When saving a LoRA model trained for gpt-oss to GGUF with standard command:
if True: model.save_pretrained_gguf("folder",tokenizer, quantization_method ="q8_0")

I get the following error:
RuntimeError: Unsloth: config.json does not exist inside {folder}

I am using BF16 version, but other quants have the same problem. I am using a proprietary dataset, which works fine with any other model. Finetuning part still works but problem occurs only in the gguf conversion part.