model fails to load when verbose=False

[amaiya]

Prerequisites

Please answer the following questions for yourself before submitting an issue.

• [X ] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
• [ X] I carefully followed the README.md.
• [ X] I searched using keywords relevant to my issue to make sure that I am creating a new issue that is not already open (or closed).
• [ X] I reviewed the Discussions, and have a new bug or useful enhancement to share.

Expected Behavior

When supplying verbose=False to Llama, the model should load as expected.

Current Behavior

When verbose=False, the model fails to load:

from llama_cpp import Llama
llm = Llama(model_path='/tmp/model.gguf', verbose=False)
# ERROR:
# [/usr/local/lib/python3.10/dist-packages/llama_cpp/utils.py](https://localhost:8080/#) in __enter__(self)
#      9         self.errnull_file = open(os.devnull, "w")
#     10 
#---> 11         self.old_stdout_fileno_undup = sys.stdout.fileno()
#     12         self.old_stderr_fileno_undup = sys.stderr.fileno()
#     13 

#UnsupportedOperation: fileno

Environment and Context

The problem happens on Google Colab and a user reported this problem occurring on Windows 11, as well. Doesn't seem to happen on Ubuntu (or Ubuntu in WSL), though.

A Google Colab notebook reproducing the issue is available here.

Failure Information (for bugs)

# [/usr/local/lib/python3.10/dist-packages/llama_cpp/utils.py](https://localhost:8080/#) in __enter__(self)
#      9         self.errnull_file = open(os.devnull, "w")
#     10 
#---> 11         self.old_stdout_fileno_undup = sys.stdout.fileno()
#     12         self.old_stderr_fileno_undup = sys.stderr.fileno()
#     13 

Steps to Reproduce

A Google Colab notebook reproducing the issue is available here.