first LoRA that actually helped

Thread Rating:

0 Vote(s) - 0 Average
1
2
3
4
5

Linear Mode

first LoRA that actually helped

batchfield55 Offline

Offline

Junior Member

Posts: 40
Threads: 4
Joined: Sep 2026
Reputation: 0

#8

10-14-2026, 03:51 AM

Quote:Tried to reproduce it just now. My result was mixed: first run looked bad, second run looked normal. The main thing that moved was latency, not qualit

Thanks, that helps. I ended up in about the same place using vLLM. I got better results once I stopped chasing one metric and just looked at whether the workflow felt usable.

Find

Reply

« Next Oldest | Next Newest »

Messages In This Thread

first LoRA that actually helped - by batchsize - 10-06-2026, 11:41 AM

Re: first LoRA that actually helped - by localtinker - 10-08-2026, 11:52 AM

Re: first LoRA that actually helped - by torchshed66 - 10-08-2026, 12:27 PM

Re: first LoRA that actually helped - by kernelarch - 10-10-2026, 12:31 AM

Re: first LoRA that actually helped - by localtinker - 10-14-2026, 01:49 AM

Re: first LoRA that actually helped - by batchsize - 10-16-2026, 05:08 PM

Re: first LoRA that actually helped - by rocmrunner40 - 10-11-2026, 12:48 AM

Re: first LoRA that actually helped - by batchfield55 - 10-14-2026, 03:51 AM

Re: first LoRA that actually helped - by llm_wren - 10-15-2026, 05:00 AM

Re: first LoRA that actually helped - by benchplease - 10-11-2026, 01:41 AM

Re: first LoRA that actually helped - by cacheline - 10-15-2026, 04:19 AM

Re: first LoRA that actually helped - by benchplease - 10-15-2026, 04:36 AM

Re: first LoRA that actually helped - by batchsize - 10-19-2026, 12:38 AM

Re: first LoRA that actually helped - by nanobrook - 10-19-2026, 01:23 AM

Re: first LoRA that actually helped - by rocmriley - 10-19-2026, 02:11 AM

View a Printable Version

Forum Jump:

Users browsing this thread: 1 Guest(s)