Upload 5 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* 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
+AETEG6110A00KPFHTKMZVNG5C0.jpeg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,174 @@
+---
+license: other
+license_name: mrl
+language:
+- en
+- zh
+base_model:
+- mistralai/Ministral-8B-Instruct-2410
+library_name: transformers
+tags:
+- axolotl
+- roleplay
+- conversational
+- chat
+---
+
+<style>
+    main {
+        --creep-bg: #0f0f0f;
+        --blood-rust: #5e2e28;
+        --faded-white: #e8e8e8;
+        background: var(--creep-bg);
+        border-radius: 10px;
+    }
+    main, details {
+        display: flex;
+        flex-direction: column;
+        align-items: center;
+        padding: 15px;
+        overflow-x: scroll;
+        scrollbar-width: none;
+    }
+    .warning-box {
+        background: #2d1a1a;
+        border: 1px solid var(--blood-rust);
+        padding: 15px;
+        margin: 20px 0;
+        position: relative;
+        overflow: hidden;
+    }
+    .warning-box::before {
+        content: '';
+        position: absolute;
+        top: 0;
+        left: -10%;
+        width: 120%;
+        height: 100%;
+        background: linear-gradient(90deg, transparent 0%, #ff000020 50%, transparent 100%);
+        animation: scan 4s infinite linear;
+    }
+    .content-block {
+        background: #1a1a1a;
+        border: 1px solid #333;
+        border-radius: 4px;
+        padding: 20px;
+        margin: 15px 0;
+        box-shadow: 0 2px 8px rgba(0,0,0,0.3);
+        position: relative;
+    }
+    code {
+        background: #000;
+        color: #f8f8f8;
+        padding: 4px 6px;
+        border-radius: 3px;
+        font-family: monospace;
+        border: 1px solid #333;
+    }
+    .spoiler-text {
+        background: linear-gradient(45deg, #ff3b3b, #ff6b6b);
+        -webkit-background-clip: text;
+        color: transparent;
+        text-shadow: 0 0 12px rgba(255,59,59,0.5);
+        animation: glitch 1s infinite steps(2);
+    }
+    img {
+        max-width: min(90vw, 400px);
+        border-radius: 6px;
+        filter: brightness(0.95) contrast(1.1);
+    }
+    @media (max-width: 768px) {
+        main {
+            padding: 10px;
+        }
+        .content-block {
+            padding: 15px;
+            margin: 10px 0;
+        }
+        details[open] {
+            padding-bottom: 20px;
+        }
+    }
+    @keyframes glitch {
+        0% { transform: translateX(0); }
+        25% { transform: translateX(-1px); }
+        50% { transform: translateX(1px); }
+        75% { transform: translateX(-1px); }
+        100% { transform: translateX(0); }
+    }
+    @keyframes scan {
+        0% { transform: translateX(-20%); }
+        100% { transform: translateX(120%); }
+    }
+</style>
+
+<main>
+<img src="Playtime_Logo.webp" alt="Playtime Co. logo" style="transform: rotate(-1deg); box-shadow: 0 4px 20px rgba(0,0,0,0.4);">
+
+<div style="font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif; line-height: 1.6; max-width: 800px; margin: 0 auto; color: var(--faded-white);">
+
+<section style="margin-bottom: 30px;">
+<p style="font-size: 1.1rem; background: #1a1a1a; padding: 20px; border-radius: 6px; border: 1px solid #333; position: relative;">
+<span style="font-weight: 600; color: #d44d4d;">Us here at Playtime Co.</span> are excited to welcome you to our QA staff! As a signatory of the Employee Confidentiality Agreement, you are required to keep all information regarding the company and our research confidential.
+</p>
+
+<p style="font-style: italic; color: #888; text-align: center; margin: 25px 0; text-shadow: 0 1px 3px rgba(0,0,0,0.5);">
+With that out of the way...
