Replies: 1 comment
|
发现可以通过配置文件覆盖模型长度、调整保留上下文长度。让 kimi 自己改就行。 It was found that the model length can be overridden and the retention context length adjusted through the configuration file. Just let kimi change it himself. |
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
升级了 Allegro 结果发现套餐好像更不经用了,猜测是上下文太长即使算上 cache 也不划算,而 Kimi Code 只会在接近限制时触发压缩上下文,希望可以配置自动 compact 的阈值。
After upgrading Allegro, I found that the package seems to be less durable. I guess the context is too long, even including cache, and it is not cost-effective. Kimi Code will only trigger the compression context when it is close to the limit. I hope the threshold for automatic compaction can be configured.
All reactions