llama : add support for Nemotron 3 Super (#20411)

* llama : add support for Nemotron 3 Super

This commit adds support for the Nemotron 3 Super model (120B.A12B)
enabling this model to be converted to GGUF format and run in llama.cpp.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Matt Clayton <156335168+mattjcly@users.noreply.github.com>

gguf-py/gguf/tensor_mapping.py

@@ -571,6 +571,14 @@ class TensorNameMap:
             "model.layers.{bid}.mlp.experts.gate_up_proj",
         ),
 
+        MODEL_TENSOR.MOE_LATENT_DOWN: (
+            "backbone.layers.{bid}.mixer.fc1_latent_proj",                 # nemotron 3 super
+        ),
+
+        MODEL_TENSOR.MOE_LATENT_UP: (
+            "backbone.layers.{bid}.mixer.fc2_latent_proj",                 # nemotron 3 super
+        ),
+
         # Feed-forward down
         MODEL_TENSOR.FFN_DOWN: (
             "gpt_neox.layers.{bid}.mlp.dense_4h_to_h",                # gptneox