You need to keep testing models in pytorch, not just GGUF, to catch this bug. If you submit it for evaluation on the open leaderboard, it will abort.

For those who need a bit of Python to test their merged models:

import os
from typing import List

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM

def main(checkpoint: str) -> None:
    """Load and return tokenizers and models for specified checkpoints."""
    
    tokenizers = [AutoTokenizer.from_pretrained(checkpoint)]
    print(f"Loaded tokenizer from {checkpoint}")
   
    models = [
        AutoModelForCausalLM.from_pretrained(
            checkpoint, device_map="auto", torch_dtype=torch.bfloat16
        ).to("cuda" if torch.cuda.is_available() else "cpu")
    ]
    
    for model in models:
        print(f"Loaded model to {model.device}")

def cli():
    """CLI entry point."""
    import argparse
    
    parser = argparse.ArgumentParser(description='Load a tokenizer and model from a given checkpoint.')
    parser.add_argument('checkpoint', type=str, help='The pre-trained checkpoint name or path')
    
    args = parser.parse_args()
    
    main(args.checkpoint)

if __name__ == "__main__":
    cli()