+- Inference (https://www.datasculpting.ai/inference)
+-- Forum: Prompting & Context Engineering (https://www.datasculpting.ai/inference/forumdisplay.php?fid=15)
+--- Forum: Structured Output (https://www.datasculpting.ai/inference/forumdisplay.php?fid=63)
+--- Thread: JSON mode across models for Mistral (/showthread.php?tid=651)
Pages:
1
2
Re: JSON mode across models for Mistral - cacheline - 10-09-2026
Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter more than it did.
Re: JSON mode across models for Mistral - fastbench - 10-09-2026
Quote:Ran a quick check on my box. The issue went away once I changed one setting and restarted the stack cleanly. I expected the model choice to matter mor
What worked for me was pretty simple. On GB200, the easiest win is often to back off the aggressive settings and see whether the problem survives. A lot of these threads end up being one bad config plus a pile of conclusions drawn from it.