初始化项目,由ModelHub XC社区提供模型
Model: Vortex5/Wicked-Oblivion-12B Source: Original Platform
This commit is contained in:
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
|
||||
cover.png filter=lfs diff=lfs merge=lfs -text
|
||||
494
README.md
Normal file
494
README.md
Normal file
@@ -0,0 +1,494 @@
|
||||
---
|
||||
base_model:
|
||||
- LatitudeGames/Muse-12B
|
||||
- yamatazen/NeonMaid-12B-v2
|
||||
- Epiculous/Violet_Twilight-v0.2
|
||||
- TheDrummer/Rocinante-X-12B-v1
|
||||
- Vortex5/Crimson-Constellation-12B
|
||||
- SicariusSicariiStuff/Impish_Nemo_12B
|
||||
- crestf411/MN-Slush
|
||||
- nothingiisreal/MN-12B-Celeste-V1.9
|
||||
- LatitudeGames/Wayfarer-12B
|
||||
- inflatebot/MN-12B-Mag-Mell-R1
|
||||
- PocketDoc/Dans-SakuraKaze-V1.0.0-12b
|
||||
- Nitral-AI/Captain-Eris_Violet-V0.420-12B
|
||||
- anthracite-org/magnum-v4-12b
|
||||
library_name: transformers
|
||||
tags:
|
||||
- mergekit
|
||||
- merge
|
||||
- roleplay
|
||||
license: apache-2.0
|
||||
---
|
||||
<section class="container">
|
||||
|
||||
<div class="header">
|
||||
<h1 class="title-main">Wicked-Oblivion-12B</h1>
|
||||
</div>
|
||||
|
||||
<div class="image-box">
|
||||
<img src="cover.png">
|
||||
</div>
|
||||
|
||||
<div class="divider"></div>
|
||||
|
||||
<section class="card">
|
||||
|
||||
<h2 class="card-title">Overview</h2>
|
||||
|
||||
<p>
|
||||
<strong class="highlight">Wicked-Oblivion-12B</strong> was created by merging
|
||||
<a href="https://huggingface.co/LatitudeGames/Muse-12B" class="link">Muse-12B</a>,
|
||||
<a href="https://huggingface.co/anthracite-org/magnum-v4-12b" class="link">magnum-v4-12b</a>,
|
||||
<a href="https://huggingface.co/yamatazen/NeonMaid-12B-v2" class="link">NeonMaid-12B-v2</a>,
|
||||
<a href="https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B" class="link">Impish_Nemo_12B</a>,
|
||||
<a href="https://huggingface.co/crestf411/MN-Slush" class="link">MN-Slush</a>,
|
||||
<a href="https://huggingface.co/Epiculous/Violet_Twilight-v0.2" class="link">Violet_Twilight-v0.2</a>,
|
||||
<a href="https://huggingface.co/LatitudeGames/Wayfarer-12B" class="link">Wayfarer-12B</a>,
|
||||
<a href="https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1" class="link">MN-12B-Mag-Mell-R1</a>,
|
||||
<a href="https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9" class="link">MN-12B-Celeste-V1.9</a>,
|
||||
<a href="https://huggingface.co/Nitral-AI/Captain-Eris_Violet-V0.420-12B" class="link">Captain-Eris_Violet-V0.420-12B</a>,
|
||||
<a href="https://huggingface.co/PocketDoc/Dans-SakuraKaze-V1.0.0-12b" class="link">Dans-SakuraKaze-V1.0.0-12b</a>,
|
||||
<a href="https://huggingface.co/TheDrummer/Rocinante-X-12B-v1" class="link">Rocinante-X-12B-v1</a>,
|
||||
and
|
||||
<a href="https://huggingface.co/Vortex5/Crimson-Constellation-12B" class="link">Crimson-Constellation-12B</a>, using a custom method.
