JaéGeR

Results 5 comments of JaéGeR

the xterm launches into a "Google 403. That's an error" window

@prikarsartam I have employed reasonable amount of time on this and encountered a way to make it work!! I hope this won't waste yours's time or anyone who encounters it...

Added dynamic context size. This is perfect for servers running llama models as a service.

Next goal is to get a dynamic context size working without the need for resetting memory. Is it possible? Let's see!!

Added dynamic context size. This is perfect for servers running llama models as a service.

Hey, @ggerganov Please have a look at this, this can be helpful for the servers which might need a dynamic context size, which would prevent it from terminating with errors...

Added dynamic context size. This is perfect for servers running llama models as a service.

@ggerganov So if the application allocates more amount of memory before hand, what's the significance of context size ```(n_ctx)```? Because earlier when I was testing one of the example codes,...

Added dynamic context size. This is perfect for servers running llama models as a service.

Finally achieved Dynamic modification of the context size without resetting the memory.