Adding `safetensors` variant of this model

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a0c6c24292ec2ea55c55e23df5ad02a5db7c358ade81e0bb922aa7c5b4c60a
+size 9986226424

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5fb0a573063d54ce6c4ba257f6408b3fc197bd60063783127664279e407e8b9
+size 2500968648

model.safetensors.index.json

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