初始化项目，由ModelHub XC社区提供模型
Model: Vortex5/NoctyxCosma-12B Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal 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
|
||||
563
README.md
Normal file
563
README.md
Normal file
@@ -0,0 +1,563 @@
|
||||
---
|
||||
base_model:
|
||||
- Delta-Vector/Rei-V3-KTO-12B
|
||||
- Retreatcost/Chrysologus-12B
|
||||
- Vortex5/Harmony-Bird-12B
|
||||
- Vortex5/Red-Synthesis-12B
|
||||
- Vortex5/Lunar-Nexus-12B
|
||||
- Vortex5/Scarlet-Eclipse-12B
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- roleplay
|
||||
---
|
||||
<div class="noctyx-stage">
|
||||
<section class="model-card">
|
||||
|
||||
|
||||
<header class="card-header">
|
||||
<div class="title-block">
|
||||
<div class="title-frame" aria-hidden="true"></div>
|
||||
|
||||
<h1 class="model-title">NoctyxCosma-12B</h1>
|
||||
|
||||
|
||||
<div class="title-accents" aria-hidden="true">
|
||||
<span class="accent-bar"></span>
|
||||
<span class="accent-dot"></span>
|
||||
<span class="accent-bar"></span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="hero-wrap">
|
||||
<div class="hero-frame" aria-hidden="true"></div>
|
||||
<img
|
||||
src="https://cdn-uploads.huggingface.co/production/uploads/6669a3a617b838fda45637b8/mCzdjBlQiwnTgnpKaaNn8.png"
|
||||
</div>
|
||||
</header>
|
||||
|
||||
<div class="flow-divider" aria-hidden="true"></div>
|
||||
|
||||
|
||||
<section class="content-panel">
|
||||
<div class="panel-frame" aria-hidden="true"></div>
|
||||
<div class="panel-inner">
|
||||
<h2 class="panel-heading">Overview</h2>
|
||||
|
||||
<p>
|
||||
<strong>NoctyxCosma-12B</strong> was created by merging
|
||||
<a href="https://huggingface.co/Vortex5/Harmony-Bird-12B">Harmony-Bird-12B</a>,
|
||||
<a href="https://huggingface.co/Retreatcost/Chrysologus-12B">Chrysologus-12B</a>,
|
||||
<a href="https://huggingface.co/Delta-Vector/Rei-V3-KTO-12B">Rei-V3-KTO-12B</a>,
|
||||
<a href="https://huggingface.co/Vortex5/Scarlet-Eclipse-12B">Scarlet-Eclipse-12B</a>,
|
||||
<a href="https://huggingface.co/Vortex5/Lunar-Nexus-12B">Lunar-Nexus-12B</a>,
|
||||
and
|
||||
<a href="https://huggingface.co/Vortex5/Red-Synthesis-12B">Red-Synthesis-12B</a>
|
||||
using a custom merge method.
|
||||
</p>
|
||||
|
||||
<details class="yaml-toggle">
|
||||
<summary>Show merge configuration</summary>
|
||||
<pre>models:
|
||||
- model: Vortex5/Harmony-Bird-12B
|
||||
- model: Retreatcost/Chrysologus-12B
|
||||
- model: Delta-Vector/Rei-V3-KTO-12B
|
||||
- model: Vortex5/Scarlet-Eclipse-12B
|
||||
- model: Vortex5/Lunar-Nexus-12B
|
||||
- model: Vortex5/Red-Synthesis-12B
|
||||
merge_method: smi_oni
|
||||
parameters:
|
||||
k_core: 2
|
||||
strength_core: 1.0
|
||||
consensus_core: 0.48
|
||||
drop_cos: 0.10
|
||||
drop_min: 3
|
||||
strength_nov: 0.45
|
||||
novelty_budget: 0.22
|
||||
consensus_nov: 0.32
|
||||
conflict_bonus: 0.18
|
||||
dtype: bfloat16
|
||||
tokenizer:
|
||||
source: Vortex5/Red-Synthesis-12B
|
||||
</pre>
|
||||
</details>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<div class="flow-divider thin" aria-hidden="true"></div>
