Update models

.gitattributes

@@ -33,3 +33,20 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q8_0-00001-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-Q8_0-00002-of-00002.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-f16-00001-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-f16-00002-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-f16-00003-of-00004.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3_1-Nemotron-51B-Instruct-f16-00004-of-00004.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3_1-Nemotron-51B-Instruct-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f1d6ad4df6fa589194203235d19bb31315cd73beb3ed2dffb02a6eb1d404ac9
+size 19418642464

Llama-3_1-Nemotron-51B-Instruct-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe29ae0b25627ac8631a34ca6f11d572ae4a0bd6c1f8650f960a0faf7fe69b0
+size 27349751840

Llama-3_1-Nemotron-51B-Instruct-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8595b234baa5fc3dc14db611793cedcdb3ab73bcc421bacc46a15a4ba6bb57b
+size 25182345248

Llama-3_1-Nemotron-51B-Instruct-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2b0a9330eafc8fb6cde9285e7cd1c9b9a081e4ecd68f02fcb8e3b1459eaa68
+size 22652393504

Llama-3_1-Nemotron-51B-Instruct-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624711249056e4dc79bda0090015f3ed0a44fe7ca35a2a91579efe90b92908aa
+size 29252368416

Llama-3_1-Nemotron-51B-Instruct-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db50b770b4cc7918f1a25f204609c4c478e41c2f10499ec900259cb052948c11
+size 31037306912

Llama-3_1-Nemotron-51B-Instruct-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:041d5660e8f40b1fe28c65c522e92814cb855426187aae81ca9359ca10e46df5
+size 29484496928

Llama-3_1-Nemotron-51B-Instruct-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f6baa9e8ba28870f76093655dcf04b9a4439a8edf4b51efc4725c44684d1c24
+size 35558504480

Llama-3_1-Nemotron-51B-Instruct-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e19d5f2172cb51bcb3dd22391cebaf4c7f0210c562200ae671d8640e115de36
+size 36465391648

Llama-3_1-Nemotron-51B-Instruct-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:906aefa4926bec89d3aff281db866bb02e4ed79792566b28cc3d6a8bebcb5c79
+size 35558504480

Llama-3_1-Nemotron-51B-Instruct-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d66d3daee89d9e2596841f3589b3268ef060aef1513070a5ce390ce00adf12f
+size 42258774048

Llama-3_1-Nemotron-51B-Instruct-Q8_0-00001-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed2a1ad93790fcfe630e5755f5ce18d9fd7a04808e36343f3b000bde61ffa55
+size 29826134528

Llama-3_1-Nemotron-51B-Instruct-Q8_0-00002-of-00002.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20fc51b96935e0e17daee28f9694ef85cc7f66faabf3ea0d2a5f126e958fbf9
+size 24905238240

Llama-3_1-Nemotron-51B-Instruct-f16-00001-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c29966a7c3b2172525e4b9b29de9391ac1507476e26ae09486fb0953501c5c47
+size 29772092192

Llama-3_1-Nemotron-51B-Instruct-f16-00002-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67d59882c28b27005f0551e3ece2e49c37a9096022f08b1cb228f8cefc09e75c
+size 29562578048

Llama-3_1-Nemotron-51B-Instruct-f16-00003-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:534c2dd1ee26a2fbf3979582b0fdafa9bd01e9d3f0eb7d78a506ab10f5bb0897
+size 29596988128

Llama-3_1-Nemotron-51B-Instruct-f16-00004-of-00004.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82558d958d66febc358278b3c96b4479e2c002dd4b7babe49cbf111cc05813f3
+size 14080741216

config.json

@@ -0,0 +1,1004 @@
+{
+  "architectures": [
+    "DeciLMForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_decilm.DeciLMConfig",
+    "AutoModelForCausalLM": "modeling_decilm.DeciLMForCausalLM"
+  },
+  "block_configs": [
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 16,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 32,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 32,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 64,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 64,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 32,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 32,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 64,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 32,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 32,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 2.625,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": true,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": null,
+        "no_op": false,
+        "replace_with_linear": true
+      },
+      "ffn": {
+        "ffn_mult": 1.3125,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    },
+    {
+      "attention": {
+        "n_heads_in_group": 8,
+        "no_op": false,
+        "replace_with_linear": false
+      },
+      "ffn": {
+        "ffn_mult": 5.25,
+        "no_op": false,
+        "replace_with_linear": false
+      }
+    }
+  ],
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "nemotron-nas",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 128256
+}