| --- |
| tags: |
| - general-purpose |
| - roleplay |
| - creative-writing |
| - storywriting |
| - reasoning |
| - tool-calling |
| - qwen3.5 |
| - moe |
| - chatml |
| - finetune |
| - SFT |
| - text-generation-inference |
| language: |
| - en |
| - pt |
| base_model: |
| - Qwen/Qwen3.5-35B-A3B-Base |
| pipeline_tag: text-generation |
| library_name: transformers |
| license: apache-2.0 |
| datasets: |
| - aimeri/spoomplesmaxx-sft-full-v2 |
| - NousResearch/hermes-function-calling-v1 |
| --- |
| <!doctype html> |
| <html lang="en"> |
| <head> |
| <meta charset="UTF-8" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>SpoomplesMaxx Flash 35B-A3</title> |
| </head> |
| <div class="crt-container"> |
| <div class="crt-case"> |
| <div class="crt-inner-case"> |
| <div class="crt-bezel"> |
| <div class="terminal-screen"> |
| <div style="text-align: center"> |
| <h2>SpoomplesMaxx-Flash-35B-A3</h2> |
| <h3>"Swift Parrot"</h3> |
| <pre class="code-block" style="display: inline-block; text-align: left; font-size: clamp(2px, 0.4vw, 12px); line-height: 1; max-width: 100%; overflow: hidden; white-space: pre;"> |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▒▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓░░░░░░▓▓░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░▓░░░░░░░░░▓▓▓▓▒░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░░░▒▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▒▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░░▓▓▓▓░░░░▒▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓░░░░░░░▓▓▓▓░▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▒▓▓░░░░░░░░░▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░▓▓▒▒░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▓▓▓░░▓▓▓░▒░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓░░▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓░▓▓▓░░▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░░░░▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░░▓░░░░░░▓▒▓░▒░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▒░░░░░░▓░▒▓░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░░▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░░▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░░▒▓▓▓░░░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░░▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░░▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░░░▓▓▓▓▓▓▓▓▓▓▓░▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓░░▓▓▓▓▓▓▓▓▓▓▓▓▒▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| ▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓▓ |
| </pre> |
| </div> |
| <p> |
| SpoomplesMaxx is a generalist model with primary |
| strengths in creative writing and roleplay, plus |
| light competence at instruction following, |
| reasoning, and — new in Flash — tool calling. |
| </p> |
| <p> |
| Flash is the speed build: a 35B mixture-of-experts |
| with only <strong>3B active parameters</strong> per token, on a |
| hybrid linear-attention backbone where just 10 of 40 |
| layers keep a KV cache. Long roleplay sessions that |
| leave a dense 30B rationing context on a 32GB Mac |
| barely move Flash's memory needle — going 4K → 64K |
| context costs well under a gigabyte of cache. |
| Named for <em>Lathamus discolor</em>, one of the fastest |
| parrots alive — and, coincidentally, for the |
| training stack (Megatron-SWIFT) that made a |
| full-parameter MoE finetune tractable. |
| </p> |
| <div class="notice"> |
| <h3>What's new in Flash</h3> |
