Upload model

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "philschmid/flan-t5-xxl-sharded-fp16",
+  "architectures": [
+    "T5Model"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 3,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.2",
+  "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 sha256:90c839bf4cd4b4404765612591f07393dfa5c990a45ee0d3a2da54bc832ad162
+size 4452442307

pytorch_model-00002-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a31d7a149dafa0150b3f6b1a07ef8c95f2096d35d781bb3e10af61cde503b7c
+size 4999843701

pytorch_model-00003-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23a0d2d645b760d32915bf87a23ebbc63ffe27461476ead5f14596b5fc95a26b
+size 4966288621

pytorch_model-00004-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49abd0ef104b9e9de7ec4a69af8f4af6a8c620bed032dcd388928e212fa77251
+size 4630743525

pytorch_model-00005-of-00005.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d21ae198fcea9129f8fc2ce1e8eb02f71730abd997f3ba68dd34b9c3002c0ae
+size 3647134777

pytorch_model.bin.index.json

@@ -0,0 +1,272 @@
+{
+  "metadata": {
+    "total_size": 23222747136
+  },
+  "weight_map": {
+    "decoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.0.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.1.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.k.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.o.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.q.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.1.EncDecAttention.v.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.2.DenseReluDense.wo.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.block.2.layer.2.layer_norm.weight": "pytorch_model-00005-of-00005.bin",
+    "decoder.embed_tokens.weight": "pytorch_model-00005-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_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.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_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.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-00002-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00003-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00004-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_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.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-00004-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00004-of-00005.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00004-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_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.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_0.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.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-00002-of-00005.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00002-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-00002-of-00005.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00002-of-00005.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00004-of-00005.bin",
+    "shared.weight": "pytorch_model-00001-of-00005.bin"
+  }
+}