初始化项目，由ModelHub XC社区提供模型
Model: EldritchLabs/Kraken-Karcher-12B-v1 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
|
||||
515
README.md
Normal file
515
README.md
Normal file
@@ -0,0 +1,515 @@
|
||||
---
|
||||
base_model:
|
||||
- aixonlab/Aether-12b
|
||||
- aixonlab/Zinakha-12b
|
||||
- allura-org/Bigger-Body-12b
|
||||
- allura-org/MN-12b-RP-Ink
|
||||
- allura-org/remnant-mn-12b
|
||||
- anthracite-org/magnum-v4-12b
|
||||
- ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2
|
||||
- Babsie/Opulus-12B-v3
|
||||
- BeaverAI/mistral-doryV2-12b
|
||||
- crestf411/nemo-sunfall-v0.6.1
|
||||
- EpistemeAI2/Fireball-Mistral-Nemo-12B-Philos
|
||||
- EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math
|
||||
- Fizzarolli/MN-12b-Rosier-v1
|
||||
- HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407
|
||||
- IIEleven11/Kalypso
|
||||
- intervitens/mini-magnum-12b-v1.1
|
||||
- jtatman/mistral_nemo_12b_reasoning_psychology_lora
|
||||
- KOOWEEYUS/BlackSheep-RP-12B
|
||||
- Lambent/Arsenic-Shahrazad-12B-v2
|
||||
- Lambent/Arsenic-Shahrazad-12B-v3
|
||||
- Lambent/arsenic-nemo-unleashed-12B
|
||||
- Lambent/Gilded-Arsenic-12B
|
||||
- mistralai/Mistral-Nemo-Instruct-2407
|
||||
- nbeerbower/Lyra-Gutenberg-mistral-nemo-12B
|
||||
- nbeerbower/Lyra4-Gutenberg-12B
|
||||
- nbeerbower/mistral-nemo-bophades-12B
|
||||
- nbeerbower/mistral-nemo-gutenberg-12B-v3
|
||||
- nbeerbower/mistral-nemo-gutenberg-12B-v4
|
||||
- nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B
|
||||
- nbeerbower/Mistral-Nemo-Gutenberg-Encore-12B
|
||||
- nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B
|
||||
- nbeerbower/mistral-nemo-wissenschaft-12B
|
||||
- NeverSleepHistorical/lumi-nemo-e2.0
|
||||
- NeverSleep/Lumimaid-v0.2-12B
|
||||
- nothingiisreal/Celeste-12B-V1.6
|
||||
- nothingiisreal/MN-12B-Celeste-V1.9
|
||||
- PocketDoc/Dans-DangerousWinds-V1.1.0-12b
|
||||
- ReadyArt/Dark-Nexus-12B-v2.0
|
||||
- ReadyArt/Forgotten-Safeword-12B-v4.0
|
||||
- ReadyArt/Omega-Darker_The-Final-Directive-12B
|
||||
- romaingrx/red-teamer-mistral-nemo
|
||||
- Sao10K/MN-12B-Lyra-v1
|
||||
- Sao10K/MN-12B-Lyra-v4
|
||||
- shisa-ai/shisa-v2-mistral-nemo-12b
|
||||
- sleepdeprived3/Christian-Bible-Expert-v2.0-12B
|
||||
- SuperbEmphasis/MN-12b-RP-Ink-RP-Longform
|
||||
- SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2
|
||||
- TheDrummer/Rivermind-12B-v1
|
||||
- TheDrummer/Rocinante-12B-v1
|
||||
- TheDrummer/Rocinante-X-12B-v1
|
||||
- Trappu/Nemo-Picaro-12B
|
||||
- Undi95/LocalC-12B-e2.0
|
||||
- VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- creative
|
||||
- creative writing
|
||||
- fiction writing
|
||||
- plot generation
|
||||
- sub-plot generation
|
||||
- fiction writing
|
||||
- story generation
|
||||
- scene continue
|
||||
- storytelling
|
||||
- fiction story
|
||||
- science fiction
|
||||
- romance
|
||||
- all genres
|
||||
- story
|
||||
- writing
|
||||
- vivid prosing
|
||||
- vivid writing
|
||||
- fiction
|
||||
- roleplaying
|
||||
- float32
|
||||
- swearing
|
||||
- rp
|
||||
- horror
|
||||
- della
|
||||
- mistral
|
||||
- nemo
|
||||
- merge
|
||||
- mergekit
|
||||
widget:
|
||||
- text: "Kraken-Karcher-12B-v1"
|
||||
output:
|
||||
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/pUx0TDH4fpFLRsVWYiMB-.png
|
||||
---
|
||||
|
||||
> [!NOTE]
|
||||
> <span style="color:red; font-weight:bold">⚠️ Note:</span> This model requires **Mistral Tekken** chat template.
