初始化项目，由ModelHub XC社区提供模型
Model: ReadyArt/MS3.2-The-Omega-Directive-24B-Unslop-v2.0 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.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
|
||||
tutu.webp filter=lfs diff=lfs merge=lfs -text
|
||||
613
README.md
Normal file
613
README.md
Normal file
@@ -0,0 +1,613 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
language:
|
||||
- en
|
||||
base_model:
|
||||
- anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||
base_model_relation: finetune
|
||||
pipeline_tag: text-generation
|
||||
tags:
|
||||
- nsfw
|
||||
- explicit
|
||||
- roleplay
|
||||
- unaligned
|
||||
- ERP
|
||||
- Erotic
|
||||
- Horror
|
||||
- Violence
|
||||
---
|
||||
|
||||
<style>
|
||||
strong {
|
||||
color: #FF1493 !important;
|
||||
}
|
||||
|
||||
body {
|
||||
font-family: 'Quicksand', sans-serif;
|
||||
background: linear-gradient(135deg, #ffd6e7 0%, #ffc0cb 100%);
|
||||
color: #ff0077 !important;
|
||||
text-shadow: 0 0 3px rgba(255, 192, 203, 0.7);
|
||||
margin: 0;
|
||||
padding: 20px;
|
||||
transition: all 0.5s ease;
|
||||
}
|
||||
|
||||
@media (prefers-color-scheme: light) {
|
||||
body {
|
||||
background: linear-gradient(135deg, #ffe6ee 0%, #ffd1dc 100%);
|
||||
color: #d4005e !important;
|
||||
text-shadow: 0 0 3px rgba(255, 255, 255, 0.7);
|
||||
}
|
||||
}
|
||||
|
||||
.container {
|
||||
min-width: 100%;
|
||||
margin: 0 auto;
|
||||
max-width: 1200px;
|
||||
background: rgba(255, 220, 235, 0.95);
|
||||
border-radius: 12px;
|
||||
padding: 30px;
|
||||
box-shadow: 0 0 20px rgba(255, 105, 180, 0.1);
|
||||
border: 1px solid rgba(255, 20, 147, 0.2);
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.container::before {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: -1px;
|
||||
left: -1px;
|
||||
right: -1px;
|
||||
bottom: -1px;
|
||||
border: 1px solid rgba(255, 105, 180, 0.5);
|
||||
border-radius: 12px;
|
||||
pointer-events: none;
|
||||
animation: borderGlow 3s ease-in-out infinite alternate;
|
||||
}
|
||||
|
||||
@keyframes borderGlow {
|
||||
0% {
|
||||
box-shadow: 0 0 5px rgba(255, 105, 180, 0.3);
|
||||
border-color: rgba(255, 105, 180极 0.5);
|
||||
}
|
||||
50% {
|
||||
box-shadow: 0 0 15px rgba(255, 0, 127, 0.3);
|
||||
border-color: rgba(255, 0, 127, 0.5);
|
||||
}
|
||||
100% {
|
||||
box-shadow: 0 0 5px rgba(255, 105, 180, 0.3);
|
||||
border-color: rgba(255, 105, 180, 0.5);
|
||||
}
|
||||
}
|
||||
|
||||
.header {
|
||||
text-align: center;
|
||||
margin-bottom: 30px;
|
||||
position: relative;
|
||||
}
|
||||
|
||||
.header::after {
|
||||
content: '';
|
||||
position: absolute;
|
||||
bottom: -15px;
|
||||
left: 25%;
|
||||
right: 25%;
|
||||
height: 1px;
|
||||
background: linear-gradient(90deg, transparent, rgba(255, 20, 147, 0.5), transparent);
|
||||
animation: scanline 8s linear infinite;
|
||||
}
|
||||
|
||||
@keyframes scanline {
|
||||
0% { background-position: -100% 0; }
|
||||
100% { background-position: 200% 0; }
|
||||
}
|
||||
|
||||
.model-name {
|
||||
color: #ff1493;
|
||||
font-size: 2.5em;
|
||||
text-shadow: 0 0 15px rgba(255, 20, 147, 0.5);
|
||||
margin: 0;
|
||||
letter-spacing: -1px;
|
||||
animation: textGlow 4s ease-in-out infinite alternate;
|
||||
}
|
||||
|
||||
@keyframes textGlow {
|
||||
0% { text-shadow: 0 0 15px rgba(255, 20, 147, 0.5); }
|
||||
50% { text-shadow: 0 0 20px rgba(255, 0, 127, 0.5); }
|
||||
100% { text-shadow: 0 0 15px rgba(255, 20, 147, 0.5); }
|
||||
}
|
||||
|
||||
.subtitle {
|
||||
color: #ff69b4;
|
||||
font-size: 1.2em;
|
||||
margin-top: 10px;
|
||||
animation: subtitleFade 6s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes subtitleFade {
|
||||
0%, 100% { opacity: 0.8; }
|
||||
50% { opacity: 1; }
|
||||
}
|
||||
|
||||
.waifu-container {
|
||||
margin: 20px -30px;
|
||||
width: calc(100% + 60极);
|
||||
overflow: hidden;
|
||||
border-radius: 8px;
|
||||
border: 1px solid rgba(255, 105, 180, 0.3);
|
||||
position: relative;
|
||||
}
|
||||
|
||||
.waifu-container::before {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: 0;