|
||||
</p>
|
||||
|
||||
<details class="config">
|
||||
<summary>Merge configuration</summary>
|
||||
<pre>
|
||||
base_model: Vortex5/Crimson-Constellation-12B
|
||||
models:
|
||||
- model: LatitudeGames/Muse-12B
|
||||
- model: anthracite-org/magnum-v4-12b
|
||||
- model: yamatazen/NeonMaid-12B-v2
|
||||
- model: SicariusSicariiStuff/Impish_Nemo_12B
|
||||
- model: crestf411/MN-Slush
|
||||
- model: Epiculous/Violet_Twilight-v0.2
|
||||
- model: LatitudeGames/Wayfarer-12B
|
||||
- model: inflatebot/MN-12B-Mag-Mell-R1
|
||||
- model: nothingiisreal/MN-12B-Celeste-V1.9
|
||||
- model: Nitral-AI/Captain-Eris_Violet-V0.420-12B
|
||||
- model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
|
||||
- model: TheDrummer/Rocinante-X-12B-v1
|
||||
- model: Vortex5/Crimson-Constellation-12B
|
||||
merge_method: gcr
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
chat_template: auto
|
||||
parameters:
|
||||
strength: 0.86
|
||||
retention: 0.66
|
||||
novelty: 0.36
|
||||
stability: 0.62
|
||||
coherence: 0.28
|
||||
tokenizer:
|
||||
source: Vortex5/Crimson-Constellation-12B
|
||||
</pre>
|
||||
</details>
|
||||
|
||||
</section>
|
||||
|
||||
<section class="card">
|
||||
<h2 class="card-title">Intended Use</h2>
|
||||
|
||||
<div class="grid">
|
||||
|
||||
<div class="tile">
|
||||
<span class="tile-main">Roleplay</span>
|
||||
<span class="tile-sub">Character-driven interaction</span>
|
||||
</div>
|
||||
|
||||
<div class="tile">
|
||||
<span class="tile-main">Storytelling</span>
|
||||
<span class="tile-sub">Long-form narrative</span>
|
||||
</div>
|
||||
|
||||
<div class="tile">
|
||||
<span class="tile-main">Creative Writing</span>
|
||||
<span class="tile-sub">Atmospheric fiction</span>
|
||||
</div>
|
||||
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<div class="divider"></div>
|
||||
|
||||
</section>
|
||||
|
||||
<style>
|
||||
|
||||
.container{
|
||||
--bg:#010104;
|
||||
--bg2:#050508;
|
||||
--panel:#09090f;
|
||||
--panel2:#111018;
|
||||
--soft:#15131f;
|
||||
|
||||
--text:#f4f1f6;
|
||||
--text-dim:#b9b3c2;
|
||||
|
||||
--red:#c81424;
|
||||
--red2:#ff2638;
|
||||
--silver:#d8d8df;
|
||||
--silver2:#8d8d9b;
|
||||
--purple:#7b3cff;
|
||||
--purple2:#b18cff;
|
||||
|
||||
--grad:linear-gradient(90deg,#c81424,#d8d8df,#7b3cff);
|
||||
|
||||
max-width:1100px;
|
||||
margin:50px auto;
|
||||
padding:48px;
|
||||
|
||||
position:relative;
|
||||
overflow:hidden;
|
||||
|
||||
border:2px solid rgba(216,216,223,0.22);
|
||||
|
||||
background:
|
||||
linear-gradient(90deg, rgba(200,20,36,0.26), transparent 14%, transparent 86%, rgba(123,60,255,0.28)),
|
||||
linear-gradient(180deg, rgba(216,216,223,0.09), transparent 18%, transparent 82%, rgba(200,20,36,0.12)),
|
||||
radial-gradient(circle at 0% 50%, rgba(255,38,56,0.24), transparent 30%),
|
||||
