Improve error messages

[mausch]

Repro steps:

1. Go to https://huggingface.co/HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive
2. Click "use this model" -> colab
3. Run code on colab

Generated code is:

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive",
	filename="Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-BF16.gguf",
)

which fails with:

ValueError                                Traceback (most recent call last)

[/tmp/ipykernel_1917/696730726.py](https://localhost:8080/#) in <cell line: 0>()
      3 from llama_cpp import Llama
      4 
----> 5 llm = Llama.from_pretrained(
      6         repo_id="HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive",
      7         filename="Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-BF16.gguf",

2 frames

[/usr/local/lib/python3.12/dist-packages/llama_cpp/_internals.py](https://localhost:8080/#) in __init__(self, path_model, params, verbose)
     56 
     57         if model is None:
---> 58             raise ValueError(f"Failed to load model from file: {path_model}")
     59 
     60         vocab = llama_cpp.llama_model_get_vocab(model)

ValueError: Failed to load model from file: /root/.cache/huggingface/hub/models--HauhauCS--Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive/snapshots/53367faad177ee6a23601983cdac4308b51393df/./Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive-BF16.gguf

This error message is not actionable as it doesn't say why it failed to load so the user can't do much about it.