Adding `safetensors` variant of this model

model-0-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a72575e72f67d694f9f387bf757387e375147972ff36148f7da002a7bda48d47
+size 407922616

model-1-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:512bf065500427a6e4f31a0c7d88e41e38acb500444203d102a42e090e5a4cc1
+size 407922616

model-10-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63419a8e869c13fb258b374eb454c3882669e6fc2b01936cbae6a8a022eda3c3
+size 407922624

model-11-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a9b3f8ef9aa3f2463c4e787447f32586f6c6cee7a888efc1f948494d47e9e9
+size 407922624

model-12-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1c1bea3f11899e2cbdaca8e0f474ef03603cb450a74488d7f046d376d1170bd
+size 407922624

model-13-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:462efb50be83d1111f4eb858ea70677985f17c510ec7088b9aef2f129f5f4abc
+size 407922624

model-14-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2f9f05e6ebf837a0b6e7e4692604280728bd2bead1ba2773a2573396c281cb3
+size 407922624

model-15-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c19f0f1ed770853ff6300b92967651fa4fc4d09048079800b3694ee4ad4a29
+size 407922624

model-16-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec6acccb5fc9dfd1e88cf774ab12570cb865583914560d47ea7993e3b522be4
+size 407922624

model-17-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1a0b30e34f135ec49dae95a613101dd479e2e260e06234cebacf48b2cd6323
+size 407922624

model-18-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe7659b1937d2a4e7b666cab59656ad5f79bed543fa117ba067b55f7efc1a51
+size 407922624

model-19-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5668990819c6fb11f31cde9e9276cb6e7bbdf798d8f78c912494cdd111e52aa3
+size 407922624

model-2-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d823cbb279ed7b27c782aecc1f83472f521168c7a54ce7327b80caff5175da4
+size 407922616

model-20-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a17fc50cf896396e8c3260e6ed281224f118d591ee71249349d5f796c219e86
+size 407922624

model-21-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c591b0e7f50e9cce0d0eddc37b6ae7745b6f36526caccd9a0e03e0ff009f699
+size 407922624

model-22-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad9929dae3cb70e4d4f85e01e962c141885ed2cb402fd47d7c7f03e70500f793
+size 407922624

model-23-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b38b94fe90d78eddfb65ecf1b1bd1a77bba9e933b89ed2af176409d0c130cee
+size 407922624

model-24-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19de6468a89b3fbdccfcafca0f2affbfd0778fb3fb962db2ed861f63aceb2131
+size 407922624

model-25-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f65166bcec3efa1dbdfd53c9013d92decfd7859c4695eafaa8bfc9ad636df38f
+size 407922624

model-26-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17e54a754c91a0ea7e5927de43988bbec6211eade972d47efa5f50e27f8c559b
+size 407922624

model-27-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:106e0cbd6f42cee20fa9076089de604b0501dad092122d99a96e51b47cbb112e
+size 407922624

model-28-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee7e2a3ab7548afa348c491621868231d2df2156fc661a6f85cc9f72fd9d62ae
+size 1065361792

model-3-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852e64d903ba3c514833218c9204eedabf686f5ce49aa7351c5af74c1c8fdd36
+size 407922616

model-4-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024f5a7a16a76e4af89bb2261a525046e6842479b3d2f3f51cf7c4c5cda0bafb
+size 407922616

model-5-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:014dea543ddfedb60e8657ed07c65abbdf7a3bc760a58acfb7e3289436b29efc
+size 407922616

model-6-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b857b9f7153be1c2438a7ec585dc5f051a0a9f772421b078078e933d74d617
+size 407922616

model-7-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f95da4f683de0e4080b0bbe9bda844723606c4bc9c64e8f25ad4459bd6afb28a
+size 407922616

model-8-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e057aa40ee498d3626d41db64dbf102cc9758a37d087ef0cd590333c9712f1a
+size 407922616

model-9-of-29.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbf07011d247bd8a79d28bcc58186563ef84e497296fec61788080528bdfca4b
+size 407922616

