Revert "2gb shards"

This reverts commit 03a519c1d0d0e476a4a12af6d6a6d9bb802c0abc.

model-00001-of-00015.safetensors → model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e5b97f5ac8b84a16da79b0cd4d2ac660424f4a3f655dbb0cbbdb7784743ef7
-size 1909299216
+oid sha256:f2ee43ebc4b14760c2a94baa24213f0f37f2a5e9b07a6e6488f4376265830d7b
+size 9981994344

model-00002-of-00015.safetensors → model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13700ed44b712d0f762b1719a6ee2cfc8d2659c800abdf30e247f573d6ed210f
-size 1986929176
+oid sha256:95e85ec13d59bfc6c6f84bc0e7419ad03776a119d739dbe4f006c2dd87bbc71c
+size 3727267912

model-00005-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d4c46816a9da3f260fd7d64708fc87502c4449a0429f27b6dfee3aecebe469ba
-size 1986929168

model-00006-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4042f69ea71c4985063e70872fa99173cf4ec006d7c9a15fc6a8b8cc712a0c2a
-size 1986965768

model-00007-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:931719bbe3d98645fc70c8e22df68636cc2f504a14dd41354e544ce346bf36ac
-size 1824072368

model-00008-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:da1d16c2321080d8f71e6396a1a1d6adf8b5866629d2a5cb7f12fec73958ebe9
-size 1986929192

model-00009-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a760dcf799420983a7db9ebf49bb9c6bc004042d6a51cfdfd07c68abec0c6740
-size 1986965768

model-00010-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f3e4da7be6ebf8c20057d8364c261126efeeceb56b2d190be3ccbf6f82b8f085
-size 1824072368

model-00011-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:590115bd785f5862835fbe023cb98ebc05d4c4f9310bc301a577283e0fb880b8
-size 1986929192

model-00012-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8957a361fa3558b14bfadb08e6e1c6611b2a8c70de914af861672fd614ae72bc
-size 1986965768

model-00013-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:40c7954b3c32e36900223d0725f7ec5e31951dc553aa7740dd8791a2c31cd584
-size 1824072368

model-00014-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10dd2988a936abd107ee5c317e38ffa6f446acd781325440d890a0a28fb159a6
-size 1986929192

model-00015-of-00015.safetensors

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:93796669d72c8c5a962b346eaf158454f52531b7b7231683020f73760fb7d6a5
-size 330403664

