Class Params

tokenizer/convert/convert.py:157–330

@dataclass
class Params:
    n_vocab:        int
    n_embd:         int
    n_layer:        int
    n_ctx:          int
    n_ff:           int
    n_head:         int
    n_head_kv:      int
    n_experts:      int | None = None
    n_experts_used: int | None = None
    f_norm_eps:     float | None = None

    rope_scaling_type: gguf.RopeScalingType | None = None
    f_rope_freq_base: float | None = None
    f_rope_scale: float | None = None
    n_orig_ctx: int | None = None
    rope_finetuned: bool | None = None

    ftype: GGMLFileType | None = None

    # path to the directory containing the model files
    path_model: Path | None = None

    @staticmethod
    def guessed(model: LazyModel) -> Params:
        # try transformer naming first
        n_vocab, n_embd = model["model.embed_tokens.weight"].shape if "model.embed_tokens.weight" in model else model["tok_embeddings.weight"].shape

        # try transformer naming first
        if "model.layers.0.self_attn.q_proj.weight" in model:
            n_layer = next(i for i in itertools.count() if f"model.layers.{i}.self_attn.q_proj.weight" not in model)
        elif "model.layers.0.self_attn.W_pack.weight" in model:   # next: try baichuan naming
            n_layer = next(i for i in itertools.count() if f"model.layers.{i}.self_attn.W_pack.weight" not in model)
        else:
            n_layer = next(i for i in itertools.count() if f"layers.{i}.attention.wq.weight" not in model)

        if n_layer < 1:
            raise Exception("failed to guess 'n_layer'. This model is unknown or unsupported.\n"
                            "Suggestion: provide 'config.json' of the model in the same directory containing model files.")

        n_head = n_embd // 128 # guessed
        n_mult = 256           # guessed

        # TODO: verify this
        n_ff = int(2 * (4 * n_embd) / 3)
        n_ff = n_mult * ((n_ff + n_mult - 1) // n_mult)

        return Params(
            n_vocab    = n_vocab,
            n_embd     = n_embd,
            n_layer    = n_layer,
            n_ctx      = -1,
            n_ff       = n_ff,
            n_head     = n_head,
            n_head_kv  = n_head,
            f_norm_eps = 1e-5,
        )