|
||||
>
|
||||
|
||||
<!DOCTYPE html>
|
||||
<style>
|
||||
body {
|
||||
font-family: sans-serif;
|
||||
color: #CDE4EE; /* Pale icy blue */
|
||||
line-height: 1.6;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
background-color: #040814; /* Very dark abyss blue */
|
||||
}
|
||||
|
||||
b, strong {
|
||||
color: #00D4FF; /* Bright cyan/lightning blue */
|
||||
text-shadow: 0 0 8px rgba(0, 212, 255, 0.4);
|
||||
}
|
||||
|
||||
.kraken-text {
|
||||
color: #E0F7FA;
|
||||
position: relative;
|
||||
z-index: 2;
|
||||
margin-left: 0.2em;
|
||||
text-shadow: 0 0 15px #00D4FF, 0 0 30px #0077B6; /* Deep sea cyan glow */
|
||||
}
|
||||
|
||||
/* Section styling */
|
||||
.section-container {
|
||||
background-color: rgba(10, 17, 28, 0.85); /* Dark slate blue */
|
||||
margin-bottom: 30px;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
border-bottom: 1px solid #0077B6; /* Deep ocean blue */
|
||||
box-shadow: 0 4px 20px rgba(0, 119, 182, 0.15);
|
||||
}
|
||||
|
||||
.section-header {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
background-color: rgba(0, 119, 182, 0.1);
|
||||
padding: 10px 20px;
|
||||
border-top: 1px solid rgba(0, 119, 182, 0.3);
|
||||
}
|
||||
|
||||
.section-indicator {
|
||||
width: 8px;
|
||||
height: 20px;
|
||||
background-color: #00D4FF;
|
||||
margin-right: 15px;
|
||||
box-shadow: 0 0 10px rgba(0, 212, 255, 0.6);
|
||||
border-radius: 2px;
|
||||
}
|
||||
|
||||
.section-title {
|
||||
font-family: 'Georgia', 'Times New Roman', serif; /* Nautical logbook feel */
|
||||
color: #E0F7FA;
|
||||
font-size: 1.4rem;
|
||||
margin: 0;
|
||||
letter-spacing: 1px;
|
||||
font-weight: 400;
|
||||
text-transform: capitalize;
|
||||
}
|
||||
|
||||
.section-content {
|
||||
padding: 20px;
|
||||
font-family: sans-serif;
|
||||
color: #CDE4EE;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
/* Title styling */
|
||||
.title-container {
|
||||
background-color: #02050A;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
margin-bottom: 40px;
|
||||
border-left: 4px solid #00D4FF;
|
||||
box-shadow: 0 6px 25px rgba(0, 212, 255, 0.15);
|
||||
}
|
||||
|
||||
.title-wrapper {
|
||||
position: relative;
|
||||
z-index: 2;
|
||||
padding: 25px 20px 30px 30px;
|
||||
font-family: 'Georgia', 'Times New Roman', serif;
|
||||
}
|
||||
|
||||
.title-main {
|
||||
color: #E0F7FA;
|
||||
font-size: 2.0rem;
|
||||
font-weight: 700;
|
||||
margin: 0;
|
||||
letter-spacing: 2px;
|
||||
display: inline-block;
|
||||
position: relative;
|
||||
text-transform: uppercase;
|
||||
}
|
||||
|
||||
.storm-overlay {
|
||||
position: absolute;
|
||||
top: 0;
|
||||
left: 0;
|
||||
width: 100%;
|
||||
height: 100%;
|
||||
/* Diagonal rain/storm effect */
|
||||
background-image: repeating-linear-gradient(15deg, rgba(0,0,0,0) 0, rgba(0, 212, 255, 0.03) 1px, rgba(0,0,0,0) 3px);
|
||||
z-index: 1;
|
||||
}
|
||||
|
||||
/* Subheading styling */
|
||||
.subheading {
|
||||
color: #48CAE4; /* Churning sea blue */
|
||||
font-size: 1.1rem;
|
||||
margin-top: 20px;
|
||||
margin-bottom: 15px;
|
||||
font-weight: 400;
|
||||
border-bottom: 1px dashed rgba(72, 202, 228, 0.4);
|
||||
display: inline-block;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 1px;
|
||||
font-family: 'Georgia', 'Times New Roman', serif;
|
||||
}
|
||||
|
||||
/* Links */
|
||||
a {
|
||||
color: #48CAE4;
|
||||
text-decoration: none;
|
||||
transition: color 0.3s ease, text-shadow 0.3s ease;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
text-decoration: underline;
|
||||
color: #00D4FF;
|
||||
text-shadow: 0 0 8px rgba(0, 212, 255, 0.5);
|
||||
}
|
||||
|
||||
/* Container */
|
||||
.container {
|
||||
max-width: 1200px;
|
||||
margin: 20px auto;
|
||||
padding: 40px 20px;
|
||||
background-color: #060B14;
|
||||
background-image:
|
||||
radial-gradient(circle at 15% 85%, rgba(0, 119, 182, 0.08) 0%, transparent 50%),