+</p>
+</section>
+
+<details>
+<summary style="font-size: 1.6rem; cursor: pointer; padding: 15px; background: #2d1a1a; color: white; border-radius: 4px; border: 1px solid #442222; transition: 0.2s;">
+<span class="spoiler-text">A̶͇͊r̵͎̭͗͛e̶̯̘̋ ̵̤͖̄̕y̶̩̎o̵̡̿u̴̙̅͂ ̵̖̋r̷̮͖̓ě̵̪̹̈́a̸̠̅d̵͖̖̔̋ẙ̷͙̃ ̷̮͖̋̈́t̴͉̅́ȍ̴̹̞ ̵̖̜̈́p̵͕̑̀ľ̵̥̓ȁ̷͔̩̇y̷̞͊̿ ̸͍̺̀͝w̶͙͈̑i̷̡͗̾t̸͎͒̐ḩ̸̳̓ ̴̮̺̇ȗ̴̢͈̉ş̷͖̔̒?̵̝̺́</span>
+</summary>
+
+<div style="margin-top: 25px;">
+<h1 style="color: #d44d4d; border-bottom: 2px solid #442222; padding-bottom: 8px; text-shadow: 0 2px 4px rgba(0,0,0,0.3);">Welcome to the Bigger Bodies Initiative</h1>
+
+<div style="text-align: center; margin: 25px 0;">
+<img src="AETEG6110A00KPFHTKMZVNG5C0.jpeg" alt="Catnap" style="max-height: 70vh; border: 2px solid #442222; box-shadow: 0 8px 30px rgba(0,0,0,0.4); transition: 0.3s filter;" onmouseover="this.style.filter='grayscale(80%)'" onmouseout="this.style.filter='none'">
+</div>
+
+<h2 style="color: #b33d3d; margin-top: 0; text-transform: uppercase; letter-spacing: 2px;">Experiment 8B</h2>
+
+<div class="content-block">
+<h3 style="color: #d44d4d; margin-top: 0;">Usecases</h3>
+<p>
+This model was designed for exceptional skill in roleplaying, both with adults and children, for our patent pending Playtime Playground. It seems to have succeeded.
+</p>
+
+<h3 style="color: #d44d4d;">Supported Languages</h3>
+<ul style="list-style-type: '▸ '; padding-left: 25px;">
+<li style="padding: 5px 0;">Native-quality English</li>
+<li style="padding: 5px 0;">Mediocre Chinese (further research needed)</li>
+</ul>
+</div>
+
+<div class="content-block">
+<h3 style="color: #d44d4d; margin-top: 0;">Usage (chat template)</h3>
+<pre style="background: #000; color: #f8f8f8; padding: 15px; border-radius: 4px; border: 1px solid #333; overflow-x: auto; white-space: pre-wrap; word-break: break-word;">
+&lt;s&gt;[SYSTEM_PROMPT]What to roleplay as[/SYSTEM_PROMPT][INST]User: xxx[/INST]ASSISTANT: yyy&lt;/s&gt;</pre>
+</div>
+
+<!-- Testing logs would go here if we had any -->
+
+<div class="warning-box">
+<h4 style="color: #ff4d4d; margin: 0 0 10px 0;">⚠️ WARNING</h4>
+<p style="margin: 0;">While Experiment 8B has shown exceptional performance, researchers must maintain safety protocols. Standard containment procedures apply.</p>
+</div>
+</div>
+</details>
+
+<details style="margin-top: 20px;">
+<summary style="font-weight: 600; color: #888; cursor: pointer;">Disclaimers</summary>
+<div style="background: #1a1a1a; padding: 15px; margin-top: 10px; border-radius: 4px; border: 1px solid #333;">
+Playtime Co., Poppy Playtime, Catnap, and all related properties are trademarks of Mob Entertainment LLC. Not affiliated with or endorsed by Mob Entertainment.
+</div>
+</details>
+
+<div style="display: flex; justify-content: center;">
+<a href="https://huggingface.co/allura-org/Bigger-Body-12b/blob/main/non-lore-README.md" style="font-weight: 600; color: #888; background: #1a1a1a; padding: 15px; margin-top: 10px; border-radius: 4px; border: 1px solid #333; text-decoration: none; text-align: center;">Go to regular model card</a>
+</div>
+
+</div>
+</main>

non-lore-README-cn.md

@@ -0,0 +1,50 @@
+[English](./non-lore-README.md) | [简体中文](./non-lore-README-cn.md)
+
+# Bigger Body 12b
+![image/png](AETEG6110A00KPFHTKMZVNG5C0.jpeg)
+基于Ministral Instruct 2410的角色扮演导向伪全微调模型  
+Ink系列的精神续作
+
+## 数据集
+Bigger Body（内部仍称为Ink v2.1）的数据混合配方堪称"黑暗料理"，比初代Ink混合配方更令人发指。
+
+<details>
+<summary>（公开）原始数据集</summary>
+
+<ul>
+    <li><a href="https://huggingface.co/datasets/Fizzarolli/limarp-processed">Fizzarolli/limarp-processed</a></li>
+    <li><a href="https://huggingface.co/datasets/Norquinal/OpenCAI">Norquinal/OpenCAI</a> - <code>two_users</code> 拆分集</li>
+    <li><a href="https://huggingface.co/datasets/allura-org/Celeste1.x-data-mixture">allura-org/Celeste1.x-data-mixture</a></li>
+    <li><a href="https://huggingface.co/datasets/mapsila/PIPPA-ShareGPT-formatted-named">mapsila/PIPPA-ShareGPT-formatted-named</a></li>
