feat(mlx_lm): Nemotron (#949)

* feat: Nemotron

https://huggingface.co/nvidia/Minitron-4B-Base

This is basically Llama with partial RoPE and LayerNorm instead of
BatchNorm. Also they add 1 to the LayerNorm weight for some reason.

* fixup! feat: Nemotron

* nits

---------

Co-authored-by: Awni Hannun <awni@apple.com>

llms/mlx_lm/tuner/utils.py

@@ -93,6 +93,7 @@ def linear_to_lora_layers(
         "llama",
         "phi",
         "mixtral",
+        "nemotron",
         "stablelm",
         "qwen2",
         "qwen2_moe",