add files for step 2038000

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "UMT5ForConditionalGeneration"
+  ],
+  "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": 2,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "umt5",
+  "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,
+  "scalable_attention": true,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5TokenizerFast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+    "_from_model_config": true,
+    "decoder_start_token_id": 0,
+    "eos_token_id": 2,
+    "pad_token_id": 0,
+    "transformers_version": "4.31.0"
+  }
+  

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cecec00366ad8181142c73242ad9c7ccf01c6d2dd1eaa6706ecbe94ce652dc92
+size 4994910688

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14afa710d7c014bc827914584ccceee19e4a571aaece1d992a6ca50abf16c493
+size 4975033384

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c89974efeaf9b8a7dfae3046427bd21e3a5c7748331bfbe10982aa952fbb8fbb
+size 1429348296

model.safetensors.index.json

@@ -0,0 +1,611 @@
+{
+  "metadata": {
+    "total_size": 11399217152
+  },
+  "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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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.relative_attention_bias.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 +1,108 @@
+{
+  "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>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,113 @@
+{
+  "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>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<unk>",
+  "unk_token": "<unk>",
+  "extra_ids": 100,
+  "model_max_length": 512,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "T5Tokenizer"
+}