python@ModelBase.register("LizzyForCausalLM")
class LizzyModel(Olmo2Model):
    def modify_tensors(self, data_torch: Tensor, name: str, bid: int | None) -> Iterable[tuple[str, Tensor]]:

        # 1. Lizzy: post_attn_norm -> llama.cpp: post_attention_norm
        if name.endswith(".post_attn_norm.weight"):
            yield (f"blk.{bid}.post_attention_norm.weight", data_torch)
            return

        # 2. Lizzy: post_mlp_norm -> llama.cpp: post_ffw_norm
        if name.endswith(".post_mlp_norm.weight"):
            yield (f"blk.{bid}.post_ffw_norm.weight", data_torch)
            return

        # 3. QK-Norms these mapped correctly via standard paths
        if name.endswith(".q_norm.weight"):
            yield (self.format_tensor_name(gguf.MODEL_TENSOR.ATTN_Q_NORM, bid), data_torch)
            return

        if name.endswith(".k_norm.weight"):
            yield (self.format_tensor_name(gguf.MODEL_TENSOR.ATTN_K_NORM, bid), data_torch)
            return

        # 4. All other tensors — pass through normally
        yield from super().modify_tensors(data_torch, name, bid)

The explicitly set RoPE scaling factor (config.rope_parameters['factor'] = 8.0)
does not match the ratio implicitly set by other parameters
(implicit factor = max_position_embeddings / original_max_position_embeddings = 4.0).
Using the explicit factor (8.0) in YaRN. This may cause unexpected behaviour.