Function convert_model_names

convert.py:1001–1036

(model: LazyModel, params: Params)

            for (name, tensor) in model.items()}

def convert_model_names(model: LazyModel, params: Params) -> LazyModel:
    tmap = gguf.TensorNameMap(params.arch, params.n_layer)
    should_skip: set[gguf.MODEL_TENSOR] = set(gguf.MODEL_TENSOR_SKIP.get(params.arch, []))

    tmp = model

    # HF models permut or pack some of the tensors, so we need to undo that
    for i in itertools.count():
        if f"model.layers.{i}.self_attn.q_proj.weight" in model:
            print(f"Permuting layer {i}")
            tmp[f"model.layers.{i}.self_attn.q_proj.weight"] = permute_lazy(model[f"model.layers.{i}.self_attn.q_proj.weight"], params.n_head, params.n_head)
            tmp[f"model.layers.{i}.self_attn.k_proj.weight"] = permute_lazy(model[f"model.layers.{i}.self_attn.k_proj.weight"], params.n_head, params.n_head_kv)
           #tmp[f"model.layers.{i}.self_attn.v_proj.weight"] =              model[f"model.layers.{i}.self_attn.v_proj.weight"]
        elif f"model.layers.{i}.self_attn.W_pack.weight" in model:
            print(f"Unpacking and permuting layer {i}")
            tmp[f"model.layers.{i}.self_attn.q_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 0, params.n_head, params.n_head)
            tmp[f"model.layers.{i}.self_attn.k_proj.weight"] = permute_part_lazy(model[f"model.layers.{i}.self_attn.W_pack.weight"], 1, params.n_head, params.n_head_kv)
            tmp[f"model.layers.{i}.self_attn.v_proj.weight"] = part_lazy        (model[f"model.layers.{i}.self_attn.W_pack.weight"], 2)
            del tmp[f"model.layers.{i}.self_attn.W_pack.weight"]
        else:
            break

    out: LazyModel = {}
    for name, lazy_tensor in model.items():
        tensor_type, name_new = tmap.get_type_and_name(name, try_suffixes = (".weight", ".bias")) or (None, None)
        if name_new is None:
            raise Exception(f"Unexpected tensor name: {name}")

        if tensor_type in should_skip:
            print(f"skipping tensor {name_new}")
            continue

        print(f"{name:48s} -> {name_new:40s} | {lazy_tensor.data_type.name:6s} | {lazy_tensor.shape}")
        out[name_new] = lazy_tensor

    return out

def postprocess_transpose(model: LazyModel) -> LazyModel:
    """Transpose ffn_down matrices for Axpy ops."""