensors",
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "shared.weight": "model-00001-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spiece.model

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

tokenizer_config.json

@@ -0,0 +1,938 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e33ab2ae08b4301cdc959531dc72a75a4533912d11559cb390cab894608c3302
+size 5496