deepseek-ai

/

deepseek-coder-33b-instruct

like 399

Yes, you can remove it.

The bellows are answers provided by deepseek coder 33B.

The trust_remote_code=True parameter in the from_pretrained method of the AutoTokenizer and AutoModelForCausalLM classes is used to indicate that the code being loaded from the remote repository should be trusted.

When you set trust_remote_code=True, the transformers library will execute the code from the remote repository, which can be a security risk if the code is not from a trusted source. This is because the code can execute arbitrary Python code, which can be used to perform malicious actions.

Therefore, it's generally recommended to set trust_remote_code=False to ensure that only trusted code is executed. This will prevent the execution of potentially harmful code.

If you want to use a version of the code without the trust_remote_code parameter, you can simply remove it from the from_pretrained method call. However, keep in mind that this will only work if the code is trusted. If the code is not trusted, it's recommended to use the trust_remote_code=False option to prevent the execution of potentially harmful code.

Thanks!