+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Harnesses, Agents & Orchestration (https://www.datasculpting.ai/inference/forumdisplay.php?fid=11)
+--- Forum: Routers (https://www.datasculpting.ai/inference/forumdisplay.php?fid=45)
+--- Thread: cleaning small domain dataset (/showthread.php?tid=506)
cleaning small domain dataset - forgemixer - 09-27-2026
Posting this in case it saves someone else a little time.
I'm not trying to build a perfect architecture diagram. I just want a sane starting point around Ollama and 7900 XTX.
Would rather learn from your scars than collect my own all at once.
Re: cleaning small domain dataset - bytesupply76 - 09-27-2026
A couple things I'd check first. If you're on llama.cpp, I'd confirm the version first and then reduce variables until the behavior is obvious. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.
Re: cleaning small domain dataset - deltapoint17 - 09-27-2026
That matches what I was seeing. That matches what I saw on B200.
Re: cleaning small domain dataset - orbitgarden - 09-28-2026
Thanks, that helps. I ended up in about the same place using Ollama.
Re: cleaning small domain dataset - batchember - 09-28-2026
Can you fill in a bit more context? Do you see the same thing with a smaller batch or shorter prompt?
Re: cleaning small domain dataset - plainworks - 09-29-2026
A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with DeepSeek and compare from there.