方程
方程
validate_credentials has been implemented and self-tested.
Added tests，because they use the real Gitee AI service, which requires a correctly filled access_token to run successfully. Therefore, the test command was not added to pytest_model_runtime.sh @crazywoola
因为前面的提示词限定了，让AI的回复只有“Y”或者“N”，所以此时，我们就可以“限制模型输出1个token”了 至于token=输入+ 输出 token 数之和，这一般是说的语言模型的能力，指某一个模型所能支持的最大tken数。 这里摘抄官网的[文档说明](https://platform.openai.com/docs/api-reference/completions/create)： > The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the completion. > > The token count of your prompt plus max_tokens cannot...