radial-gradient(circle at 100% 50%, rgba(123,60,255,0.26), transparent 30%),
|
||||
radial-gradient(circle at 50% 12%, rgba(216,216,223,0.12), transparent 34%),
|
||||
repeating-linear-gradient(135deg, rgba(216,216,223,0.035) 0 1px, transparent 1px 18px),
|
||||
linear-gradient(180deg,#050508 0%,#010104 52%,#000000 100%);
|
||||
|
||||
color:var(--text);
|
||||
font-family:"Cinzel","Georgia","Times New Roman",serif;
|
||||
|
||||
display:flex;
|
||||
flex-direction:column;
|
||||
gap:36px;
|
||||
|
||||
box-shadow:
|
||||
inset 0 0 0 1px rgba(255,255,255,0.05),
|
||||
inset 26px 0 70px rgba(200,20,36,0.16),
|
||||
inset -26px 0 70px rgba(123,60,255,0.18),
|
||||
}
|
||||
|
||||
.container::before{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset:14px;
|
||||
pointer-events:none;
|
||||
border:1px solid rgba(216,216,223,0.18);
|
||||
background:
|
||||
linear-gradient(90deg, rgba(255,38,56,0.28), transparent 20%, transparent 80%, rgba(123,60,255,0.32)),
|
||||
linear-gradient(180deg, rgba(216,216,223,0.12), transparent 22%, transparent 78%, rgba(216,216,223,0.08));
|
||||
clip-path:polygon(
|
||||
0 0, 18% 0, 18% 3px, 82% 3px, 82% 0, 100% 0,
|
||||
100% 24%, calc(100% - 3px) 24%, calc(100% - 3px) 76%, 100% 76%,
|
||||
100% 100%, 82% 100%, 82% calc(100% - 3px), 18% calc(100% - 3px), 18% 100%,
|
||||
0 100%, 0 76%, 3px 76%, 3px 24%, 0 24%
|
||||
);
|
||||
opacity:.95;
|
||||
}
|
||||
|
||||
.container::after{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset:-40%;
|
||||
pointer-events:none;
|
||||
background:
|
||||
conic-gradient(from 90deg,
|
||||
transparent 0 12%,
|
||||
rgba(200,20,36,0.12) 12% 14%,
|
||||
transparent 14% 36%,
|
||||
rgba(216,216,223,0.08) 36% 38%,
|
||||
transparent 38% 62%,
|
||||
rgba(123,60,255,0.12) 62% 64%,
|
||||
transparent 64% 100%);
|
||||
opacity:.45;
|
||||
filter:blur(10px);
|
||||
}
|
||||
|
||||
.header{
|
||||
position:relative;
|
||||
z-index:1;
|
||||
text-align:center;
|
||||
padding:28px 16px 30px;
|
||||
border-bottom:1px solid rgba(216,216,223,0.12);
|
||||
background:
|
||||
linear-gradient(90deg, rgba(200,20,36,0.12), rgba(216,216,223,0.05), rgba(123,60,255,0.12));
|
||||
}
|
||||
|
||||
.header::before,
|
||||
.header::after{
|
||||
content:"";
|
||||
position:absolute;
|
||||
bottom:10px;
|
||||
width:130px;
|
||||
height:2px;
|
||||
background:var(--grad);
|
||||
box-shadow:
|
||||
0 0 14px rgba(200,20,36,0.55),
|
||||
0 0 20px rgba(123,60,255,0.45);
|
||||
}
|
||||
|
||||
.header::before{
|
||||
left:24px;
|
||||
}
|
||||
|
||||
.header::after{
|
||||
right:24px;
|
||||
}
|
||||
|
||||
.title-main{
|
||||
margin:0;
|
||||
font-size:clamp(1.1rem,3vw,2.3rem);
|
||||
font-weight:900;
|
||||
letter-spacing:.09em;
|
||||
text-transform:uppercase;
|
||||
position:relative;
|
||||
display:inline-block;
|
||||
|
||||
white-space:nowrap;