model.safetensors.index.json

@@ -1,202 +0,0 @@
-{
-  "metadata": {
-    "total_size": 27418477824
-  },
-  "weight_map": {
-    "transformer.h.0.input_layernorm.bias": "model-00001-of-00015.safetensors",
-    "transformer.h.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.1.input_layernorm.bias": "model-00001-of-00015.safetensors",
-    "transformer.h.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00015.safetensors",
-    "transformer.h.10.input_layernorm.bias": "model-00005-of-00015.safetensors",
-    "transformer.h.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.10.self_attention.dense.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.10.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.11.input_layernorm.bias": "model-00006-of-00015.safetensors",
-    "transformer.h.11.input_layernorm.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.self_attention.dense.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.11.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.input_layernorm.bias": "model-00006-of-00015.safetensors",
-    "transformer.h.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.self_attention.dense.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.12.self_attention.query_key_value.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.13.input_layernorm.bias": "model-00006-of-00015.safetensors",
-    "transformer.h.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
-    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.self_attention.dense.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.13.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.input_layernorm.bias": "model-00007-of-00015.safetensors",
-    "transformer.h.14.input_layernorm.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.self_attention.dense.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.14.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.15.input_layernorm.bias": "model-00007-of-00015.safetensors",
-    "transformer.h.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.15.self_attention.dense.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.15.self_attention.query_key_value.weight": "model-00007-of-00015.safetensors",
-    "transformer.h.16.input_layernorm.bias": "model-00008-of-00015.safetensors",
-    "transformer.h.16.input_layernorm.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.self_attention.dense.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.16.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.17.input_layernorm.bias": "model-00008-of-00015.safetensors",
-    "transformer.h.17.input_layernorm.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.17.self_attention.dense.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.17.self_attention.query_key_value.weight": "model-00008-of-00015.safetensors",
-    "transformer.h.18.input_layernorm.bias": "model-00009-of-00015.safetensors",
-    "transformer.h.18.input_layernorm.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.self_attention.dense.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.18.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.input_layernorm.bias": "model-00009-of-00015.safetensors",
-    "transformer.h.19.input_layernorm.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.self_attention.dense.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.19.self_attention.query_key_value.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.2.input_layernorm.bias": "model-00002-of-00015.safetensors",
-    "transformer.h.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.self_attention.dense.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.2.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.20.input_layernorm.bias": "model-00009-of-00015.safetensors",
-    "transformer.h.20.input_layernorm.weight": "model-00009-of-00015.safetensors",
-    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.self_attention.dense.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.20.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.input_layernorm.bias": "model-00010-of-00015.safetensors",
-    "transformer.h.21.input_layernorm.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.self_attention.dense.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.21.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.22.input_layernorm.bias": "model-00010-of-00015.safetensors",
-    "transformer.h.22.input_layernorm.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.22.self_attention.dense.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.22.self_attention.query_key_value.weight": "model-00010-of-00015.safetensors",
-    "transformer.h.23.input_layernorm.bias": "model-00011-of-00015.safetensors",
-    "transformer.h.23.input_layernorm.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.self_attention.dense.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.23.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.24.input_layernorm.bias": "model-00011-of-00015.safetensors",
-    "transformer.h.24.input_layernorm.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.24.self_attention.dense.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.24.self_attention.query_key_value.weight": "model-00011-of-00015.safetensors",
-    "transformer.h.25.input_layernorm.bias": "model-00012-of-00015.safetensors",
-    "transformer.h.25.input_layernorm.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.self_attention.dense.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.25.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.input_layernorm.bias": "model-00012-of-00015.safetensors",
-    "transformer.h.26.input_layernorm.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.self_attention.dense.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.26.self_attention.query_key_value.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.27.input_layernorm.bias": "model-00012-of-00015.safetensors",
-    "transformer.h.27.input_layernorm.weight": "model-00012-of-00015.safetensors",
-    "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.self_attention.dense.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.27.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.input_layernorm.bias": "model-00013-of-00015.safetensors",
-    "transformer.h.28.input_layernorm.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.self_attention.dense.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.28.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.29.input_layernorm.bias": "model-00013-of-00015.safetensors",
-    "transformer.h.29.input_layernorm.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.29.self_attention.dense.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.29.self_attention.query_key_value.weight": "model-00013-of-00015.safetensors",
-    "transformer.h.3.input_layernorm.bias": "model-00002-of-00015.safetensors",
-    "transformer.h.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.3.self_attention.dense.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.3.self_attention.query_key_value.weight": "model-00002-of-00015.safetensors",
-    "transformer.h.30.input_layernorm.bias": "model-00014-of-00015.safetensors",
-    "transformer.h.30.input_layernorm.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.self_attention.dense.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.30.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.31.input_layernorm.bias": "model-00014-of-00015.safetensors",
-    "transformer.h.31.input_layernorm.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00015-of-00015.safetensors",
-    "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.31.self_attention.dense.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.31.self_attention.query_key_value.weight": "model-00014-of-00015.safetensors",
-    "transformer.h.4.input_layernorm.bias": "model-00003-of-00015.safetensors",
-    "transformer.h.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.self_attention.dense.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.4.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.input_layernorm.bias": "model-00003-of-00015.safetensors",
-    "transformer.h.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.self_attention.dense.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.5.self_attention.query_key_value.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.6.input_layernorm.bias": "model-00003-of-00015.safetensors",
-    "transformer.h.6.input_layernorm.weight": "model-00003-of-00015.safetensors",
-    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.self_attention.dense.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.6.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.input_layernorm.bias": "model-00004-of-00015.safetensors",
-    "transformer.h.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.self_attention.dense.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.7.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.8.input_layernorm.bias": "model-00004-of-00015.safetensors",
-    "transformer.h.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.8.self_attention.dense.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.8.self_attention.query_key_value.weight": "model-00004-of-00015.safetensors",
-    "transformer.h.9.input_layernorm.bias": "model-00005-of-00015.safetensors",
-    "transformer.h.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.self_attention.dense.weight": "model-00005-of-00015.safetensors",
-    "transformer.h.9.self_attention.query_key_value.weight": "model-00005-of-00015.safetensors",
-    "transformer.ln_f.bias": "model-00015-of-00015.safetensors",
-    "transformer.ln_f.weight": "model-00015-of-00015.safetensors",
-    "transformer.word_embeddings.weight": "model-00001-of-00015.safetensors"
-  }
-}

model-00003-of-00015.safetensors → pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b84ab4f3c73bacb562641c4fe426f757fb51615efd14ca1ca3663071dc8008e
-size 1986965752
+oid sha256:71df7f76b33ae5afd2d6185422944e5063cd69d065cb73421ffdaae1bca4ef9e
+size 9982026522

