<h3 id="heading-37">Previous version</h3><p>v3 : same old training parameters version</p><p>v1 and v2 were abandoned because the outputs are poor, they were designed as lite version,</p><h3 id="heading-38">New version</h3><p>v4 : version with new training parameters</p><p>v5 : most optimized version with new training parameters</p><p>v4 and v5 also perform well with simple prompts (last 2 posts for example)</p><h3 id="heading-39"></h3><p><strong>without trigger words the outputs result slightly different, maybe worthwhile to try.</strong></p><p>Since new parameters perform better and more normal, next I will train new version for each model before. Hopefully that will be much faster.</p><p></p>

Files with SHA256: 28eff4f622228cda71f2bd72f870389ea7a30486bdd9d5a8badb0bd5bb971e73