Adding `safetensors` variant of this model (#1)

- Adding `safetensors` variant of this model (aafad727087163c37fd2eab8b8c7fd0afedbe8c8)


Co-authored-by: Safetensors convertbot <[email protected]>

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ef8dc1525108992df901b82167bcfcd61ace4364ebd65180026ab111ba4f35f
+size 9970745400

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8cb7ad4cc23ce77abf54802d0e315145240980c7a8c2b3d1b56482b56f2332f
+size 950154160

model.safetensors.index.json

@@ -0,0 +1,427 @@
+{
+    "metadata": {
+        "total_size": 10920847360
+    },
+    "weight_map": {
+        "embed_out.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.embed_in.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.final_layernorm.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.final_layernorm.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.0.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.1.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.10.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.11.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.12.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.13.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.14.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.15.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.16.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.17.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.18.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.19.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.2.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.20.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.21.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.22.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.23.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.24.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.25.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.26.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.27.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.28.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.29.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.3.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.30.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.30.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.30.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.30.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.30.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.31.self_attention.rotary_emb.inv_freq": "model-00002-of-00002.safetensors",
+        "megatron_gpt.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.4.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.5.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.6.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.7.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.8.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+        "megatron_gpt.layers.9.self_attention.rotary_emb.inv_freq": "model-00001-of-00002.safetensors"
+    }
+}