pytorch_model-00001-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dcc6b4251e53efbde51d4267520049b5fd6290d5b4d3a7ad95f180e5f47c4dcf
-size 1909302101

model-00004-of-00015.safetensors → pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec939c0bca9ed24a14b89afb4bfc6d4e23f0ce232197d84a17f13ed3d5aba0f8
-size 1824072352
+oid sha256:92ad1f3e7abd726291a34fb5e8d80c3e5c2025bc3f137bbd6fa8a9cb081057eb
+size 3727279707

pytorch_model-00002-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:91505af0d02b77bcc1e2f41c2acb1ef60625dd688abc6c50bad493a37b8c5408
-size 1986932345

pytorch_model-00003-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35ccc21d95528dfa6be25e5b439f53f17cb9a044a7e9dfd4e61f5a58cde9d355
-size 1986969309

pytorch_model-00004-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:662025b98bc27ccc6edddc04b1d1c8528da36ed0efb538499494b25e981a9b64
-size 1824075723

pytorch_model-00005-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5b55c63a3646bf82d9df1b16cd0c0fd1b13686f8d0c3f65ac96c0b631a452e4f
-size 1986932345

pytorch_model-00006-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:82e27b55247afe45d8f1ad66e869953b3bc2aeded98f5839d5a78249c72f7efc
-size 1986969309

pytorch_model-00007-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2b1b676120ed79ae2b1f2b1bb49501af70cfee5b4716c7540f28bbe6e61c71ff
-size 1824075723

pytorch_model-00008-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ca67f101145e22551ce485d9a9d75d4cbaf0f27e3ad3902accfba3749e3901d
-size 1986932345

pytorch_model-00009-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:df972d9c60693ff21ae7ff3f5411b7e53d82dda5035a8dad4d1e67c17a3e8b5d
-size 1986969309

pytorch_model-00010-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6d4f8abc1d6e1b4e42918572fcf6b52f930040846d043ad28a2c95eff7f84f22
-size 1824075723

pytorch_model-00011-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c050c86969b75eabd38cfc686f1ab8603b8e345ae495051aa044f6402f131a17
-size 1986932345

pytorch_model-00012-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:357d43e96875c27decf9c84d1b0ad8a8b00af6377602014f3da41b1466ef3502
-size 1986969309

pytorch_model-00013-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a593fe4635ae63eec96f3a3aa1d43d3ca62e615fad5658e63661494fd17f1279
-size 1824075723

pytorch_model-00014-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0544c157fb6fee6627ed6d9ddd2dd13d3b69200de20d2e0a72877531cc2215cf
-size 1986932345

pytorch_model-00015-of-00015.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3805702dea4614f05988ed0eada9b1e087cb12ccc34080642756b986daadb8bd
-size 330404876

pytorch_model.bin.index.json

@@ -1,203 +1,203 @@
 {
   "metadata": {
-    "total_size": 27418477824
+    "total_size": 13709238912
   },
   "weight_map": {
-    "lm_head.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00015.bin",
-    "transformer.h.10.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.11.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.12.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.13.input_layernorm.bias": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.13.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
-    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.14.input_layernorm.bias": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.15.input_layernorm.bias": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.15.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00007-of-00015.bin",
-    "transformer.h.16.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.17.input_layernorm.bias": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.17.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00008-of-00015.bin",
-    "transformer.h.18.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.19.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.19.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.2.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.20.input_layernorm.bias": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.20.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
-    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.21.input_layernorm.bias": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.21.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.22.input_layernorm.bias": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.22.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00010-of-00015.bin",
-    "transformer.h.23.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.24.input_layernorm.bias": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.24.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00011-of-00015.bin",
-    "transformer.h.25.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.26.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.26.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.27.input_layernorm.bias": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.27.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
-    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.28.input_layernorm.bias": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.28.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.29.input_layernorm.bias": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.29.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00013-of-00015.bin",
-    "transformer.h.3.input_layernorm.bias": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00002-of-00015.bin",
-    "transformer.h.30.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.30.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.31.input_layernorm.bias": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.31.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00015-of-00015.bin",
-    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00014-of-00015.bin",
-    "transformer.h.4.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.5.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.6.input_layernorm.bias": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.6.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
-    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.7.input_layernorm.bias": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.8.input_layernorm.bias": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.8.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00004-of-00015.bin",
-    "transformer.h.9.input_layernorm.bias": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00005-of-00015.bin",
-    "transformer.ln_f.bias": "pytorch_model-00015-of-00015.bin",
-    "transformer.ln_f.weight": "pytorch_model-00015-of-00015.bin",
-    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00015.bin"
+    "lm_head.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.30.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.30.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.31.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin"
   }
 }