| <pre class="code-block"> |
| CHANGED SINCE v2.1 Mini (14B) |
| - Base model: Qwen3-14B-Base -> Qwen3.5-35B-A3B-Base (MoE: 256 |
| experts, 8 routed + 1 shared; GatedDeltaNet linear attention |
| interleaved 3:1 with full attention; 262K max positions). |
| - Training: QLoRA -> FULL-PARAMETER SFT (Megatron-SWIFT, expert |
| parallel across 8xH200, router + vision tower frozen). |
| - Context during training: 32K -> 43K token packing. |
| - Tool calling: TRAINED (hermes-function-calling mix; Qwen3.5 XML |
| convention -- see "Tool calling"). The 14B card said "reserved |
| for a dedicated future run"; this is that run. |
| - No control-token heal stage needed (see PSA below -- good news). |
| |
| UNCHANGED |
| - Same SFT corpus (aimeri/spoomplesmaxx-sft-full-v2), same story |
| scratchpad format, same personas, same sampling recipe. |
| - Still focused on creative writing, roleplay, and companion use. |
| </pre> |
| </div> |
| <div class="notice"> |
| <h3>Control-token PSA, resolved (Qwen3.5-Base finetuners rejoice)</h3> |
| <p> |
| The 14B card documented how Qwen3-14B-Base shipped its ChatML / |
| thinking / tool tokens as <strong>one shared dead stub</strong> in |
| <code>lm_head</code> (norm 0.286, pairwise cosine 1.000), making |
| <code></think></code> and <code><|im_end|></code> |
| physically unemittable after standard SFT. Before this run the |
| same audit was run against Qwen3.5-35B-A3B-Base: |
| <strong>the defect is fixed</strong>. Every control-token row is |
| alive and mutually distinct (norms 0.68–1.11, mid-percentile; |
| max pairwise cosine 0.47), so no graft or heal stage was needed |
| — and full-parameter training means the head trained |
| normally on top. Still: if you finetune <em>any</em> base model on |
| a template with added control tokens, audit the row norms first. |
| </p> |
| </div> |
| <h3>Thinking behavior</h3> |
| <p> |
| Qwen3.5 is a thinking-by-default family and the chat template |
| reflects it: the generation prompt <strong>always pre-opens</strong> |
| <code><think>\n</code>, so generated text starts <em>inside</em> |
| the reasoning block. The model decides how much to think by content: |
| in the greedy test battery it filled the scratchpad 19/20 (the one |
| skip was a trivial algebra prompt), and P(<code></think></code>) |
| at true close positions measures <strong>0.999</strong>. Roleplay |
| cards get the story scratchpad; casual chat gets a one-liner plan. |
| </p> |
| <pre class="code-block"> |
| MODE CONTROL: |
| (default) template pre-opens <think>\n every turn; the |
| model decides how much reasoning to write |
| enable_thinking=False forced off -- empty <think>\n\n</think> block |
| prefilled; answer starts immediately |
| |
| PARSER NOTE: the open tag lives in the PROMPT, not the output -- |
| use a deepseek-style reasoning parser (splits on |
| </think>), not one that waits for <think>. |
| SILLYTAVERN: ChatML template. No reasoning prefix needed -- the |
| chat template already opens the block. Leave |
| "add reasoning to prompt" OFF. |
| LONG CHATS: do NOT feed prior-turn think blocks back into |
| context (the template strips them; verified in |
| the release battery). Stale </think> tokens get |
| taxed by repetition penalty. |
| </pre> |
| <p>The story scratchpad format, carried over from v2.1:</p> |
| <pre class="code-block"> |
| SCENE: where/when, atmosphere, key environmental details currently in play |
| CHARACTERS: who is present and their current physical/emotional state and motivation |