|
||||
|
||||
|
||||
<section class="content-panel">
|
||||
<div class="panel-frame" aria-hidden="true"></div>
|
||||
<div class="panel-inner">
|
||||
<h2 class="panel-heading">Intended Use</h2>
|
||||
|
||||
<div class="use-rect-row">
|
||||
<div class="use-rect">Creative Writing</div>
|
||||
<div class="use-rect">Storytelling</div>
|
||||
<div class="use-rect">Roleplay</div>
|
||||
</div>
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<div class="end-cap" aria-hidden="true"></div>
|
||||
|
||||
</section>
|
||||
</div>
|
||||
|
||||
<style>
|
||||
@import url('https://fonts.googleapis.com/css2?family=Orbitron:wght@500;600&family=Inter:wght@400;500;600&display=swap');
|
||||
|
||||
:root{
|
||||
--bg0: #06070a;
|
||||
--bg1: #0b0d12;
|
||||
|
||||
--ink: #eef0f6;
|
||||
--muted: rgba(238,240,246,0.72);
|
||||
|
||||
--silver1: #e7e9ef;
|
||||
--silver2: #b9bfcc;
|
||||
--silver3: #7c8392;
|
||||
|
||||
--red: #b0121d;
|
||||
--pink: #e04b7a;
|
||||
|
||||
--line: rgba(231,233,239,0.16);
|
||||
--shadow: rgba(0,0,0,0.60);
|
||||
}
|
||||
|
||||
|
||||
*{ box-sizing: border-box; }
|
||||
|
||||
.noctyx-stage{
|
||||
min-height: 100vh;
|
||||
padding: 84px 20px;
|
||||
background:
|
||||
radial-gradient(1200px 620px at 18% 16%, rgba(224,75,122,0.18), transparent 60%),
|
||||
radial-gradient(900px 540px at 84% 18%, rgba(176,18,29,0.18), transparent 62%),
|
||||
radial-gradient(1000px 560px at 55% 92%, rgba(231,233,239,0.10), transparent 62%),
|
||||
linear-gradient(180deg, var(--bg0), var(--bg1));
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.noctyx-stage::before{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset:0;
|
||||
pointer-events:none;
|
||||
background:
|
||||
linear-gradient(180deg, rgba(0,0,0,0.00), rgba(0,0,0,0.55)),
|
||||
repeating-linear-gradient(
|
||||
90deg,
|
||||
rgba(231,233,239,0.05) 0px,
|
||||
rgba(231,233,239,0.05) 1px,
|
||||
transparent 1px,
|
||||
transparent 38px
|
||||
),
|
||||
repeating-linear-gradient(
|
||||
0deg,
|
||||
rgba(231,233,239,0.04) 0px,
|
||||
rgba(231,233,239,0.04) 1px,
|
||||
transparent 1px,
|
||||
transparent 38px
|
||||
);
|
||||
opacity: 0.55;
|
||||
}
|
||||
|
||||
.noctyx-stage::after{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset:-20%;
|
||||
pointer-events:none;
|
||||
background:
|
||||
radial-gradient(circle at 25% 30%, rgba(224,75,122,0.10), transparent 55%),
|
||||
radial-gradient(circle at 70% 35%, rgba(176,18,29,0.10), transparent 58%),
|
||||
radial-gradient(circle at 55% 75%, rgba(231,233,239,0.06), transparent 62%);
|
||||
filter: blur(10px);
|
||||
opacity: 0.9;
|
||||
}
|
||||
|
||||
.model-card{
|
||||
max-width: 1120px;
|
||||
margin: 0 auto;
|
||||
padding: 120px 74px 110px;
|
||||
border-radius: 28px;
|
||||
position: relative;
|
||||
color: var(--ink);
|
||||
font-family: "Inter", sans-serif;
|
||||
|
||||
border: 2px solid transparent;
|
||||
background:
|
||||
radial-gradient(1000px 520px at 20% 10%, rgba(224,75,122,0.10), transparent 55%),
|
||||