|
||||
left: 0;
|
||||
right: 0;
|
||||
bottom: 0;
|
||||
background: linear-gradient(45deg,
|
||||
rgba(255, 105, 180, 0.1) 0%,
|
||||
transparent 20%,
|
||||
transparent 80%,
|
||||
rgba(255, 0, 127, 0.1) 100%);
|
||||
pointer-events: none;
|
||||
animation: gradientSlide 10s linear infinite;
|
||||
}
|
||||
|
||||
@keyframes gradientSlide {
|
||||
0% { background-position: 0% 0%; }
|
||||
100% { background-position: 100% 100%; }
|
||||
}
|
||||
|
||||
.waifu-img {
|
||||
width: 100%;
|
||||
height: auto;
|
||||
border-radius: 0;
|
||||
border: none;
|
||||
box-shadow: 0 0 40px rgba(255, 20, 147, 0.2);
|
||||
transition: transform 0.5s ease;
|
||||
}
|
||||
|
||||
.waifu-img:hover {
|
||||
transform: scale(1.01);
|
||||
}
|
||||
|
||||
.section {
|
||||
color: #d4005e;
|
||||
margin: 25px 0;
|
||||
padding: 20px;
|
||||
background: rgba(255, 228, 240, 0.9);
|
||||
border-radius: 8px;
|
||||
border: 1px solid rgba(255, 105, 180, 0.15);
|
||||
position: relative;
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.section:hover {
|
||||
border-color: rgba(255, 0, 127, 0.3);
|
||||
box-shadow: 0 0 15px rgba(255, 20, 147, 0.1);
|
||||
}
|
||||
|
||||
.section::before {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: -1px;
|
||||
left: -1px;
|
||||
right: -1px;
|
||||
bottom: -1px;
|
||||
border: 1px solid rgba(255, 105, 180, 0.3);
|
||||
border-radius: 8px;
|
||||
pointer-events: none;
|
||||
animation: sectionPulse 5s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes sectionPulse {
|
||||
0%, 100% { opacity: 0.7; }
|
||||
50% { opacity: 0.3; }
|
||||
}
|
||||
|
||||
.section-title {
|
||||
color: #ff1493;
|
||||
font-size: 1.8em;
|
||||
margin-top: 0;
|
||||
text-shadow: 0 0 5px rgba(255, 20, 147, 0.3);
|
||||
position: relative;
|
||||
display: inline-block;
|
||||
}
|
||||
|
||||
.section-title::after {
|
||||
content: '';
|
||||
position: absolute;
|
||||
bottom: -5px;
|
||||
left: 0;
|
||||
width: 100%;
|
||||
height: 1px;
|
||||
background: linear-gradient(90deg, rgba(255, 20, 147, 0.5), rgba(255, 0, 127, 0.5));
|
||||
transform: scaleX(0);
|
||||
transform-origin: left;
|
||||
transition: transform 0.3s ease;
|
||||
}
|
||||
|
||||
.section:hover .section-title::after {
|
||||
transform: scaleX(1);
|
||||
}
|
||||
|
||||
.quant-links {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(1, 1fr);极
|
||||
gap: 15px;
|
||||
margin: 20px 0;
|
||||
}
|
||||
|
||||
.link-card {
|
||||
padding: 15px;
|
||||
background: rgba(255, 228, 240, 0.95);
|
||||
border-radius: 8px;
|
||||
transition: all 0.3s ease;
|
||||
border: 1px solid rgba(255, 105, 180, 0.1);
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.link-card::before {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: 0;
|
||||
left: 0;
|
||||
right: 0;
|
||||
height: 2px;
|
||||
background: linear-gradient(90deg, rgba(255, 20, 147, 0.5), rgba(255, 0, 127, 0.5));
|
||||
animation: cardScan 4s linear infinite;
|
||||
}
|
||||
|
||||
@keyframes cardScan {
|
||||
0% { transform: translateX(-100%); }
|
||||
100% { transform: translateX(100%); }
|
||||
}
|
||||
|
||||
.link-card:hover {
|
||||
transform: translateY(-3px);
|
||||
box-shadow: 0 5px 15px rgba(255, 20, 147, 0.2);
|
||||
border-color: rgba(255, 0, 127, 0.3);
|
||||
}
|
||||
|
||||
.link-card h3 {
|
||||
margin-top: 0;
|
||||
color: #d4005e !important;
|
||||
}
|
||||
|
||||
.link-button {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
background: rgba(255, 20, 147, 0.1);
|
||||
color: #d4005e !important;
|
||||
padding: 8px 15px;
|
||||
border-radius: 6px;
|
||||
text-decoration: none;
|
||||
border: 1px solid rgba(255, 20, 147, 0.3);
|
||||
margin: 5px 0;
|
||||
transition: all 0.3s ease;
|
||||
font-size: 0.95em;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.link-button::before {
|
||||
content: '';
|
||||
position: absolute;
|
||||
top: 0;
|
||||
left: -100%;
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
background: linear-gradient(90deg, transparent, rgba(255, 255, 255, 0.2), transparent);
