GGUF support

[sebaxakerhtc]

Hi. Can you add support of .gguf models?
Looks like it work with GGML only
For now I have this

sebaxakerhtc@llama:~/llama-telegram-bot$ python3 bot.py
llama.cpp: loading model from pytorch_model.bin
error loading model: unknown (magic, version) combination: 04034b50, 08080000; is this really a GGML file?
llama_init_from_file: failed to load model
Traceback (most recent call last):
  File "/home/sebaxakerhtc/llama-telegram-bot/bot.py", line 28, in <module>
    llama = Llama(model_path=MODEL_PATH, n_gpu_layers=int(GPU_LAYERS))
  File "/usr/local/lib/python3.10/dist-packages/llama_cpp/llama.py", line 197, in __init__
    assert self.ctx is not None
AssertionError