radial-gradient(900px 520px at 82% 12%, rgba(176,18,29,0.12), transparent 58%),
|
||||
linear-gradient(180deg, rgba(16,18,26,0.92), rgba(10,11,16,0.92)) padding-box,
|
||||
linear-gradient(145deg, rgba(231,233,239,0.85), rgba(124,131,146,0.85), rgba(231,233,239,0.85)) border-box;
|
||||
|
||||
box-shadow:
|
||||
0 46px 120px var(--shadow),
|
||||
inset 0 1px 0 rgba(255,255,255,0.10);
|
||||
|
||||
overflow: hidden;
|
||||
}
|
||||
|
||||
.model-card::before{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset: 12px;
|
||||
border-radius: 22px;
|
||||
pointer-events:none;
|
||||
border: 1px solid rgba(231,233,239,0.20);
|
||||
box-shadow:
|
||||
inset 0 0 0 1px rgba(0,0,0,0.55),
|
||||
inset 0 0 34px rgba(224,75,122,0.08),
|
||||
inset 0 0 34px rgba(176,18,29,0.08);
|
||||
}
|
||||
|
||||
.model-card::after{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset:0;
|
||||
pointer-events:none;
|
||||
background:
|
||||
radial-gradient(circle at 0% 0%, rgba(231,233,239,0.12), transparent 38%),
|
||||
radial-gradient(circle at 100% 0%, rgba(231,233,239,0.10), transparent 40%),
|
||||
radial-gradient(circle at 0% 100%, rgba(224,75,122,0.12), transparent 44%),
|
||||
radial-gradient(circle at 100% 100%, rgba(176,18,29,0.12), transparent 46%),
|
||||
repeating-linear-gradient(180deg, rgba(255,255,255,0.03) 0px, rgba(255,255,255,0.03) 1px, transparent 1px, transparent 7px);
|
||||
opacity: 0.75;
|
||||
}
|
||||
|
||||
.card-header{
|
||||
text-align:center;
|
||||
position: relative;
|
||||
z-index: 1;
|
||||
margin-bottom: 120px;
|
||||
}
|
||||
|
||||
.title-block{
|
||||
display:inline-block;
|
||||
position: relative;
|
||||
padding: 30px 44px 26px;
|
||||
border-radius: 14px;
|
||||
background: linear-gradient(180deg, rgba(255,255,255,0.06), rgba(255,255,255,0.02));
|
||||
border: 1px solid rgba(231,233,239,0.18);
|
||||
box-shadow: 0 26px 66px rgba(0,0,0,0.55);
|
||||
|
||||
|
||||
max-width: min(900px, 100%);
|
||||
}
|
||||
|
||||
.title-frame{
|
||||
position: absolute;
|
||||
inset: -8px -12px;
|
||||
border-radius: 14px;
|
||||
z-index: -1;
|
||||
|
||||
background: transparent;
|
||||
|
||||
border: 1px solid rgba(231,233,239,0.35);
|
||||
|
||||
box-shadow:
|
||||
0 10px 28px rgba(0,0,0,0.45);
|
||||
}
|
||||
|
||||
.model-title{
|
||||
margin: 0;
|
||||
padding: 6px 0;
|
||||
|
||||
font-family: "Orbitron", sans-serif;
|
||||
font-size: clamp(1.65rem, 3.0vw, 2.7rem);
|
||||
letter-spacing: 0.095em;
|
||||
line-height: 1.25;
|
||||
|
||||
white-space: nowrap;
|
||||
overflow: visible;
|
||||
|
||||
color: var(--ink);
|
||||
text-shadow:
|
||||
0 1px 0 rgba(0,0,0,0.55),
|
||||
0 0 16px rgba(224,75,122,0.10),
|
||||
0 0 16px rgba(176,18,29,0.10);
|
||||
}
|
||||
|
||||
.model-subtitle{
|
||||
margin: 14px 0 0;
|
||||
font-size: 1.02rem;
|
||||
letter-spacing: 0.06em;
|
||||
color: var(--muted);
|
||||
}
|
||||
|
||||
.title-accents{
|
||||
margin: 18px auto 0;
|
||||
width: min(520px, 80%);
|
||||
display:flex;
|
||||
align-items:center;
|
||||
justify-content:center;
|
||||
gap: 14px;
|
||||
}
|
||||
|
||||