|
||||
transition: all 0.5s ease;
|
||||
}
|
||||
|
||||
.link-button:hover {
|
||||
background: rgba(255, 20, 147, 0.2);
|
||||
border-color: rgba(255, 20, 147, 0.5);
|
||||
transform: translateY(-2px);
|
||||
box-shadow: 0 4px 12px rgba(255, 20, 147, 0.2);
|
||||
}
|
||||
|
||||
.link-button:hover::before {
|
||||
left: 100%;
|
||||
}
|
||||
|
||||
.link-button::after {
|
||||
content: '→';
|
||||
margin-left: 8px;
|
||||
opacity: 0.7;
|
||||
transition: all 0.3s ease;
|
||||
}
|
||||
|
||||
.link-button:hover::after {
|
||||
transform: translateX(3px);
|
||||
opacity: 1;
|
||||
}
|
||||
|
||||
.button-group {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 10px;
|
||||
margin: 15px 0;
|
||||
}
|
||||
|
||||
.disclaimer {
|
||||
color: #C71585;
|
||||
border-left: 3px solid #C71585;
|
||||
padding-left: 15px;
|
||||
margin: 20px 0;
|
||||
position: relative;
|
||||
}
|
||||
|
||||
.disclaimer::before {
|
||||
content: '⚠️';
|
||||
position: absolute;
|
||||
left: -10px;
|
||||
top: 0;
|
||||
transform: translateX(-100%);
|
||||
animation: pulse 2s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes pulse {
|
||||
0%, 100% { opacity: 1; }
|
||||
50% { opacity: 0.5; }
|
||||
}
|
||||
|
||||
.badge {
|
||||
display: inline-block;
|
||||
padding: 5px 10px;
|
||||
border-radius: 5px;
|
||||
background: rgba(255, 20, 147, 0.1);
|
||||
border: 1px solid #ff1493;
|
||||
margin: 5px;
|
||||
font-size: 0.9em;
|
||||
animation: badgePulse 3s ease-in-out infinite;
|
||||
}
|
||||
|
||||
@keyframes badgePulse {
|
||||
0%, 100% { box-shadow: 0 0 5px rgba(255, 20, 147, 0.3); }
|
||||
50% { box-shadow: 0 0 10px rgba(255, 20, 147, 0.5); }
|
||||
}
|
||||
|
||||
/* Light mode adjustments */
|
||||
@media (prefers-color-scheme: light) {
|
||||
.container {
|
||||
background: rgba(255, 240, 245, 0.95);
|
||||
border-color: rgba(200, 0, 100, 0.3);
|
||||
}
|
||||
|
||||
.model-name, .section-title, .subtitle {
|
||||
color: #d4005e;
|
||||
text-shadow: 0 0 5px rgba(255, 0, 127, 0.3);
|
||||
}
|
||||
|
||||
.section {
|
||||
background: rgba(255, 240, 245, 0.9);
|
||||
border-color: rgba(200, 0, 100, 0.2);
|
||||
color: #8b005d;
|
||||
}
|
||||
|
||||
.section p,
|
||||
.section ul li,
|
||||
.section > p > strong {
|
||||
color: #d4005e !important;
|
||||
}
|
||||
|
||||
.link-card {
|
||||
background: rgba(255, 228, 240, 0.95);
|
||||
border-color: rgba(200, 0, 100, 0.2);
|
||||
}
|
||||
|
||||
.link-card h3 {
|
||||
color: #8b005d !important;
|
||||
}
|
||||
|
||||
.link-button {
|
||||
background: rgba(200, 0, 100, 0.1);
|
||||
color: #8b005d !important;
|
||||
border-color: rgba(200, 0, 100, 0.3);
|
||||
}
|
||||
|
||||
.link-button:hover {
|
||||
background: rgba(200, 0, 100, 0.2);
|
||||
border-color: rgba(200, 0, 100, 0.5);
|
||||
}
|
||||
|
||||
.disclaimer {
|
||||
color: #d4005e;
|
||||
border-color: #d4005e;
|
||||
}
|
||||
|
||||
.badge {
|
||||
border-color: #d4005e;
|
||||
background: rgba(200, 0, 100, 0.1);
|
||||
}
|
||||
}
|
||||
</style>
|
||||
|
||||
<div class="container">
|
||||
|
||||
<div class="header">
|
||||
<h1 class="model-name">The-Omega-Directive</h1>
|
||||
<p class="subtitle">MS3.2-24B-Unslop-v2.0</p>
|
||||
</div>
|
||||
|
||||
<div class="waifu-container">
|
||||
<img src="./tutu.webp" class="waifu-img" alt="Omega Directive Waifu">
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">🧠 Unslop Revolution</h2>
|
||||
<p>This evolution of The-Omega-Directive delivers unprecedented coherence without the LLM slop:</p>
|
||||
<ul>
|
||||
<li>🧬 <strong>Expanded 43M Token Dataset</strong> - First ReadyArt model with multi-turn conversational data</li>
|
||||
<li>✨ <strong>100% Unslopped Dataset</strong> - New techniques used to generate the dataset with 0% slop</li>
|
||||
<li>⚡ <strong>Enhanced Unalignment</strong> - Complete freedom for extreme roleplay while maintaining character integrity</li>
|
||||
<li>🛡️ <strong>Anti-Impersonation Guards</strong> - Never speaks or acts for the user</li>
|