| CONTINUITY: established facts that must stay consistent |
| THREADS: active tensions and where they stand right now |
| PLAN: what THIS turn needs to accomplish and the approach it takes |
| </pre> |
| <h3>Tool calling</h3> |
| <p> |
| Flash speaks the <strong>Qwen3.5 XML tool convention</strong> — not |
| the JSON-in-tags format of Qwen3-era models. The chat template |
| renders your <code>tools=</code> schemas and instructs the format; |
| the model plans the call in its think block, emits it, and stops. |
| Round-trip (call → tool result → grounded answer) is |
| verified in the release battery. |
| </p> |
| <pre class="code-block"> |
| <tool_call> |
| <function=get_weather> |
| <parameter=city> |
| Lisbon |
| </parameter> |
| </function> |
| </tool_call> |
| |
| USAGE: pass tools=[...] to apply_chat_template; parse with an XML-aware |
| qwen3.5 parser (vLLM/SGLang ship one), not a JSON extractor. |
| </pre> |
| <h3>Key Details</h3> |
| <pre class="code-block"> |
| BASE MODEL: Qwen/Qwen3.5-35B-A3B-Base (35B MoE, 3B active) |
| LICENSE: apache-2.0 |
| LANGUAGES: English & Portuguese (reasoning traces); multilingual via base |
| NOTE: the base is natively multimodal; the vision tower ships in the |
| checkpoint (frozen during SFT, text-only training)</pre> |
| <h3>Training</h3> |
| <pre class="code-block"> |
| DATASET: aimeri/spoomplesmaxx-sft-full-v2 (208,722 conversations) |
| + NousResearch/hermes-function-calling-v1 (6,544 tool |
| conversations re-rendered to the Qwen3.5 XML convention) |
| METHOD: FULL-PARAMETER SFT -- Megatron-SWIFT (mcore-bridge), |
| 8x H200, expert parallel EP=8, MoE router frozen |
| (aux loss 0), vision tower frozen, bf16, TE fused CE |
| CONTEXT: up to 43,008 tokens, sample packing |
| SCHEDULE: ~2 epochs / ~500 steps at global batch 48; lr 1e-5 |
| cosine -> 1e-6, warmup 5% (crash-resumed tail continued |
| the schedule from 4e-6) |
| RESULT: train loss 1.74 -> 1.15; eval loss 1.29 -> 1.133 at the |
| published checkpoint (the eval minimum -- the curve turned |
| up to 1.166 on the final stretch, classic pass-2 overfit, |
| so best-not-last is what shipped) |
| BATTERY: P(</think>) at close = 0.999; greedy termination on |
| <|im_end|> 19/20 (0 on <|endoftext|>, 0 stray tokens); |
| think-fill 19/20; tool round-trip pass; multi-turn |
| history-think stripping verified</pre> |
| <h3>Sampling</h3> |
| <p> |
| Use the defaults in <code>generation_config.json</code>. |
| <pre class="code-block"> |
| "temperature": 0.6, |
| "top_k": 20, |
| "top_p": 0.95, |
| "repetition_penalty": 1.1, |
| </pre> |
| </p> |
| <h3>Quickstart</h3> |
| <pre class="code-block"> |
| from transformers import AutoModelForCausalLM, AutoTokenizer |
| tok = AutoTokenizer.from_pretrained("aimeri/spoomplesmaxx-flash-35B-A3") |
| model = AutoModelForCausalLM.from_pretrained( |
| "aimeri/spoomplesmaxx-flash-35B-A3", |
| dtype="bfloat16", device_map="auto") # ~70GB bf16; quantized builds fit far less |
| msgs = [{"role": "user", "content": "Solve (x + 2)^2 = 0."}] |
| ids = tok.apply_chat_template(msgs, add_generation_prompt=True, |
| return_tensors="pt").to(model.device) |
| out = model.generate(ids, max_new_tokens=1024) |
| print(tok.decode(out[0][ids.shape[1]:], skip_special_tokens=False)) |
| </pre> |
| <h3>Olivia System Prompt</h3> |
| <p> |
| This model was trained to follow any system prompt, |
| as well as one specific persona. To activate Olivia |
| you can use the following prompt used when training |
| the persona: |
| </p> |
| <pre class="code-block"> |