.accent-bar{
|
||||
height: 4px;
|
||||
flex: 1;
|
||||
border-radius: 999px;
|
||||
background: linear-gradient(90deg, transparent, rgba(231,233,239,0.55), transparent);
|
||||
}
|
||||
.accent-dot{
|
||||
width: 10px;
|
||||
height: 10px;
|
||||
border-radius: 999px;
|
||||
background: radial-gradient(circle at 30% 30%, var(--pink), var(--red));
|
||||
box-shadow: 0 0 18px rgba(224,75,122,0.35);
|
||||
}
|
||||
|
||||
.hero-wrap{
|
||||
margin-top: 58px;
|
||||
display: inline-block;
|
||||
position: relative;
|
||||
max-width: 94%;
|
||||
}
|
||||
|
||||
.hero-frame{
|
||||
display: none;
|
||||
}
|
||||
|
||||
.hero-wrap img{
|
||||
display: block;
|
||||
max-width: 100%;
|
||||
|
||||
border-radius: 12px;
|
||||
|
||||
outline: 0.5px solid rgba(231,233,239,0.35);
|
||||
outline-offset: 0;
|
||||
|
||||
box-shadow: none;
|
||||
}
|
||||
|
||||
.flow-divider{
|
||||
width: 86%;
|
||||
height: 8px;
|
||||
margin: 120px auto;
|
||||
border-radius: 999px;
|
||||
position: relative;
|
||||
z-index: 1;
|
||||
background: linear-gradient(90deg, transparent, rgba(231,233,239,0.34), rgba(224,75,122,0.38), rgba(231,233,239,0.34), transparent);
|
||||
box-shadow: 0 0 20px rgba(224,75,122,0.14), 0 0 18px rgba(231,233,239,0.10);
|
||||
}
|
||||
.flow-divider.thin{
|
||||
width: 70%;
|
||||
height: 6px;
|
||||
}
|
||||
|
||||
.content-panel{
|
||||
max-width: 980px;
|
||||
margin: 120px auto;
|
||||
position: relative;
|
||||
z-index: 1;
|
||||
|
||||
overflow: visible;
|
||||
}
|
||||
|
||||
.panel-frame{
|
||||
position:absolute;
|
||||
inset:-14px;
|
||||
border-radius: 12px;
|
||||
pointer-events:none;
|
||||
background: linear-gradient(145deg, rgba(231,233,239,0.40), rgba(124,131,146,0.32), rgba(231,233,239,0.36));
|
||||
box-shadow: 0 34px 92px rgba(0,0,0,0.55);
|
||||
}
|
||||
|
||||
.panel-frame::before{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset: 3px;
|
||||
border-radius: 11px;
|
||||
background: linear-gradient(180deg, rgba(0,0,0,0.35), rgba(0,0,0,0.15));
|
||||
box-shadow: inset 0 0 0 1px rgba(231,233,239,0.14), inset 0 0 26px rgba(224,75,122,0.08);
|
||||
}
|
||||
|
||||
.panel-inner{
|
||||
position: relative;
|
||||
padding: 86px 76px;
|
||||
border-radius: 10px;
|
||||
text-align: center;
|
||||
background:
|
||||
radial-gradient(900px 260px at 50% 0%, rgba(224,75,122,0.12), transparent 60%),
|
||||
radial-gradient(900px 260px at 50% 110%, rgba(176,18,29,0.10), transparent 62%),
|
||||
linear-gradient(180deg, rgba(255,255,255,0.06), rgba(255,255,255,0.02));
|
||||
border: 1px solid rgba(231,233,239,0.16);
|
||||
}
|
||||
|
||||
.panel-heading{
|
||||
margin: 0 0 42px;
|
||||
font-family:"Orbitron",sans-serif;
|
||||
font-size: 2.35rem;
|
||||
letter-spacing: 0.14em;
|
||||
color: var(--ink);
|
||||
transition: text-shadow 0.25s ease, transform 0.25s ease;
|
||||
}
|
||||
|
||||
.panel-heading:hover{
|
||||
transform: translateY(-1px);
|
||||
text-shadow: 0 0 18px rgba(224,75,122,0.28), 0 0 24px rgba(231,233,239,0.14);
|
||||
}
|
||||
|
||||
.content-panel p{
|
||||
margin: 0;
|
||||
