Adding `safetensors` variant of this model (#13)

- Adding `safetensors` variant of this model (e486a3b87ff20d70293084fdfaad8ff34ba291d6)


Co-authored-by: Safetensors convertbot <SFconvertbot@users.noreply.huggingface.co>

model-00001-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:256586f41e894087ca3b02830874f02cfe93b95566b17c4f93d4e63c7f188502
+size 1917134504

model-00002-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1e17ea4569d52e86c8ac4db4cd5b73af15954b133adf8ffb3d44f5c00296f5
+size 1986949128

model-00003-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9730b1c37671eab931db772ab8d6dc36eb0e136fad27a3e858e65c7c481cd15
+size 1905502376

model-00004-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02d890951f7f34723009796a6a2cd6f10311dd0c0b72a914fb8749dc7bd8316a
+size 1905520808

model-00005-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49cc2958d851e0a13fed56073df3ed987a1b1130af74047653c7fbb701ea0d0
+size 1986949160

model-00006-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a41129382c2aaeb800d551ec655b7c09b2211bd8d03c640c932163deed162b
+size 1905502408

model-00007-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9443bfbbf8ebb44b0fb84f579c509134fb555353b3d90cb8ea0cf7943e3160ec
+size 1905520808

model-00008-of-00008.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b671c8df63598a21bdf2432bb8934a639bfcafc8be68a9965b58fa24d7daf6d
+size 921323816

model.safetensors.index.json

@@ -0,0 +1,203 @@
+{
+    "metadata": {
+        "total_size": 14434379520
+    },
+    "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"
+    }
+}