Jake Nelson
Jake Nelson
@naranjarosa Hi Naran, I am concerned you are planning to use the given code for nefarious purposes. Can you confirm your reasoning behind wanting to make the form functional? I...
Same here, it seems really slow for me too on a TPU.
Update: I managed to get it working. The first call to the API seems to take a long time as it caches "whatever" internally - it's not very clear. Once...
It is not clear enough
This feature is pending,
@teknium1 how would one do so? I am a bit of a newbie here, is the process easy? Else I may find help elsewhere.
@teknium1 I've done a bit of research, and what you really want to do is to increase the size of the "context window", this is effectively how many tokens the...
Or very roughly 136 minutes of non-stop talking at rate of 183 words per minute.
I'm referencing GPT4-32k's max context size. The context size does seem to pose an issue, but I've devised a cheap solution.  I was thinking why not 1) take in...
The code seems to spam org.asynchttpclient.netty.channel.NettyChannelConnector$1.operationComplete()
> Is this happening under heavy load? This is indeed happening under heavy load (800+ requests per second). I chose this library as it's performant, but it seems to also...