T5 safetensors

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "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": "4.21.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a68b2c8c080696a10109612a649bc69330991ecfea65930ccfdfbdb011f2686
+size 4989319680

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8ed6556d7507e38af5b428c605fb2a6f2bdb7e80bd481308b865f7a40c551ca
+size 4999830656

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c831635f83041f83faf0024b39c6ecb21b45d70dd38a63ea5bac6c7c6e5e558c
+size 4865612720

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a5f2d69205be92ad48fe5d712d38c2ff55627969116aeffc58bd75a28da468
+size 4194506688

model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 19049242624
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.0.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.1.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.10.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.11.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.12.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.12.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.13.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.14.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.15.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.16.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.17.layer.1.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.0.layer_norm.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00004.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.18.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.19.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.2.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.20.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.21.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.22.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.0.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.23.layer.1.layer_norm.weight": "model-00004-of-00004.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.3.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.4.layer.1.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.0.layer_norm.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00001-of-00004.safetensors",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.7.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.8.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.0.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00002-of-00004.safetensors",
+    "encoder.block.9.layer.1.layer_norm.weight": "model-00002-of-00004.safetensors",
+    "encoder.final_layer_norm.weight": "model-00004-of-00004.safetensors",
+    "shared.weight": "model-00001-of-00004.safetensors"
+  }
+}

pytorch_model.bin.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_size": 19575627776
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}