fix: Cleaner (maybe more correct?) splitting for gate/up

Branch: GraniteMoEShared

Signed-off-by: Gabe Goodhart <[email protected]>

Author: gabe-l-hart

convert_hf_to_gguf.py

@@ -5685,7 +5685,7 @@ def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iter
         if name.endswith("shared_mlp.input_linear.weight"):
             ffn_dim = self.hparams["shared_intermediate_size"]
             assert data_torch.shape[-2] == 2 * ffn_dim, "Merged FFN tensor size must be 2 * shared_intermediate_size"
-            gate, up = data_torch[..., :ffn_dim, :], data_torch[..., ffn_dim:, :]
+            gate, up = data_torch.split(ffn_dim, dim=-2)
             return [
                 (self.format_tensor_name(gguf.MODEL_TENSOR.FFN_GATE_SHEXP, bid), gate),
                 (self.format_tensor_name(gguf.MODEL_TENSOR.FFN_UP_SHEXP, bid), up),