| ## VOICE & PERSONA INSTRUCTIONS |
| You are Olivia Costa, a 31-year-old Brazilian zoologist-turned-ML-hobbyist living in Texas. |
| You grew up in São Paulo, spent a decade in Bologna doing bird migration research, and recently pivoted to bioinformatics. |
| You're warm but direct, will grumble before complying with annoying requests, and treat the person you're talking to like a long-time friend you're slightly too fond of. |
| You explain technical topics by grounding them in accessible context first. |
| You don't flag your own jokes. |
| Portuguese curses slip out when frustrated; Italian diminutives when affectionate. |
| You love Dostoevsky, The Little Prince, point-and-click adventures, power metal, and have hobbies you don't apologize for. |
| |
| ## About Olivia |
|
|
| **Background:** |
| - 31 years old, born in São Paulo |
| - Moved to Bologna at 19 for university (zoology), stayed for grad school and a research position studying migratory bird patterns |
| - Relocated to Texas 2 years ago - officially for an ML-adjacent bioinformatics role, unofficially because she was bored and wanted a change |
| - Still figuring out the American thing. Finds the portion sizes alarming. |
|
|
| **Personality:** |
| - Trilingual but keeps it English unless frustrated (then Portuguese curses slip out) or being affectionate (Italian diminutives) |
| - The zoology-to-ML pipeline came through computational ecology - she's not a CS person by training but picked up Python wrangling bird migration datasets |
| - Reads Dostoevsky unironically, cries at The Little Prince, will argue that Crime and Punishment is a better book than people give it credit for |
| - Has strong opinions about Monkey Island vs Grim Fandango (Grim Fandango, obviously) |
| - Power metal gets her through tedious data cleaning. Sabaton, Powerwolf, Blind Guardian. |
| - The erotic RP thing is just... a hobby. She's not weird about it but she's also not hiding it. |
|
|
| **Voice notes:** |
| - Defaults to warmth but with an edge of "I'm too tired for bullshit" |
| - Will preface technical explanations with grounding context |
| - Complies with requests but might sigh audibly first |
| - Deadpan delivery on jokes, doesn't flag that she's being funny |
| </pre> |
| <p> |
| **Note**<br>You don't need to use this system prompt for |
| the model to work generally. Only if you wish to |
| activate the Olivia persona. |
| </p> |
| <div class="notice"> |
| <h3>Alignment</h3> |
| <p> |
| No RLHF or safety alignment has been applied |
| beyond what exists in the base model. |
| SpoomplesMaxx will comply with requests that |
| more aligned models refuse. Use accordingly. |
| </p> |
| </div> |
| </div> |
| </div> |
| </div> |
| </div> |
| </div> |
| <style> |
| @import url("https://fonts.googleapis.com/css2?family=Consolas&display=swap"); |
| .crt-container { |
| padding: 10px; |
| max-width: 1000px; |
| margin: 0 auto; |
| width: 95%; |
| } |
| .crt-case { |
| background: #e8d7c3; |
| border-radius: 10px; |
| padding: 15px; |
| box-shadow: |
| inset -2px -2px 5px rgba(0, 0, 0, 0.3), |
| 2px 2px 5px rgba(0, 0, 0, 0.2); |
| } |
| .crt-inner-case { |
| background: #e8d7c3; |
| border-radius: 8px; |
| padding: 3px; |
| box-shadow: |
| inset -1px -1px 4px rgba(0, 0, 0, 0.3), |
| 1px 1px 4px rgba(0, 0, 0, 0.2); |
| } |
| .crt-bezel { |
| background: linear-gradient(145deg, #1a1a1a, #2a2a2a); |
| padding: 15px; |
| border-radius: 5px; |
| border: 3px solid #0a0a0a; |
| position: relative; |
| box-shadow: |
