Method write_all

utils/convert-ms-to-gguf-bitnet.py:1314–1344

(
        fname_out: Path, ftype: GGMLFileType, params: Params, model: LazyModel, vocab: BaseVocab, svocab: gguf.SpecialVocab,
        concurrency: int = DEFAULT_CONCURRENCY, endianess: gguf.GGUFEndian = gguf.GGUFEndian.LITTLE,
        pad_vocab: bool = False,
    )

    @staticmethod
    def write_all(
        fname_out: Path, ftype: GGMLFileType, params: Params, model: LazyModel, vocab: BaseVocab, svocab: gguf.SpecialVocab,
        concurrency: int = DEFAULT_CONCURRENCY, endianess: gguf.GGUFEndian = gguf.GGUFEndian.LITTLE,
        pad_vocab: bool = False,
    ) -> None:
        check_vocab_size(params, vocab, pad_vocab=pad_vocab)

        of = OutputFile(fname_out, endianess=endianess)

        if 'bitnet' in of.gguf.arch:
            svocab.chat_template = "{% for message in messages %}{% if loop.first %}{{ bos_token }}{% endif %}{% if message['role'] == 'user' %}{{ 'Human: ' + message['content'] + '\\n\\nBITNETAssistant: ' + eos_token }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token }}{% endif %}{% endfor %}"

        # meta data
        of.add_meta_arch(params)
        if isinstance(vocab, Vocab):
            of.add_meta_vocab(vocab)
            of.add_meta_special_vocab(svocab)
        else:  # NoVocab
            of.gguf.add_tokenizer_model(vocab.tokenizer_model)

        # tensor info
        for name, lazy_tensor in model.items():
            of.add_tensor_info(name, lazy_tensor)

        of.write_meta()
        of.write_tensor_info()

        # tensor data
        of.write_tensor_data(ftype, model, concurrency)

        of.close()


def pick_output_type(model: LazyModel, output_type_str: str | None) -> GGMLFileType: