Upload LlamaForCausalLM

config.json

@@ -23,6 +23,19 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
+  "quantization_config": {
+    "backward_dtype": "bf16",
+    "forward_dtype": "nvfp4",
+    "forward_method": "abs_max",
+    "hadamard_group_size": 16,
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "pseudoquantization": false,
+    "quant_method": "fp_quant",
+    "store_master_weights": false,
+    "transform_init": "hadamard"
+  },
   "rms_norm_eps": 1e-05,
   "rope_scaling": {
     "factor": 8.0,

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ed96e68ce9efab0e4d1d98b42eb3a65ea1a25658786642e11a34bc4954e04d
+size 4977475024

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f70af9efce273f2dbb03522ea4532a75dea16add2fa30bb07e8040d5a183b252
+size 1050673280