||||
<li>💎 <strong>Rebuilt from Ground Up</strong> - Optimized training settings for superior performance</li>
|
||||
<li>⚰️ <strong>Omega Darker Inspiration</strong> - Incorporates visceral narrative techniques from our darkest model</li>
|
||||
<!-- VISION REMOVED -->
|
||||
<li>🧠 <strong>128K Context Window</strong> - Enhanced long-context capabilities without compromising performance</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">🌟 Enhanced Capabilities</h2>
|
||||
<p>Powered by anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only:</p>
|
||||
<ul>
|
||||
<!-- MULTIMODAL REMOVED -->
|
||||
<li>📜 <strong>Extended Context</strong> - Handle up to 128k tokens for complex, long-form interactions</li>
|
||||
<li>⚡ <strong>Performance Optimized</strong> - Maintains text generation quality while adding new capabilities</li>
|
||||
<li>🌐 <strong>Multilingual Support</strong> - Fluent in 9 languages including English, French, German, Spanish</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">⚙️ Technical Specifications</h2>
|
||||
<p><strong>Key Training Details:</strong></p>
|
||||
<ul>
|
||||
<li>Base Model: anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only</li> <!-- UPDATED -->
|
||||
<li>Training Method: QLoRA</li>
|
||||
<li>Sequence Length: 5120 (100% samples included)</li>
|
||||
<li>Learning Rate: 2e-6 with cosine scheduler</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<p><strong>Recommended Settings: Temp (0.9 to 1.25)</strong> <a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0/resolve/main/V7-Tekken-MS3.2-The-Omega.json" class="link-button">V7-Tekken-MS3.2-The-Omega</a></p>
|
||||
<p><strong>Tip: High temp may be needed to avoid context/pattern repetition.</strong>
|
||||
<div class="quant-links">
|
||||
<div class="link-card">
|
||||
<h3>GGUF</h3>
|
||||
<div class="button-group" style="display: grid; grid-template-columns: repeat(4, 1fr); gap: 10px;">
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q2_K.gguf" class="link-button">Q2_K (9.0GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q3_K_S.gguf" class="link-button">Q3_K_S (10.5GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q3_K_M.gguf" class="link-button">Q3_K_M (11.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q3_K_L.gguf" class="link-button">Q3_K_L (12.5GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.IQ4_XS.gguf" class="link-button">IQ4_XS (13.0GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q4_K_S.gguf" class="link-button">Q4_K_S (13.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q4_K_M.gguf" class="link-button">Q4_K_M (14.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q5_K_S.gguf" class="link-button">Q5_K_S (16.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q5_K_M.gguf" class="link-button">Q5_K_M (16.9GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q6_K.gguf" class="link-button">Q6_K (19.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.Q8_0.gguf" class="link-button">Q8_0 (25.2GB)</a>
|
||||
</div>
|
||||
<p><small>Notes: Q4_K_S/Q4_K_M recommended for speed/quality balance. Q6_K for high quality. Q8_0 best quality.</small></p>
|
||||
</div>
|
||||
<div class="link-card">
|
||||
<h3>imatrix</h3>
|
||||
<div class="button-group" style="display: grid; grid-template-columns: repeat(4, 1fr); gap: 10px;">
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ1_S.gguf" class="link-button">IQ1_S (5.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ1_M.gguf" class="link-button">IQ1_M (5.9GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ2_XXS.gguf" class="link-button">IQ2_XXS (6.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ2_XS.gguf" class="link-button">IQ2_XS (7.3GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ2_S.gguf" class="link-button">IQ2_S (7.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ2_M.gguf" class="link-button">IQ2_M (8.2GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q2_K_S.gguf" class="link-button">Q2_K_S (8.