font-size: 1.30rem;
|
||||
line-height: 1.95;
|
||||
color: rgba(238,240,246,0.82);
|
||||
}
|
||||
|
||||
strong{ color: var(--ink); font-weight: 700; }
|
||||
|
||||
.model-card a{
|
||||
color: rgba(238,240,246,0.86);
|
||||
text-decoration: underline;
|
||||
text-decoration-thickness: 2px;
|
||||
text-underline-offset: 3px;
|
||||
}
|
||||
.model-card a:hover{ text-shadow: 0 0 14px rgba(224,75,122,0.22); }
|
||||
|
||||
.yaml-toggle summary{
|
||||
margin-top: 40px;
|
||||
font-size: 1.05rem;
|
||||
font-weight: 650;
|
||||
letter-spacing: 0.04em;
|
||||
cursor:pointer;
|
||||
color: rgba(238,240,246,0.74);
|
||||
}
|
||||
.yaml-toggle summary:hover{
|
||||
color: rgba(238,240,246,0.92);
|
||||
text-shadow: 0 0 16px rgba(224,75,122,0.18);
|
||||
}
|
||||
.yaml-toggle pre{
|
||||
margin-top: 18px;
|
||||
padding: 28px;
|
||||
text-align:left;
|
||||
border-radius: 10px;
|
||||
overflow-x:auto;
|
||||
background: linear-gradient(180deg, rgba(231,233,239,0.10), rgba(231,233,239,0.05));
|
||||
border: 1px solid rgba(231,233,239,0.16);
|
||||
border-left: 6px solid rgba(224,75,122,0.65);
|
||||
font-size: 1.02rem;
|
||||
line-height: 1.65;
|
||||
color: rgba(238,240,246,0.86);
|
||||
}
|
||||
|
||||
.yaml-toggle pre{
|
||||
max-width: 100%;
|
||||
overflow-x: auto;
|
||||
box-sizing: border-box;
|
||||
}
|
||||
|
||||
.yaml-toggle pre{
|
||||
font-family: ui-monospace, SFMono-Regular, Menlo, Consolas, monospace;
|
||||
|
||||
text-rendering: optimizeLegibility;
|
||||
-webkit-font-smoothing: antialiased;
|
||||
-moz-osx-font-smoothing: grayscale;
|
||||
|
||||
transform: none;
|
||||
backface-visibility: hidden;
|
||||
}
|
||||
|
||||
.use-rect-row{
|
||||
display: flex;
|
||||
justify-content: center;
|
||||
align-items: stretch;
|
||||
gap: 28px;
|
||||
margin-top: 42px;
|
||||
|
||||
flex-wrap: nowrap;
|
||||
max-width: 100%;
|
||||
}
|
||||
|
||||
.use-rect{
|
||||
width: 100%;
|
||||
max-width: 100%;
|
||||
|
||||
padding: 22px 16px;
|
||||
|
||||
text-align: center;
|
||||
font-size: 1.02rem;
|
||||
letter-spacing: 0.03em;
|
||||
white-space: nowrap;
|
||||
|
||||
color: rgba(238,240,246,0.96);
|
||||
|
||||
background:
|
||||
linear-gradient(
|
||||
180deg,
|
||||
rgba(255,255,255,0.10),
|
||||
rgba(255,255,255,0.02)
|
||||
);
|
||||
|
||||
border: 1px solid rgba(231,233,239,0.22);
|
||||
border-radius: 5px;
|
||||
|
||||
box-shadow:
|
||||
inset 0 1px 0 rgba(255,255,255,0.14),
|
||||
inset 0 -2px 0 rgba(0,0,0,0.55),
|
||||
0 10px 24px rgba(0,0,0,0.55),
|
||||
0 2px 0 rgba(0,0,0,0.65);
|
||||
|
||||
position: relative;
|
||||
}
|
||||
|
||||
.use-rect::after{
|
||||
content:"";
|
||||
position:absolute;
|
||||
left: 22%;
|
||||
right: 22%;
|
||||
bottom: 9px;
|
||||
height: 2px;
|
||||
border-radius: 999px;
|
||||
background: linear-gradient(
|
||||
90deg,
|
||||
rgba(176,18,29,0.95),
|
||||
rgba(224,75,122,0.95)
|
||||
);
|
||||
box-shadow: 0 0 10px rgba(224,75,122,0.26);
|
||||
}
|
||||
|
||||
.use-rect:hover{
|
||||
transform: translateY(-2px);
|
||||
box-shadow:
|
||||
inset 0 1px 0 rgba(255,255,255,0.16),