|
||||
max-width:100%;
|
||||
line-height:1.05;
|
||||
|
||||
color:#050508;
|
||||
background:none;
|
||||
-webkit-background-clip:initial;
|
||||
background-clip:initial;
|
||||
|
||||
-webkit-text-stroke:1px rgba(230,230,238,0.92);
|
||||
|
||||
text-shadow:
|
||||
0 2px 0 rgba(0,0,0,1),
|
||||
0 0 4px rgba(216,216,223,0.85),
|
||||
0 0 12px rgba(200,20,36,0.55),
|
||||
0 0 22px rgba(123,60,255,0.42),
|
||||
0 0 34px rgba(0,0,0,0.9);
|
||||
}
|
||||
|
||||
.title-main::before{
|
||||
content:"Wicked-Oblivion-12B";
|
||||
position:absolute;
|
||||
inset:0;
|
||||
z-index:-1;
|
||||
|
||||
color:#000;
|
||||
white-space:nowrap;
|
||||
|
||||
-webkit-text-stroke:6px rgba(0,0,0,0.98);
|
||||
|
||||
text-shadow:
|
||||
0 0 16px rgba(200,20,36,0.42),
|
||||
0 0 24px rgba(123,60,255,0.38);
|
||||
}
|
||||
|
||||
.title-main::after{
|
||||
content:"";
|
||||
position:absolute;
|
||||
left:50%;
|
||||
bottom:-12px;
|
||||
transform:translateX(-50%);
|
||||
width:78%;
|
||||
height:3px;
|
||||
background:linear-gradient(90deg,#c81424,#d8d8df,#7b3cff);
|
||||
box-shadow:
|
||||
0 0 14px rgba(200,20,36,0.7),
|
||||
0 0 22px rgba(123,60,255,0.55);
|
||||
}
|
||||
|
||||
.image-box{
|
||||
position:relative;
|
||||
z-index:1;
|
||||
display:flex;
|
||||
justify-content:center;
|
||||
}
|
||||
|
||||
.image-box img{
|
||||
width:100%;
|
||||
max-width:880px;
|
||||
|
||||
border:2px solid rgba(216,216,223,0.2);
|
||||
background:var(--soft);
|
||||
|
||||
box-shadow:
|
||||
0 10px 0 rgba(0,0,0,0.9),
|
||||
0 0 0 1px rgba(200,20,36,0.22),
|
||||
0 0 24px rgba(200,20,36,0.22),
|
||||
0 0 42px rgba(123,60,255,0.16);
|
||||
}
|
||||
|
||||
.divider{
|
||||
position:relative;
|
||||
z-index:1;
|
||||
height:3px;
|
||||
width:100%;
|
||||
background:var(--grad);
|
||||
opacity:1;
|
||||
|
||||
box-shadow:
|
||||
0 0 16px rgba(200,20,36,0.65),
|
||||
0 0 24px rgba(216,216,223,0.25),
|
||||
0 0 32px rgba(123,60,255,0.45);
|
||||
}
|
||||
|
||||
.card{
|
||||
position:relative;
|
||||
z-index:1;
|
||||
background:
|
||||
linear-gradient(90deg, rgba(200,20,36,0.10), transparent 18%, transparent 82%, rgba(123,60,255,0.12)),
|
||||
linear-gradient(180deg,#101017,#060609);
|
||||
padding:26px 28px;
|
||||
|
||||
border:2px solid rgba(216,216,223,0.16);
|
||||
|
||||
box-shadow:
|
||||
inset 0 0 0 1px rgba(255,255,255,0.035),
|
||||
inset 14px 0 40px rgba(200,20,36,0.09),
|
||||
inset -14px 0 40px rgba(123,60,255,0.10),
|
||||
0 8px 0 rgba(0,0,0,0.85),
|
||||
0 0 16px rgba(200,20,36,0.16),
|
||||
0 0 22px rgba(123,60,255,0.12);
|
||||
}
|
||||
|
||||
.card::before{
|
||||
content:"";
|
||||
position:absolute;
|
||||
inset:8px;
|
||||
pointer-events:none;
|
||||
border:1px solid rgba(216,216,223,0.09);
|
||||
}
|
||||
|
||||
.card-title{
|
||||
margin:0 0 12px;
|
||||
font-size:1.25rem;
|
||||