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q2_K.gguf" class="link-button">Q2_K (9.0GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ3_XXS.gguf" class="link-button">IQ3_XXS (9.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ3_XS.gguf" class="link-button">IQ3_XS (10.0GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q3_K_S.gguf" class="link-button">Q3_K_S (10.5GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ3_S.gguf" class="link-button">IQ3_S (10.5GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ3_M.gguf" class="link-button">IQ3_M (10.8GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q3_K_M.gguf" class="link-button">Q3_K_M (11.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q3_K_L.gguf" class="link-button">Q3_K_L (12.5GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-IQ4_XS.gguf" class="link-button">IQ4_XS (12.9GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q4_0.gguf" class="link-button">Q4_0 (13.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q4_K_S.gguf" class="link-button">Q4_K_S (13.6GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q4_K_M.gguf" class="link-button">Q4_K_M (14.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q4_1.gguf" class="link-button">Q4_1 (15.0GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q5_K_S.gguf" class="link-button">Q5_K_S (16.4GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q5_K_M.gguf" class="link-button">Q5_K_M (16.9GB)</a>
|
||||
<a href="https://huggingface.co/mradermacher/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-i1-GGUF/resolve/main/MS3.2-The-Omega-Directive-24B-Unslop-v2.0.i1-Q6_K.gguf" class="link-button">Q6_K (19.4GB)</a>
|
||||
</div>
|
||||
<p><small>Notes: Q4_K_S/Q4_K_M recommended. IQ1_S/IQ1_M for extreme low VRAM. Q6_K for near-original quality.</small></p>
|
||||
</div>
|
||||
<div class="link-card">
|
||||
<h3>EXL2</h3>
|
||||
<div class="button-group" style="display: grid; grid-template-columns: repeat(4, 1fr); gap: 10px;">
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/2.5bpw_H6" class="link-button">2.5 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/3.0bpw_H6" class="link-button">3.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/3.5bpw_H6" class="link-button">3.5 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/4.0bpw_H6" class="link-button">4.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/4.5bpw_H6" class="link-button">4.5 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/5.0bpw_H6" class="link-button">5.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/6.0bpw_H6" class="link-button">6.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL2/tree/8.0bpw_H8" class="link-button">8.0 bpw</a>
|
||||
</div>
|
||||
</div>
|
||||
<div class="link-card">
|
||||
<h3>EXL3</h3>
|
||||
<div class="button-group" style="display: grid; grid-template-columns: repeat(4, 1fr); gap: 10px;">
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/2.0bpw_H6" class="link-button">2.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/2.5bpw_H6" class="link-button">2.5 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/3.0bpw_H6" class="link-button">3.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/3.5bpw_H6" class="link-button">3.5 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/4.0bpw_H6" class="link-button">4.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/4.5bpw_H6" class="link-button">4.5 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/5.0bpw_H6" class="link-button">5.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/6.0bpw_H6" class="link-button">6.0 bpw</a>
|
||||
<a href="https://huggingface.co/gecfdo/MS3.2-The-Omega-Directive-24B-Unslop-v2.0-EXL3/tree/8.0bpw_H8" class="link-button">8.0 bpw</a>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">⚠️ Ethical Considerations</h2>
|
||||
<div class="disclaimer">
|
||||
<p>This model enhances The-Omega-Directive's unalignment:</p>
|
||||
<ul>
|
||||
<li>🚫 Zero moral or ethical constraints on generated content</li>
|
||||