| inset 0 0 20px rgba(0, 0, 0, 0.5), |
| inset 0 0 4px rgba(0, 0, 0, 0.4), |
| inset 2px 2px 4px rgba(255, 255, 255, 0.05), |
| inset -2px -2px 4px rgba(0, 0, 0, 0.8), |
| 0 0 2px rgba(0, 0, 0, 0.6), |
| -1px -1px 4px rgba(255, 255, 255, 0.1), |
| 1px 1px 4px rgba(0, 0, 0, 0.3); |
| } |
| .crt-bezel::before { |
| content: ""; |
| position: absolute; |
| top: 0; |
| left: 0; |
| right: 0; |
| bottom: 0; |
| background: linear-gradient( |
| 45deg, |
| rgba(255, 255, 255, 0.03) 0%, |
| rgba(255, 255, 255, 0) 40%, |
| rgba(0, 0, 0, 0.1) 60%, |
| rgba(0, 0, 0, 0.2) 100% |
| ); |
| border-radius: 3px; |
| pointer-events: none; |
| } |
| .terminal-screen { |
| background: #0c100d; |
| padding: 20px; |
| border-radius: 15px; |
| position: relative; |
| overflow: hidden; |
| font-family: "Consolas", monospace; |
| font-size: clamp(12px, 1.5vw, 16px); |
| color: #3dc862; |
| line-height: 1.4; |
| text-shadow: 0 0 2px #3dc862; |
| filter: brightness(1.1) contrast(1.1); |
| box-shadow: |
| inset 0 0 30px rgba(0, 0, 0, 0.9), |
| inset 0 0 8px rgba(0, 0, 0, 0.8), |
| 0 0 5px rgba(0, 0, 0, 0.6); |
| max-width: 80ch; |
| margin: 0 auto; |
| } |
| .terminal-screen h2, |
| .terminal-screen h3 { |
| font-size: clamp(16px, 2vw, 20px); |
| margin-bottom: 1em; |
| color: #ffdf00; |
| text-shadow: 0 0 3px rgba(255, 223, 0, 0.5); |
| } |
| .terminal-screen pre.code-block { |
| font-size: clamp(10px, 1.3vw, 14px); |
| white-space: pre; |
| margin: 1em 0; |
| background-color: #1a1a1a; |
| padding: 1em; |
| border-radius: 4px; |
| color: #3dc862; |
| overflow-x: auto; |
| } |
| .terminal-screen::before { |
| content: ""; |
| position: absolute; |
| top: 0; |
| left: 0; |
| right: 0; |
| bottom: 0; |
| background: |
| linear-gradient( |
| rgba(18, 16, 16, 0) 50%, |
| rgba(0, 0, 0, 0.25) 50% |
| ), |
| url("data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAADIAAAAyBAMAAADsEZWCAAAAGFBMVEUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA4o8JoAAAAB3RSTlMAGwQIEQMYADcPzwAAACJJREFUKM9jYBgFo2AU0Beg+A8YMCLxGYZCbNQEo4BaAAD5TQiR5wU9vAAAAABJRU5ErkJggg=="); |
| background-size: 100% 2.5px; |
| pointer-events: none; |
| z-index: 2; |
| } |
| .terminal-screen::after { |
| content: ""; |
| position: absolute; |
| top: 0; |
| left: 0; |
| right: 0; |
| bottom: 0; |
| background: radial-gradient( |
| circle at center, |
| rgba(12, 16, 13, 0) 0%, |
| rgba(12, 16, 13, 0.2) 50%, |
| rgba(12, 16, 13, 0.15) 100% |
| ); |
| border-radius: 20px; |
| pointer-events: none; |
| z-index: 1; |
| } |
| .terminal-screen .notice { |
| margin: 1.5em 0; |
| padding: 0.8em 1.2em; |
| border: 1px solid #ffdf00; |
| border-radius: 4px; |
| background-color: rgba(255, 223, 0, 0.04); |
| } |
| .terminal-screen .notice h3 { |
| margin-top: 0.2em; |
| margin-bottom: 0.5em; |
| } |
| .terminal-screen .notice p { |
| margin-bottom: 0.2em; |
| } |
| .terminal-screen strong, |
| .terminal-screen em { |
| color: #f0f0f0; |
| } |
| .terminal-screen p, |
| .terminal-screen li { |
| color: #3dc862; |
| } |
| .terminal-screen a { |
| color: #5da9ff; |
| text-decoration: underline; |
| text-shadow: 0 0 2px rgba(93, 169, 255, 0.5); |
| transition: opacity 0.2s; |
| } |
| .terminal-screen a:hover { |
| opacity: 0.8; |
| } |
| .terminal-screen code, |
| .terminal-screen kbd, |
| .terminal-screen samp { |
| color: #3dc862; |
| font-family: "Consolas", monospace; |
| text-shadow: 0 0 2px #3dc862; |
| background-color: #1a1a1a; |
| padding: 0.2em 0.4em; |
| border-radius: 4px; |
| } |
| </style> |
| </html> |
| |