letter-spacing:.14em;
|
||||
text-transform:uppercase;
|
||||
color:#e4e4eb;
|
||||
text-shadow:
|
||||
0 0 12px rgba(216,216,223,0.28),
|
||||
0 0 18px rgba(200,20,36,0.24);
|
||||
}
|
||||
|
||||
.card p{
|
||||
margin:10px 0;
|
||||
line-height:1.7;
|
||||
color:var(--text-dim);
|
||||
font-family:"Inter","Segoe UI",sans-serif;
|
||||
}
|
||||
|
||||
.highlight{
|
||||
color:#ff2638;
|
||||
font-weight:800;
|
||||
text-shadow:0 0 12px rgba(200,20,36,0.45);
|
||||
}
|
||||
|
||||
.link{
|
||||
color:#d8d8df;
|
||||
text-decoration:none;
|
||||
font-weight:700;
|
||||
}
|
||||
|
||||
.link:hover{
|
||||
color:#ff2638;
|
||||
text-decoration:underline;
|
||||
text-shadow:0 0 10px rgba(200,20,36,0.45);
|
||||
}
|
||||
|
||||
.method{
|
||||
color:#b18cff;
|
||||
font-weight:800;
|
||||
text-shadow:0 0 12px rgba(123,60,255,0.6);
|
||||
}
|
||||
|
||||
.config{
|
||||
margin-top:16px;
|
||||
border:1px solid rgba(216,216,223,0.16);
|
||||
background:#030305;
|
||||
}
|
||||
|
||||
.config summary{
|
||||
padding:10px 14px;
|
||||
cursor:pointer;
|
||||
font-size:.85rem;
|
||||
text-transform:uppercase;
|
||||
letter-spacing:.08em;
|
||||
font-weight:800;
|
||||
color:#d8d8df;
|
||||
background:
|
||||
linear-gradient(90deg, rgba(200,20,36,0.18), rgba(10,10,16,1), rgba(123,60,255,0.18));
|
||||
font-family:"Inter","Segoe UI",sans-serif;
|
||||
}
|
||||
|
||||
.config pre{
|
||||
margin:0;
|
||||
padding:16px;
|
||||
font-family:ui-monospace,Consolas,monospace;
|
||||
font-size:.85rem;
|
||||
overflow-x:auto;
|
||||
background:
|
||||
radial-gradient(circle at 0% 50%, rgba(200,20,36,0.08), transparent 26%),
|
||||
radial-gradient(circle at 100% 50%, rgba(123,60,255,0.08), transparent 26%),
|
||||
#020203;
|
||||
color:#dfe0e8;
|
||||
}
|
||||
|
||||
.grid{
|
||||
display:flex;
|
||||
gap:16px;
|
||||
flex-wrap:wrap;
|
||||
margin-top:14px;
|
||||
}
|
||||
|
||||
.tile{
|
||||
flex:1 1 180px;
|
||||
padding:16px;
|
||||
|
||||
background:
|
||||
linear-gradient(135deg, rgba(200,20,36,0.11), rgba(21,19,31,1), rgba(123,60,255,0.10));
|
||||
border:1px solid rgba(216,216,223,0.17);
|
||||
|
||||
text-align:center;
|
||||
|
||||
box-shadow:
|
||||
inset 0 0 0 1px rgba(255,255,255,0.035),
|
||||
inset 10px 0 26px rgba(200,20,36,0.08),
|
||||
inset -10px 0 26px rgba(123,60,255,0.08);
|
||||
}
|
||||
|
||||
.tile:hover{
|
||||
transform:translateY(-2px);
|
||||
border-color:#d8d8df;
|
||||
|
||||
box-shadow:
|
||||
0 4px 0 rgba(0,0,0,0.85),
|
||||
0 0 16px rgba(200,20,36,0.28),
|
||||
0 0 20px rgba(123,60,255,0.22);
|
||||
}
|
||||
|
||||
.tile-main{
|
||||
display:block;
|
||||
font-weight:800;
|
||||
text-transform:uppercase;
|
||||
letter-spacing:.08em;
|
||||
color:#ff2638;
|
||||
margin-bottom:6px;
|
||||
text-shadow:0 0 10px rgba(200,20,36,0.45);
|
||||
}
|
||||
|
||||
.tile-sub{
|
||||