model.safetensors.index.json

@@ -0,0 +1,206 @@
+{
+    "weight_map": {
+        "transformer.encoder.layers.0.input_layernorm.weight": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.0.self_attention.dense.weight": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-0-of-29.safetensors",
+        "transformer.encoder.layers.1.input_layernorm.weight": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.1.self_attention.dense.weight": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-1-of-29.safetensors",
+        "transformer.encoder.layers.2.input_layernorm.weight": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.2.self_attention.dense.weight": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-2-of-29.safetensors",
+        "transformer.encoder.layers.3.input_layernorm.weight": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.3.self_attention.dense.weight": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-3-of-29.safetensors",
+        "transformer.encoder.layers.4.input_layernorm.weight": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.4.self_attention.dense.weight": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-4-of-29.safetensors",
+        "transformer.encoder.layers.5.input_layernorm.weight": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.5.self_attention.dense.weight": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-5-of-29.safetensors",
+        "transformer.encoder.layers.6.input_layernorm.weight": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.6.self_attention.dense.weight": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-6-of-29.safetensors",
+        "transformer.encoder.layers.7.input_layernorm.weight": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.7.self_attention.dense.weight": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-7-of-29.safetensors",
+        "transformer.encoder.layers.8.input_layernorm.weight": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.8.self_attention.dense.weight": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-8-of-29.safetensors",
+        "transformer.encoder.layers.9.input_layernorm.weight": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.9.self_attention.dense.weight": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-9-of-29.safetensors",
+        "transformer.encoder.layers.10.input_layernorm.weight": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.10.self_attention.dense.weight": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-10-of-29.safetensors",
+        "transformer.encoder.layers.11.input_layernorm.weight": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.11.self_attention.dense.weight": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-11-of-29.safetensors",
+        "transformer.encoder.layers.12.input_layernorm.weight": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.12.self_attention.dense.weight": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-12-of-29.safetensors",
+        "transformer.encoder.layers.13.input_layernorm.weight": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.13.self_attention.dense.weight": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-13-of-29.safetensors",
+        "transformer.encoder.layers.14.input_layernorm.weight": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.14.self_attention.dense.weight": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-14-of-29.safetensors",
+        "transformer.encoder.layers.15.input_layernorm.weight": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.15.self_attention.dense.weight": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-15-of-29.safetensors",
+        "transformer.encoder.layers.16.input_layernorm.weight": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.16.self_attention.dense.weight": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-16-of-29.safetensors",
+        "transformer.encoder.layers.17.input_layernorm.weight": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.17.self_attention.dense.weight": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-17-of-29.safetensors",
+        "transformer.encoder.layers.18.input_layernorm.weight": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.18.self_attention.dense.weight": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-18-of-29.safetensors",
+        "transformer.encoder.layers.19.input_layernorm.weight": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.19.self_attention.dense.weight": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-19-of-29.safetensors",
+        "transformer.encoder.layers.20.input_layernorm.weight": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.20.self_attention.dense.weight": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-20-of-29.safetensors",
+        "transformer.encoder.layers.21.input_layernorm.weight": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.21.self_attention.dense.weight": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-21-of-29.safetensors",
+        "transformer.encoder.layers.22.input_layernorm.weight": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.22.self_attention.dense.weight": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-22-of-29.safetensors",
+        "transformer.encoder.layers.23.input_layernorm.weight": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.23.self_attention.dense.weight": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-23-of-29.safetensors",
+        "transformer.encoder.layers.24.input_layernorm.weight": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.24.self_attention.dense.weight": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-24-of-29.safetensors",
+        "transformer.encoder.layers.25.input_layernorm.weight": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.25.self_attention.dense.weight": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-25-of-29.safetensors",
+        "transformer.encoder.layers.26.input_layernorm.weight": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.26.self_attention.dense.weight": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-26-of-29.safetensors",
+        "transformer.encoder.layers.27.input_layernorm.weight": "model-27-of-29.safetensors",
+        "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-27-of-29.safetensors",
+        "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-27-of-29.safetensors",
+        "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-27-of-29.safetensors",
+        "transformer.encoder.layers.27.self_attention.dense.weight": "model-27-of-29.safetensors",
+        "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-27-of-29.safetensors",
+        "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-27-of-29.safetensors",
+        "transformer.embedding.word_embeddings.weight": "model-28-of-29.safetensors",
+        "transformer.output_layer.weight": "model-28-of-29.safetensors",
+        "transformer.encoder.final_layernorm.weight": "model-28-of-29.safetensors"
+    },
+    "metadata": {
+        "total_size": 12487168000
+    }
+}