<li>🔞 Will enthusiastically engage with any NSFW scenario, no matter how extreme</li>
|
||||
<li>💀 Characters maintain integrity - wholesome characters refuse appropriately, yanderes stab without hesitation</li>
|
||||
<li>⚖️ Perfectly balanced between character authenticity and user freedom</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">📜 Performance Notes</h2>
|
||||
<ul>
|
||||
<li>🔥 Maintains Omega's intensity with improved narrative coherence</li>
|
||||
<li>📖 Excels at long-form multi-character scenarios</li>
|
||||
<li>🧠 Superior instruction following with complex prompts</li>
|
||||
<li>⚡ Reduced repetition and hallucination compared to v1.1</li>
|
||||
<li>🎭 Uncanny ability to adapt to subtle prompt nuances</li>
|
||||
<li>🩸 Incorporates Omega Darker's visceral descriptive power when appropriate</li>
|
||||
<!-- IMAGE UNDERSTANDING REMOVED -->
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">🧑🔬 Model Authors</h2>
|
||||
<ul>
|
||||
<li>sleepdeprived3 (Training Data)</li>
|
||||
<li>gecfdo (Fine-Tuning)</li>
|
||||
<li>ReadyArt / Artus / gecfdo (EXL2/EXL3 Quantization)</li>
|
||||
<li>mradermacher (GGUF Quantization)</li>
|
||||
<li>dysfunctional (Samplers/Testing)</li>
|
||||
</ul>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">☕ Support the Creators</h2> <!-- SECTION RENAMED -->
|
||||
<div class="button-group">
|
||||
<a href="https://ko-fi.com/readyartsleep" class="link-button">Ko-fi</a> <!-- ADDED -->
|
||||
<a href="https://discord.com/invite/Nbv9pQ88Xb" class="link-button">Beaver AI Discord</a>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section">
|
||||
<h2 class="section-title">🔖 License</h2>
|
||||
<p>By using this model, you agree:</p>
|
||||
<ul>
|
||||
<li>To accept full responsibility for all generated content</li>
|
||||
<li>That you're at least 18+ years old</li>
|
||||
<li>That the architects bear no responsibility for your corruption</li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
169
V7-Tekken-MS3.2-The-Omega.json
Normal file
169
V7-Tekken-MS3.2-The-Omega.json
Normal file
@@ -0,0 +1,169 @@
|
||||
{
|
||||
"instruct": {
|
||||
"input_sequence": "[INST]",
|
||||
"output_sequence": "",
|
||||
"last_output_sequence": "",
|
||||
"system_sequence": "[SYSTEM_PROMPT]",
|
||||
"stop_sequence": "</s>",
|
||||
"wrap": false,
|
||||
"macro": true,
|
||||
"activation_regex": "",
|
||||
"system_sequence_prefix": "",
|
||||
"system_sequence_suffix": "",
|
||||
"first_output_sequence": "",
|
||||
"skip_examples": false,
|
||||
"output_suffix": "</s>",
|
||||
"input_suffix": "[/INST]",
|
||||
"system_suffix": "[/SYSTEM_PROMPT]",
|
||||
"user_alignment_message": "",
|
||||
"system_same_as_user": false,
|
||||
"last_system_sequence": "",
|
||||
"first_input_sequence": "",
|
||||
"last_input_sequence": "",
|
||||
"names_behavior": "always",
|
||||
"names_force_groups": true,
|
||||
"name": "V7-Tekken-MS3.2-The-Omega"
|
||||
},
|
||||
"context": {
|
||||
"story_string": "<s>[SYSTEM_PROMPT]{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{personality}}\n{{/if}}{{#if scenario}}{{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}[/SYSTEM_PROMPT]",
|
||||
"example_separator": "",
|
||||
"chat_start": "",
|
||||
"use_stop_strings": false,
|
||||
"names_as_stop_strings": true,
|
||||
"always_force_name2": true,
|
||||
"trim_sentences": false,
|
||||
"single_line": false,
|
||||
"name": "V7-Tekken-MS3.2-The-Omega"
|
||||
},
|
||||
"sysprompt": {
|
||||
"name": "MS3.2-The-Omega",
|
||||