+    <li><a href="https://huggingface.co/datasets/allenai/tulu-3-sft-personas-instruction-following">allenai/tulu-3-sft-personas-instruction-following</a></li>
+    <li><a href="https://huggingface.co/datasets/readmehay/medical-01-reasoning-SFT-json">readmehay/medical-01-reasoning-SFT-json</a></li>
+    <li><a href="https://huggingface.co/datasets/LooksJuicy/ruozhiba">LooksJuicy/ruozhiba</a></li>
+    <li><a href="https://huggingface.co/datasets/shibing624/roleplay-zh-sharegpt-gpt4-data">shibing624/roleplay-zh-sharegpt-gpt4-data</a></li>
+    <li><a href="https://huggingface.co/datasets/CausalLM/Retrieval-SFT-Chat">CausalLM/Retrieval-SFT-Chat</a></li>
+    <li><a href="https://huggingface.co/datasets/ToastyPigeon/fujin-filtered-instruct">ToastyPigeon/fujin-filtered-instruct</a></li>
+</ul>
+</details>
+
+## 量化版本
+待补充！
+
+## 推荐配置
+对话模板：Mistral *v7-tekken*（注意不是v3-tekken！！主要区别是v7版有特定的`[SYSTEM_PROMPT]`和`[/SYSTEM_PROMPT]`标签）  
+推荐采样器（非绝对最优，请自行尝试）：
+- 我完全没头绪。请自行探索。
+
+## 超参数
+### 通用配置
+- 训练轮次 = 2
+- 学习率 = 2e-6
+- 学习率调度器 = 余弦退火
+- 优化器 = [Apollo-mini](https://github.com/zhuhanqing/APOLLO)
+- 优化目标模块 = `all_linear`
+- 有效批次大小 = 16
+- 权重衰减 = 0.01
+- 预热步数 = 50
+- 总训练步数 = 920
+
+## 致谢
+衷心感谢所有数据集创建者的贡献  
+特别鸣谢Allura成员们的测试支持与精神鼓励 爱你们 /柏拉图式

non-lore-README.md

@@ -0,0 +1,50 @@
+[English](./non-lore-README.md) | [简体中文](./non-lore-README-cn.md)
+
+# Bigger Body 12b
+![image/png](AETEG6110A00KPFHTKMZVNG5C0.jpeg)
+A roleplay-focused pseudo full-finetune of Ministral Instruct 2410.
+The successor to the Ink series.
+
+## Dataset
+The Bigger Body (referred to as Ink v2.1, because that's still the internal name) mix is absolutely disgusting. It's even more cursed than the original Ink mix.
+
+<details>
+<summary>(Public) Original Datasets</summary>
+
+<ul>
+    <li><a href="https://huggingface.co/datasets/Fizzarolli/limarp-processed">Fizzarolli/limarp-processed</a></li>
+    <li><a href="https://huggingface.co/datasets/Norquinal/OpenCAI">Norquinal/OpenCAI</a> - <code>two_users</code> split</li>
+    <li><a href="https://huggingface.co/datasets/allura-org/Celeste1.x-data-mixture">allura-org/Celeste1.x-data-mixture</a></li>
+    <li><a href="https://huggingface.co/datasets/mapsila/PIPPA-ShareGPT-formatted-named">mapsila/PIPPA-ShareGPT-formatted-named</a></li>
+    <li><a href="https://huggingface.co/datasets/allenai/tulu-3-sft-personas-instruction-following">allenai/tulu-3-sft-personas-instruction-following</a></li>
+    <li><a href="https://huggingface.co/datasets/readmehay/medical-01-reasoning-SFT-json">readmehay/medical-01-reasoning-SFT-json</a></li>
+    <li><a href="https://huggingface.co/datasets/LooksJuicy/ruozhiba">LooksJuicy/ruozhiba</a></li>
+    <li><a href="https://huggingface.co/datasets/shibing624/roleplay-zh-sharegpt-gpt4-data">shibing624/roleplay-zh-sharegpt-gpt4-data</a></li>
+    <li><a href="https://huggingface.co/datasets/CausalLM/Retrieval-SFT-Chat">CausalLM/Retrieval-SFT-Chat</a></li>
+    <li><a href="https://huggingface.co/datasets/ToastyPigeon/fujin-filtered-instruct">ToastyPigeon/fujin-filtered-instruct</a></li>
+</ul>
+</details>
+
+## Quants
+TODO!
+
+## Recommended Settings
+Chat template: Mistral *v7-tekken* (NOT v3-tekken !!!! the main difference is that v7 has specific `[SYSTEM_PROMPT]` and `[/SYSTEM_PROMPT]` tags)  
+Recommended samplers (not the be-all-end-all, try some on your own!):
+- I have literally no idea. you're on your own.
+
+## Hyperparams
+### General
+- Epochs = 2
+- LR = 2e-6
+- LR Scheduler = Cosine
+- Optimizer = [Apollo-mini](https://github.com/zhuhanqing/APOLLO)
+- Optimizer target modules = `all_linear`
+- Effective batch size = 16
+- Weight Decay = 0.01
+- Warmup steps = 50
+- Total steps = 920
+
+## Credits
+Humongous thanks to the people who created the data.  
+Big thanks to all Allura members for testing and emotional support ilya /platonic