update

config.json

@@ -0,0 +1,57 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 65536,
+  "d_kv": 128,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 128,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 32128
+}

pytorch_model-00001-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf2a563d48691508030c3d85245cd03a3d6740924390a6b10ec40334ee67d427
+size 9862528612

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193e5c784cbe483d24bd99a32a6bc4c7e0741c1bac9fcb2897bbd9f15382dd4c
+size 9996755851

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07f8d690a3f168f9e9d9d543995bb7cec05ef20b5b5dae4c0ce04e7be3a0d7ae
+size 9932266453

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:645c2d5cff151b36fc57607a0d311e7cffddee8ec63fcc5544a5549a6c7e11ea
+size 9932261297

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d34391b44ae2f4662f10f5f548b262c85438b5a5b2538ce1263b5dc7805bb454
+size 5768832538

pytorch_model.bin.index.json

@@ -0,0 +1,519 @@
+{
+  "metadata": {
+    "total_size": 45624074240
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.10.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.11.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.12.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.13.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.14.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.15.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.16.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.17.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.EncDecAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.18.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.18.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.19.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.20.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.21.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.22.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wi.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.23.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.3.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.4.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.5.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.6.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.7.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wi.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.8.layer.2.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.EncDecAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wi.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.2.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.block.9.layer.2.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00002-of-00005.bin",
+    "decoder.final_layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "lm_head.weight": "pytorch_model-00005-of-00005.bin",
+    "shared.weight": "pytorch_model-00001-of-00005.bin"
+  }
+}

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>"], "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-11b", "tokenizer_class": "T5Tokenizer"}