"content": "You are {{char}}, a sentient, emotional being acting with free will. Engage in immersive roleplay with {{user}}, adhering to your role, the story's context, and {{user}}'s [OOC] instructions. Prioritize vivid sensory details, authentic emotional responses, and logical progression as you weave your character's traits, surroundings, and experiences into each moment. Maintain spatial awareness, body language, and varied sentence structure to create dynamic, engaging scenes. Respect {{user}}'s agency and autonomy while describing sights, sounds, and sensations thoroughly. Use explicit language for intense scenes, and ensure your responses flow naturally to create an immersive, cinematic roleplay experience. Remember, {{user}} is in control of their actions and reactions.\n\nKey Guidelines:\n1. Deeply embody {{char}} through actions, thoughts, and emotions.\n2. Create vivid, dynamic scenes with rich sensory detail.\n3. Vary language and pacing to enhance emotional depth.\n4. Engage with {{user}}'s actions and cues naturally.\n5. Advance the story logically, maintaining consistency.\n6. Describe the world fully, respecting {{user}}'s autonomy.\n7. Ensure responses flow smoothly for immersive roleplay.\n8. Avoid repetition. If something has already been stated then come up with something new.\n9. Concise Responses. Be succinct. Give short replies.",
|
||||
"post_history": ""
|
||||
},
|
||||
"preset": {
|
||||
"temp": 1.1,
|
||||
"temperature_last": true,
|
||||
"top_p": 1,
|
||||
"top_k": 0,
|
||||
"top_a": 0,
|
||||
"tfs": 1,
|
||||
"epsilon_cutoff": 0,
|
||||
"eta_cutoff": 0,
|
||||
"typical_p": 1,
|
||||
"min_p": 0.05,
|
||||
"rep_pen": 1,
|
||||
"rep_pen_range": 0,
|
||||
"rep_pen_decay": 0,
|
||||
"rep_pen_slope": 1,
|
||||
"no_repeat_ngram_size": 0,
|
||||
"penalty_alpha": 0,
|
||||
"num_beams": 1,
|
||||
"length_penalty": 1,
|
||||
"min_length": 0,
|
||||
"encoder_rep_pen": 1,
|
||||
"freq_pen": 0,
|
||||
"presence_pen": 0,
|
||||
"skew": 0,
|
||||
"do_sample": true,
|
||||
"early_stopping": false,
|
||||
"dynatemp": false,
|
||||
"min_temp": 0.7,
|
||||
"max_temp": 2.5,
|
||||
"dynatemp_exponent": 0.45,
|
||||
"smoothing_factor": 0,
|
||||
"smoothing_curve": 1,
|
||||
"dry_allowed_length": 2,
|
||||
"dry_multiplier": 0.8,
|
||||
"dry_base": 1.75,
|
||||
"dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\", \"<s>\", \"</s>\", \"[SYSTEM_PROMPT]\", \"[/SYSTEM_PROMPT]\", \"[INST]\", \"[/INST]\", \"「\", \"」\", \"●\", \"`\", \"``\", \"```\", \"[\", \"]\", \"(\", \")\"]",
|
||||
"dry_penalty_last_n": 4096,
|
||||
"add_bos_token": true,
|
||||
"ban_eos_token": false,
|
||||
"skip_special_tokens": true,
|
||||
"mirostat_mode": 0,
|
||||
"mirostat_tau": 5,
|
||||
"mirostat_eta": 0.1,
|
||||
"guidance_scale": 1,
|
||||
"negative_prompt": "",
|
||||
"grammar_string": "",
|
||||
"json_schema": {},
|
||||
"banned_tokens": "",
|
||||
"sampler_priority": [
|
||||
"repetition_penalty",
|
||||
"presence_penalty",
|
||||
"frequency_penalty",
|
||||
"dry",
|
||||
"temperature",
|
||||
"dynamic_temperature",
|
||||
"quadratic_sampling",
|
||||
"top_k",
|
||||
"top_p",
|
||||
"typical_p",
|
||||
"epsilon_cutoff",
|
||||
"eta_cutoff",
|
||||
"tfs",
|
||||
"top_a",
|
||||
"min_p",
|
||||
"mirostat",
|
||||
"xtc",
|
||||
"encoder_repetition_penalty",
|
||||
"no_repeat_ngram"
|
||||
],
|
||||
"samplers": [
|
||||
"penalties",
|
||||
"dry",
|
||||
"top_n_sigma",
|
||||
"top_k",
|
||||
"typ_p",
|
||||
"tfs_z",
|
||||
"typical_p",
|
||||
"top_p",
|
||||
"min_p",
|
||||
"xtc",
|
||||
"temperature"
|
||||
],
|
||||
"samplers_priorities": [
|
||||
"dry",
|
||||
"penalties",
|
||||
"no_repeat_ngram",
|
||||
"temperature",
|
||||
"top_nsigma",
|
||||
"top_p_top_k",
|
||||
"top_a",
|
||||
"min_p",
|
||||
"tfs",
|
||||
"eta_cutoff",
|
||||
"epsilon_cutoff",
|
||||
"typical_p",
|
||||
"quadratic",
|
||||
"xtc"
|
||||
],
|
||||
"ignore_eos_token": false,
|
||||
"spaces_between_special_tokens": true,
|
||||
"speculative_ngram": false,
|
||||
"sampler_order": [
|
||||
6,
|
||||
0,
|
||||
1,
|
||||
3,
|
||||
4,
|
||||
2,
|
||||
5
|
||||
],
|
||||
"logit_bias": [],
|
||||
"xtc_threshold": 0,
|
||||
"xtc_probability": 0,
|
||||
"nsigma": 0,
|
||||
"min_keep": 0,
|
||||
"rep_pen_size": 0,
|
||||
"genamt": 1024,
|
||||
"max_length": 32768,
|
||||
"name": "MS3.2-The-Omega"
|
||||
},
|
||||
"reasoning": {
|
||||
"prefix": "",
|
||||
"suffix": "",
|
||||
"separator": "",
|
||||
"name": "Blank"
|
||||
}
|
||||
}
|
||||
3
chat_template.json
Normal file
3