|
||||
inset 0 -2px 0 rgba(0,0,0,0.65),
|
||||
0 18px 36px rgba(0,0,0,0.65),
|
||||
0 4px 0 rgba(0,0,0,0.75);
|
||||
}
|
||||
|
||||
@media (max-width: 1100px){
|
||||
.use-rect-row{
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
.use-rect{
|
||||
flex: 1 1 100%;
|
||||
max-width: 100%;
|
||||
white-space: normal;
|
||||
}
|
||||
}
|
||||
|
||||
.end-cap{
|
||||
width: 64%;
|
||||
height: 8px;
|
||||
margin: 72px auto 0;
|
||||
border-radius: 999px;
|
||||
background: linear-gradient(90deg, transparent, rgba(231,233,239,0.22), rgba(224,75,122,0.32), rgba(231,233,239,0.22), transparent);
|
||||
position: relative;
|
||||
z-index: 1;
|
||||
}
|
||||
|
||||
.noctyx-stage::before,
|
||||
.noctyx-stage::after{
|
||||
content: none !important;
|
||||
background: none !important;
|
||||
filter: none !important;
|
||||
opacity: 0 !important;
|
||||
}
|
||||
|
||||
</style>
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 2,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"model_type": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 10,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.3",
|
||||
"unsloth_version": "2024.9",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131075
|
||||
}
|
||||
22
mergekit_config.yml
Normal file
22
mergekit_config.yml
Normal file
@@ -0,0 +1,22 @@
|
||||
|
||||
models:
|
||||
- model: Vortex5/Harmony-Bird-12B
|
||||
- model: Retreatcost/Chrysologus-12B
|
||||
- model: Delta-Vector/Rei-V3-KTO-12B
|
||||
- model: Vortex5/Scarlet-Eclipse-12B
|
||||
- model: Vortex5/Lunar-Nexus-12B
|
||||
- model: Vortex5/Red-Synthesis-12B
|
||||
merge_method: smi_oni
|
||||
parameters:
|
||||
k_core: 2
|
||||
strength_core: 1.0
|
||||
consensus_core: 0.48
|
||||
drop_cos: 0.10
|
||||
drop_min: 3
|
||||
strength_nov: 0.45
|
||||
novelty_budget: 0.22
|
||||
consensus_nov: 0.32
|
||||
conflict_bonus: 0.18
|
||||
dtype: bfloat16
|
||||
tokenizer:
|
||||
source: Vortex5/Red-Synthesis-12B
|
||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0de2483355c7134891d140c575d00b15f9cfdb52956cc0b84fd70b6489749b1
|
||||
size 4865550776
|
||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e1d9b6ed4df76df58809ebaf437b9545fc4e428d916cc60746be83dce885077c
|
||||
size 4907529456
|
||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d59db65aa717dd19a13a6bb59b07da75ae2b0719b55dfe0f5c46ffe4c3938bf4
|
||||
size 4907529464
|
||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f1f094a2cc1650230929ccd20a55f3add908168a338c2408ed8bc053c0b0e1b5
|
||||
size 4907529456
|
||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1f7354f872d3cb036496a23d11c25e7715db5c53fbfebec6f88a8e59c45a5e4e
|
||||
size 4907529392
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495626240,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00005.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:33cb74e9ca1c0323b1be5f7e367b96bae218c22d0c4ed5b0edeec39f3a8755c3
|
||||
size 17078856
|
||||
8042
tokenizer_config.json
Normal file
8042
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user