Actual parameter setting for different sizes of the model?

[Lucas-TY]

 parser.add_argument(
        "--total-token",
        type=int,
        default=60,
        help="The maximum number of new generated tokens.",
    )
    parser.add_argument(
        "--depth",
        type=int,
        default=5,
        help="The maximum number of new generated tokens.",
    )

I noticed the actual depth is args.depth+1, and actual total-token is args.total_token - 1.

refer to this part of the code:

class Model(nn.Module):
    def __init__(self, config, load_emb=False, path=None, bias=True, total_tokens=63, depth=5, top_k=8, threshold=1.0):
        super().__init__()

        self.gradient_checkpointing = True
        self.padding_idx = config.pad_token_id
        self.vocab_size = config.vocab_size

        self.embed_tokens = nn.Embedding(config.vocab_size, config.hidden_size, self.padding_idx)
        if load_emb:
            from safetensors import safe_open
            import json
            try:
                with open(os.path.join(path, "model.safetensors.index.json"), "r") as f:
                    index_json = json.loads(f.read())
                    emb_path = index_json["weight_map"]["model.embed_tokens.weight"]
                with safe_open(os.path.join(path, emb_path),
                               framework="pt",
                               device="cpu") as f:
                    tensor_slice = f.get_slice("model.embed_tokens.weight")
                    vocab_size, hidden_dim = tensor_slice.get_shape()
                    tensor = tensor_slice[:, :hidden_dim].float()
            except:
                with open(os.path.join(path, "pytorch_model.bin.index.json"), "r") as f:
                    index_json = json.loads(f.read())
                    emb_path = index_json["weight_map"]["model.embed_tokens.weight"]
                weights = torch.load(os.path.join(path, emb_path))
                tensor = weights["model.embed_tokens.weight"].float()
            self.embed_tokens.weight.data = tensor

        self.top_k = top_k
        self.total_tokens = total_tokens - 1
        self.depth = depth
        self.threshold = math.log(threshold)

Could you please show me your settings for different sizes of the model?