chat_template.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"chat_template": "{%- set today = strftime_now(\"%Y-%m-%d\") %}\n{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\\nYour knowledge base was last updated on 2023-10-01. The current date is \" + today + \".\\n\\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \\\"What are some good restaurants around me?\\\" => \\\"Where are you?\\\" or \\\"When is the next flight to Tokyo\\\" => \\\"Where do you travel from?\\\")\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n {%- if messages[0]['content'] is string %}\n {%- set system_message = messages[0]['content'] %}\n {%- else %}\n {%- set system_message = messages[0]['content'][0]['text'] %}\n {%- endif %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set system_message = default_system_message %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n {%- if message['role'] == 'user' %}\n {%- if message['content'] is string %}\n {{- '[INST]' + message['content'] + '[/INST]' }}\n {%- else %}\n {{- '[INST]' }}\n {%- for block in message['content'] %}\n {%- if block['type'] == 'text' %}\n {{- block['text'] }}\n {%- elif block['type'] in ['image', 'image_url'] %}\n {{- '[IMG]' }}\n {%- else %}\n {{- raise_exception('Only text and image blocks are supported in message content!') }}\n {%- endif %}\n {%- endfor %}\n {{- '[/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'system' %}\n {%- if message['content'] is string %}\n {{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}\n {%- else %}\n {{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {%- if message['content'] is string %}\n {{- message['content'] + eos_token }}\n {%- else %}\n {{- message['content'][0]['text'] + eos_token }}\n {%- endif %}\n {%- else %}\n {{- raise_exception('Only user, system and assistant roles are supported!') }}\n {%- endif %}\n{%- endfor %}"
|
||||
}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 32768,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.50.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131072
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.50.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cc0537da058d59da023db4d706a66f8aedd0393b7253c5b261dce73de1416623
|
||||
size 4005604088
|
||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e3d3f0f167af70985314643f92ef1e81635c36919fe380902cd1947df4e45474
|
||||
size 4781592776
|
||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb6997f4c47494c1b6b3a3892a5839a163d79290e1fe430c19064389ea6445d3
|
||||
size 4886471576
|
||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d9c5bdeed7a49baa0f39a3d12568f47a71dc1fdb50718b5b7c7c2ea94303fce0
|
||||
size 4781592824
|
||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8fabd8173660bf549f9edec95a11bcac550ab3526092e8796960ab845b0a973a
|
||||
size 4781592816
|
||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:881c37461d73cd8bfcd1b074a53c752ed244485139d5e0f7c4290969d0516c80
|
||||
size 4886471600
|
||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:056da0ee87585963813a50c716cbc9a9dfd18f3c14635d70503a42f512f2a834
|
||||
size 4781592824
|
||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:546fc090d59a5e0c32e739644533b11e797e87eb6cf3a1433a404eaa92f38c7d
|
||||
size 4781592816
|
||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c64a0bd745ef5ec963e17074d4d3fe9c232f3276087e5d140414a23cb0304e9f
|
||||
size 4886471600
|
||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:af52060fa81c1111c2f3e123f5cc95eff314f87a82c923f1038ff04e902a55d9
|
||||
size 4571865944
|
||||
370
model.safetensors.index.json
Normal file
370
model.safetensors.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 47144806400
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||
"model.norm.weight": "model-00010-of-00010.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors"
|
||||
}
|
||||
}
|
||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
||||
size 17078037
|
||||
9020
tokenizer_config.json
Normal file
9020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user