aimeri/spoomplesmaxx-mini-14B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: aimeri/spoomplesmaxx-mini-14B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-09-03 16:57:16 +08:00
commit 8bde24a940
8 changed files with 746 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

504
README.md Normal file
View File

@@ -0,0 +1,504 @@
---
tags:
- general-purpose
- roleplay
- creative-writing
- storywriting
- reasoning
- qwen3
- chatml
- finetune
- SFT
- text-generation-inference
language:
- en
- pt
base_model:
- Qwen/Qwen3-14B-Base
pipeline_tag: text-generation
library_name: transformers
license: apache-2.0
datasets:
- aimeri/spoomplesmaxx-sft-full-v2
---
<!doctype html>
<html lang="en">
<head>
<meta charset="UTF-8" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>SpoomplesMaxx V2.1 Mini 14B</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-V2.1-Mini-14B</h2>
<h3>"Flight of the Cockatiels"</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 and
reasoning.
</p>
<p>
The Mini brings the v2.1 data and training recipe
to a 14B you can run on a single 24GB card. Smaller
bird, same energy.
</p>
<div class="notice">
<h3>What's new in v2.1 Mini</h3>
<p>
The Mini keeps the v2.1 <strong>data mix</strong> — including the
long-context roleplay corpus where each in-character turn is
preceded by an explicit <code>&lt;think&gt;</code> planning
scratchpad — and swaps the base model down a weight class.
Qwen3-14B-Base was chosen after a long hunt: it is essentially the
only current dense (no MoE, no Mamba), non-VLM model in the
12&ndash;14B class with a true pretrained base available and enough
pretraining tokens (~36T) to skip continued pretraining entirely.
</p>
<pre class="code-block">
CHANGED SINCE v2.1 (30B)
- Base model: Granite 4.1 30B -> Qwen3-14B-Base. Template is now
standard ChatML with native &lt;think&gt;/&lt;/think&gt; reasoning.
- Control-token heal: a dedicated post-SFT training stage to revive
Qwen3-Base's dead special tokens (see notice below).
- Content-conditional thinking election (emergent -- see
"Thinking behavior").
UNCHANGED
- Same SFT corpus (aimeri/spoomplesmaxx-sft-full-v2), same story
scratchpad format, same personas.
- Still no tool-calling data -- reserved for a dedicated future run.
- Still focused on creative writing, roleplay, and companion use.
</pre>
</div>
<div class="notice">
<h3>The control-token heal (PSA for Qwen3-Base finetuners)</h3>
<p>
Qwen ships Qwen3-14B-Base with the ChatML/thinking tokens
(<code>&lt;|im_start|&gt;</code>, <code>&lt;|im_end|&gt;</code>,
<code>&lt;think&gt;</code>, <code>&lt;/think&gt;</code>, tool
tokens) present in the vocab but <strong>never trained</strong>:
their <code>lm_head</code> rows are literally one shared stub
vector (norm 0.286, pairwise cosine 1.000). A standard frozen-head
QLoRA SFT on this base learns to <em>reason</em> but physically
cannot <em>emit</em> <code>&lt;/think&gt;</code> or
<code>&lt;|im_end|&gt;</code> &mdash; the symptom is a perfect
reasoning trace that ends in a random stray token where the close
tag should be.
</p>
<p>
The fix shipped in this model: the special-token rows were grafted
from <code>Qwen/Qwen3-14B</code> (same vocab, dims, and lineage),
then a short single-GPU heal (500 steps, plain HF + PEFT, fresh
attn/MLP LoRA + trainable <code>embed_tokens</code> /
<code>lm_head</code>) taught the model to open and close the block
natively. Post-heal, P(<code>&lt;/think&gt;</code>) at true close
positions measures <strong>0.998</strong> and every generation
terminates on <code>&lt;|im_end|&gt;</code>. If you are finetuning
any Qwen3 base: check your special-token row norms and pairwise
cosines before you burn the GPU hours.
</p>
</div>
<h3>Thinking behavior</h3>
<p>
This model elects thinking <strong>by content</strong>. Reasoning-shaped
prompts and roleplay cards with the scratchpad open
<code>&lt;think&gt;</code> unprompted (18/20 in the greedy test
battery); casual chat skips the ceremony and just answers. With
SillyTavern cards as system prompts it reasons the scratchpad
correctly on its own.
</p>
<pre class="code-block">
MODE CONTROL (baked into the chat template):
enable_thinking=True forced thinking -- the template prefills
&lt;think&gt;\n so every turn reasons (deliberate
deviation from the stock Qwen3 template)
enable_thinking=False forced off -- empty &lt;think&gt;\n\n&lt;/think&gt;
block (Qwen3 convention); the reasoning
migrates into the visible answer
(unset) the model elects by content -- the default
election behavior described above
SILLYTAVERN: ST builds prompts itself. ChatML template; for
forced thinking use a deepseek-style reasoning
prefix that opens &lt;think&gt; (same trick as the 30B
macaws); no prefix = the model elects.
PARSER NOTE: in forced mode the open tag lives in the PROMPT,
not the output -- reasoning parsers that expect
the model to emit &lt;think&gt; itself (e.g. vLLM's
qwen3 parser) should use a deepseek-style parser
for that mode.
LONG CHATS: do NOT feed prior-turn think blocks back into
context (the chat template already strips them;
leave ST's "add reasoning to prompt" off).
Stale &lt;/think&gt; tokens in context get taxed by
repetition penalty and thinking can stop
terminating.
</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>Key Details</h3>
<pre class="code-block">
BASE MODEL: Qwen/Qwen3-14B-Base
LICENSE: apache-2.0
LANGUAGES: English & Portuguese (reasoning traces); multilingual via base</pre>
<h3>Training</h3>
<pre class="code-block">
DATASET: aimeri/spoomplesmaxx-sft-full-v2
STAGE 1: QLoRA SFT (4-bit NF4 base), Unsloth DDP, all-linear,
LoRA rank 128 / alpha 256
CONTEXT: up to 32,768 tokens, BFD sample packing (padding-free)
SCHEDULE: 2 epochs / 764 steps, lr 1e-4 cosine, warmup 0.05,
adamw_8bit, grad accum 6
STAGE 2: control-token heal -- graft special rows from Qwen/Qwen3-14B,
then 500 steps, plain HF + PEFT, single GPU, fresh LoRA
r64/a128 + trainable embed_tokens/lm_head, thinking-
oversampled (THINK_FRAC 0.7), embed lr 10x below trunk
RESULT: eval loss 4.02 -> 1.32 (train loss 1.60 -> 1.35); heal
held-out non-thinking loss 1.53 -> 1.31;
P(&lt;/think&gt;) at close = 0.998</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/[REPO]")
model = AutoModelForCausalLM.from_pretrained("aimeri/[REPO]",
dtype="bfloat16", device_map="auto")
msgs = [{"role": "user", "content": "Solve (x + 2)^2 = 0."}]
# enable_thinking=True -> forced thinking (template prefills <think>,
# so generated text starts INSIDE the block)
# enable_thinking=False -> forced off (empty think block in prompt)
# omit the kwarg -> the model elects by content
ids = tok.apply_chat_template(msgs, add_generation_prompt=True,
enable_thinking=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>