font-size:.9rem;
|
||||
color:var(--text-dim);
|
||||
font-family:"Inter","Segoe UI",sans-serif;
|
||||
}
|
||||
|
||||
@media(max-width:600px){
|
||||
.container{
|
||||
padding:28px 20px;
|
||||
}
|
||||
.card{
|
||||
padding:20px;
|
||||
}
|
||||
.header::before,
|
||||
.header::after{
|
||||
display:none;
|
||||
}
|
||||
}
|
||||
|
||||
</style>
|
||||
4
chat_template.jinja
Normal file
4
chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
||||
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
||||
' + message['content'] + '<|im_end|>' + '
|
||||
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
||||
' }}{% endif %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"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,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.56.2",
|
||||
"use_cache": false,
|
||||
"vocab_size": 131075
|
||||
}
|
||||
3
cover.png
Normal file
3
cover.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2dc2cc1aee08238f6d221792caaaad782d97d125f235bc090137dc3401551092
|
||||
size 2154429
|
||||
28
mergekit_config.yml
Normal file
28
mergekit_config.yml
Normal file
@@ -0,0 +1,28 @@
|
||||
|
||||
base_model: Vortex5/Crimson-Constellation-12B
|
||||
models:
|
||||
- model: LatitudeGames/Muse-12B
|
||||
- model: anthracite-org/magnum-v4-12b
|
||||
- model: yamatazen/NeonMaid-12B-v2
|
||||
- model: SicariusSicariiStuff/Impish_Nemo_12B
|
||||
- model: crestf411/MN-Slush
|
||||
- model: Epiculous/Violet_Twilight-v0.2
|
||||
- model: LatitudeGames/Wayfarer-12B
|
||||
- model: inflatebot/MN-12B-Mag-Mell-R1
|
||||
- model: nothingiisreal/MN-12B-Celeste-V1.9
|
||||
- model: Nitral-AI/Captain-Eris_Violet-V0.420-12B
|
||||
- model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
|
||||
- model: TheDrummer/Rocinante-X-12B-v1
|
||||
- model: Vortex5/Crimson-Constellation-12B
|
||||
merge_method: gcr
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
chat_template: auto
|
||||
parameters:
|
||||
strength: 0.86
|
||||
retention: 0.66
|
||||
novelty: 0.36
|
||||
stability: 0.62
|
||||
coherence: 0.28
|
||||
tokenizer:
|
||||
source: Vortex5/Crimson-Constellation-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 sha256:637574fb7e2e2283a1761e6981c3f1447130b06b4485779d747df8ed727d4da8
|
||||
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:fe648437133afe362d9043607fbd54c4cae412cb960b7f43ccc3272b477b6d31
|
||||
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 sha256:22b5d1c57bd4a97fea21b8712a3bcf8a3b2c62bc944f13c026e51d54524a1640
|
||||
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 sha256:80fae45b4af9f897f4e4b0d2f479cda938158982564f492249c87be48207357f
|
||||
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:d13762d5d84f857df45897b7ae5293d4bc3cc14a34db107a6f805177fb65af48
|
||||
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