Adding `safetensors` variant of this model (#23)

- Adding `safetensors` variant of this model (c2d28f08b86bacac392140d0f6b26c05d567321f)


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

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b1052386eac358a18add3d0f92521c85ab338979da8eeb08a6499555b857f80d
+size 1827774160

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f88d7f69a3940711b87308eb20dd0544df22aff81134fa0d5160d3c859f5d321
+size 1968291888

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:447d41b7c5e7b2558905c98733469aa9e132540c91e13c4cdd7bfc58b60cc650
+size 1927406936

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386305288e2bcc4a26fcffef433c94592d155bf36e365f054f63d3e6b55a1429
+size 1815217640

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c304e2821774d649997d1f5ae5fa12afd4d1dc5fea2bf6e8b829405b81fa7f2
+size 1968291920

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef45bbd33d6d540d3d3523bb169b52b91b9e265176ab7efc6838233bc3b7e95d
+size 1927406960

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eb545c6aa8a839c56a78b80331fcb4fa403341925f79fb6a761e2e847bf1e40
+size 1052805400

model.safetensors.index.json

@@ -0,0 +1,207 @@
+{
+    "metadata": {
+        "total_size": 12487168064
+    },
+    "weight_map": {
+        "transformer.embedding.word_embeddings.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.final_layernorm.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.0.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.0.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.0.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.1.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.10.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.10.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.10.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.10.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.10.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.10.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.11.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.12.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.12.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.12.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.12.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.12.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.13.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.13.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.13.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.13.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.13.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.13.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.13.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.14.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.15.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.mlp.dense_4h_to_h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.mlp.dense_h_to_4h.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.16.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.17.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.17.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.17.self_attention.dense.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.17.self_attention.query_key_value.bias": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.17.self_attention.query_key_value.weight": "model-00004-of-00007.safetensors",
+        "transformer.encoder.layers.18.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.18.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.18.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.18.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.18.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.18.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.18.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.19.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.2.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.2.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.2.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.20.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.20.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.20.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.20.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.20.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.20.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.mlp.dense_4h_to_h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.mlp.dense_h_to_4h.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.self_attention.dense.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.self_attention.query_key_value.bias": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.21.self_attention.query_key_value.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+        "transformer.encoder.layers.22.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.22.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.22.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.22.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.22.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.22.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.23.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.24.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.mlp.dense_4h_to_h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.25.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.26.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.26.mlp.dense_h_to_4h.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.26.self_attention.dense.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.26.self_attention.query_key_value.bias": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.26.self_attention.query_key_value.weight": "model-00006-of-00007.safetensors",
+        "transformer.encoder.layers.27.input_layernorm.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.27.mlp.dense_4h_to_h.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.27.mlp.dense_h_to_4h.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.27.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.27.self_attention.dense.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.27.self_attention.query_key_value.bias": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.27.self_attention.query_key_value.weight": "model-00007-of-00007.safetensors",
+        "transformer.encoder.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.3.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.3.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.3.self_attention.dense.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.3.self_attention.query_key_value.bias": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.3.self_attention.query_key_value.weight": "model-00001-of-00007.safetensors",
+        "transformer.encoder.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.4.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.4.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.4.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.4.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.4.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.5.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.6.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.mlp.dense_4h_to_h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.mlp.dense_h_to_4h.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.self_attention.dense.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.self_attention.query_key_value.bias": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.7.self_attention.query_key_value.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+        "transformer.encoder.layers.8.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.8.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.8.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.8.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.8.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.8.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.input_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.mlp.dense_4h_to_h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.mlp.dense_h_to_4h.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.self_attention.dense.weight": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.self_attention.query_key_value.bias": "model-00003-of-00007.safetensors",
+        "transformer.encoder.layers.9.self_attention.query_key_value.weight": "model-00003-of-00007.safetensors",
+        "transformer.output_layer.weight": "model-00007-of-00007.safetensors",
+        "transformer.rotary_pos_emb.inv_freq": "model-00001-of-00007.safetensors"
+    }
+}