91
chat_template.jinja Normal file
View File

@@ -0,0 +1,91 @@
{%- if tools %}
{{- '<|im_start|>system\n' }}
{%- if messages[0].role == 'system' %}
{{- messages[0].content + '\n\n' }}
{%- endif %}
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
{%- else %}
{%- if messages[0].role == 'system' %}
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endfor %}
{%- for message in messages %}
{%- if message.content is string %}
{%- set content = message.content %}
{%- else %}
{%- set content = '' %}
{%- endif %}
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- if loop.index0 > ns.last_query_index %}
{%- if loop.last or (not loop.last and reasoning_content) %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- else %}
{{- '<|im_start|>' + message.role + '\n' + content }}
{%- endif %}
{%- if message.tool_calls %}
{%- for tool_call in message.tool_calls %}
{%- if (loop.first and content) or (not loop.first) %}
{{- '\n' }}
{%- endif %}
{%- if tool_call.function %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{{- '<tool_call>\n{"name": "' }}
{{- tool_call.name }}
{{- '", "arguments": ' }}
{%- if tool_call.arguments is string %}
{{- tool_call.arguments }}
{%- else %}
{{- tool_call.arguments | tojson }}
{%- endif %}
{{- '}\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if enable_thinking is defined and enable_thinking is false %}
{{- '<think>\n\n</think>\n\n' }}
{%- elif enable_thinking is defined and enable_thinking is true %}
{{- '<think>\n' }}
{%- endif %}
{%- endif %}

80
config.json Normal file
View File

@@ -0,0 +1,80 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": [
151645,
151643
],
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 17408,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 32768,
"max_window_layers": 40,
"model_type": "qwen3",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.5.0",
"unsloth_fixed": true,
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936
}

14
generation_config.json Normal file
View File

@@ -0,0 +1,14 @@
{
"bos_token_id": 151643,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"do_sample": true,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"repetition_penalty": 1.1,
"transformers_version": "4.51.0"
}

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b85ff491f675637f79b716c321030b7b10010b15e8d711d403ad9fb3821769a1
size 29536666272

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:476870a1f2fb6f6a2759a6ede2383bf9d5d738f17844563b65c91965b722ae09
size 11422924

15
tokenizer_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"is_local": true,
"model_max_length": 32768,
"pad_token": "<|endoftext|>",
"padding_side": "right",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}