add files for finetuning on python

config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "/home/patrick/t5/t5-v1_1-xxl",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+    "_from_model_config": true,
+    "decoder_start_token_id": 0,
+    "eos_token_id": 1,
+    "pad_token_id": 0,
+    "transformers_version": "4.27.0.dev0"
+  }

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48fc9dd2ee6422fd5750d7dd83305a8c62acbc5aa7c8ae5b5dcff63e412181a9
+size 4989319680

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af7a9b894132dfa4ec10a53c7bd95e1c3b051e134e17d1915a7cc282cb5ef3ca
+size 4999830656

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3375d3234ba36c19e23b63b3649e6c6e0ba2f603b6f23670d9b9937cfeb05ed
+size 4865612720

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffc72c07dd85ca2894a7bbfd32b279ad419c7c61aa2e164c920a5c63f8d9a6d2
+size 4899192216

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d73616f22151e94941883f1d0edcedca46afed9d1f233062da26e80ded953a
+size 4966293584

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e7adae537280b0fb13b2bc71df14389f14ee9896a40009cb706ac84b653c39d
+size 4999864400

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6983e9150c701a7309165776feb2e5aa82ad04af74b0e6c323ded8b2da54b6ae
+size 4999847968

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8426c1893bdd7752057d7aa7a64587e9bb8fa230ccc12c1934baac1820708d52
+size 4966293656

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71c5f455bd14640027cc8ff62adb4ffb78d050fb884c281f8b2d6f719f546f56
+size 4855143672

model.safetensors.index.json

@@ -0,0 +1,565 @@
+{
+  "metadata": {
+    "total_size": 44541329408
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.0.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.1.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.10.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.10.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.11.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.12.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.13.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.0.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.1.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_0.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wi_1.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.14.layer.2.layer_norm.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "model-00007-of-00009.safetensors",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.15.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.16.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.17.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.18.layer.2.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.0.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.1.layer_norm.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_0.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wi_1.weight": "model-00008-of-00009.safetensors",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.19.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.2.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.0.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.1.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_0.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wi_1.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.20.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.0.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.1.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_0.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wi_1.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.21.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.0.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.1.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_0.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wi_1.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.22.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.0.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.1.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_0.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wi_1.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.23.layer.2.layer_norm.weight": "model-00009-of-00009.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.3.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.1.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.4.layer.2.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.0.layer_norm.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00005-of-00009.safetensors",
+    "decoder.block.5.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.5.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.6.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.7.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.8.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.0.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.1.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00006-of-00009.safetensors",
+    "decoder.block.9.layer.2.layer_norm.weight": "model-00006-of-00009.safetensors",
+    "decoder.final_layer_norm.weight": "model-00009-of-00009.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00009.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00004-of-00009.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00009.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00009.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00009.safetensors",
+    "encoder.final_layer_norm.weight": "model-00004-of-00009.safetensors",
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "shared.weight": "model-00001-of-00009.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "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>"]}

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 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "model_max_length": 512, "name_or_path": "t5-small"}