Adding `safetensors` variant of this model

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1485593c55d3da33456d3da0357202354701aa671e19604f014e499f3de273
+size 1827774160

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f839830a978cfad234e2e8d060ae7efab7cfdf0acf6fcda32c3f99fec2ec7d
+size 1968291888

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4b391cdbfe1aea34d0b926a44934664f3af3fbada0c7a689fc8ce2bda8df931
+size 1927406936

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d6048a09b6df7b84f75fc782969603e271be01d28adbecaba63769c9e428e4
+size 1815217640

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:090298891fea341950f6d86a5d0ca1adbe800a386f03f58eb63ec33fcfe495e7
+size 1968291920

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0efed4801156ad154c5c0a611c4dac2c58ef9bb92c03328e79dab05e069491
+size 1927406960

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93044259fc4d183df8ba1efcd84e834c3e674181d3a4510e2557ba85b45fe11f
+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"
+    }
+}