Adding `safetensors` variant of this model

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:debc2b311c7e16cb3bf41a305d9811b91af3d0da3c70c1a334375a43c93b81bc
+size 1917279912

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ff25fb2ac161cb7dde98a520fab39929d44bc241131b0d1721884e51896f4f
+size 1986949128

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f468ddf47f5f2ff8a08c75b00c54cc4b65da1588f0b32c17a2383d9fef7fdfed
+size 1905502376

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25f3dbcec86b5ead9e92e980887cb6ac828d4b7a759376b39f4345b833d8a25b
+size 1905520808

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc163364197de76aa60255381f1574c4af14f63bb8c614a0b12ea0ebf5ecb5e
+size 1986949160

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a96caac971749f66eeade44030b7460b46ba0929a7e81f123c5e43d255e97d
+size 1905502408

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd363705c0c68db6bf1cf0f2b916eee733d648fa94297c9fc57c2e0b20b44120
+size 1905520808

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc20c363f8198164102c3cee1173e9d79250e80c5f5d0aa4cf38b3eada855a8d
+size 921469224

model.safetensors.index.json

@@ -0,0 +1,203 @@
+{
+    "metadata": {
+        "total_size": 14434670336
+    },
+    "weight_map": {
+        "lm_head.weight": "model-00008-of-00008.safetensors",
+        "transformer.h.0.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.10.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.10.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.10.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.11.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.11.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.12.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.12.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.13.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.13.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.13.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.14.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.14.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.15.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.15.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.16.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.16.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.17.input_layernorm.bias": "model-00004-of-00008.safetensors",
+        "transformer.h.17.input_layernorm.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.17.self_attention.dense.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.17.self_attention.query_key_value.weight": "model-00004-of-00008.safetensors",
+        "transformer.h.18.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.18.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.18.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.19.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.19.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.2.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.20.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.20.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.20.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.21.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.self_attention.dense.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.21.self_attention.query_key_value.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.22.input_layernorm.bias": "model-00005-of-00008.safetensors",
+        "transformer.h.22.input_layernorm.weight": "model-00005-of-00008.safetensors",
+        "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.22.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.22.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.23.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.23.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.24.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.24.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.25.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.mlp.dense_4h_to_h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.25.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.input_layernorm.bias": "model-00006-of-00008.safetensors",
+        "transformer.h.26.input_layernorm.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.26.mlp.dense_h_to_4h.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.self_attention.dense.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.26.self_attention.query_key_value.weight": "model-00006-of-00008.safetensors",
+        "transformer.h.27.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.27.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.27.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.28.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.28.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.29.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.29.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.3.input_layernorm.bias": "model-00001-of-00008.safetensors",
+        "transformer.h.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.3.self_attention.dense.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00008.safetensors",
+        "transformer.h.30.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.30.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.mlp.dense_4h_to_h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.mlp.dense_h_to_4h.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.30.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.31.input_layernorm.bias": "model-00007-of-00008.safetensors",
+        "transformer.h.31.input_layernorm.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.31.mlp.dense_4h_to_h.weight": "model-00008-of-00008.safetensors",
+        "transformer.h.31.mlp.dense_h_to_4h.weight": "model-00008-of-00008.safetensors",
+        "transformer.h.31.self_attention.dense.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.31.self_attention.query_key_value.weight": "model-00007-of-00008.safetensors",
+        "transformer.h.4.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.4.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.4.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.5.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.5.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.6.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.6.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.7.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.self_attention.dense.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.7.self_attention.query_key_value.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.8.input_layernorm.bias": "model-00002-of-00008.safetensors",
+        "transformer.h.8.input_layernorm.weight": "model-00002-of-00008.safetensors",
+        "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.8.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.8.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.input_layernorm.bias": "model-00003-of-00008.safetensors",
+        "transformer.h.9.input_layernorm.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.self_attention.dense.weight": "model-00003-of-00008.safetensors",
+        "transformer.h.9.self_attention.query_key_value.weight": "model-00003-of-00008.safetensors",
+        "transformer.ln_f.bias": "model-00008-of-00008.safetensors",
+        "transformer.ln_f.weight": "model-00008-of-00008.safetensors",
+        "transformer.word_embeddings.weight": "model-00001-of-00008.safetensors"
+    }
+}