|
||||
radial-gradient(circle at 85% 15%, rgba(0, 212, 255, 0.05) 0%, transparent 50%);
|
||||
min-height: calc(100vh - 40px);
|
||||
border: 1px solid #003A5C; /* Deep teal/blue border */
|
||||
border-radius: 8px;
|
||||
box-shadow: 0 8px 40px rgba(0, 0, 0, 0.9), inset 0 0 20px rgba(0, 119, 182, 0.05);
|
||||
}
|
||||
|
||||
/* Code blocks */
|
||||
pre {
|
||||
background-color: #020408;
|
||||
border: 1px solid #003A5C;
|
||||
border-left: 3px solid #0077B6;
|
||||
padding: 15px;
|
||||
border-radius: 4px;
|
||||
color: #90E0EF;
|
||||
overflow-x: auto;
|
||||
}
|
||||
code {
|
||||
font-family: 'Courier New', Courier, monospace;
|
||||
color: #00D4FF;
|
||||
background-color: rgba(0, 212, 255, 0.08);
|
||||
padding: 2px 4px;
|
||||
border-radius: 3px;
|
||||
}
|
||||
pre code {
|
||||
color: #90E0EF;
|
||||
background-color: transparent;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
</style>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Kraken</title>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<div class="container">
|
||||
<div class="title-container">
|
||||
<div class="storm-overlay"></div>
|
||||
<div class="title-wrapper">
|
||||
<h1 class="title-main">
|
||||
<span class="kraken-text">🦑 Kraken Karcher 12B v1</span>
|
||||
</h1>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/pUx0TDH4fpFLRsVWYiMB-.png" alt="Kraken" style="width:100%; border-radius: 5px; margin-bottom: 30px; border: 1px solid #003A5C; box-shadow: 0 0 20px rgba(0, 119, 182, 0.2);">
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">Overview</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
This is a merge of pre-trained language models created using <a href="https://github.com/cg123/mergekit">mergekit</a>.
|
||||
<br><br>
|
||||
This is the smartest of the 3 tested variants: Della, Karcher, and Model_Stock. <b>Kraken v1 combines 52 finetunes with the Nemo base model</b>, no merges included. It was designed primarily for <b>creativity</b> and <b>roleplay</b>. The early terminations bug with v0 has been solved by removing all ChatML based models, leaving only default Mistral Tekken tokenizers. This version took 16 hours to merge via the <code>karcher</code> method while running for 500 iterations.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">Merge Details</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
<b>Merge Details</b><br>
|
||||
This model was merged using the <a href="https://arxiv.org/abs/2406.11617">karcher</a> merge method.<br><br>
|
||||
The <a href="https://huggingface.co/spaces/Naphula/model_tools/blob/main/graph_v18.py">graph_v18.py</a> patch was helpful to use 8GB VRAM for acceleration.<br><br>
|
||||
<b>Models Merged</b><br>
|
||||
The following models were included in the merge:
|
||||
<ul>
|
||||
<li><a href="https://huggingface.co/aixonlab/Aether-12b">aixonlab/Aether-12b</a></li>
|
||||
<li><a href="https://huggingface.co/aixonlab/Zinakha-12b">aixonlab/Zinakha-12b</a></li>
|
||||
<li><a href="https://huggingface.co/allura-org/Bigger-Body-12b">allura-org/Bigger-Body-12b</a></li>
|
||||
<li><a href="https://huggingface.co/allura-org/MN-12b-RP-Ink">allura-org/MN-12b-RP-Ink</a></li>
|
||||
<li><a href="https://huggingface.co/allura-org/remnant-mn-12b">allura-org/remnant-mn-12b</a></li>
|
||||
<li><a href="https://huggingface.co/anthracite-org/magnum-v4-12b">anthracite-org/magnum-v4-12b</a></li>
|
||||
<li><a href="https://huggingface.co/ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2">ArliAI/Mistral-Nemo-12B-ArliAI-RPMax-v1.2</a></li>
|
||||
<li><a href="https://huggingface.co/Babsie/Opulus-12B-v3">Babsie/Opulus-12B-v3</a></li>
|
||||
<li><a href="https://huggingface.co/BeaverAI/mistral-doryV2-12b">BeaverAI/mistral-doryV2-12b</a></li>
|
||||
<li><a href="https://huggingface.co/crestf411/nemo-sunfall-v0.6.1">crestf411/nemo-sunfall-v0.6.1</a></li>
|
||||
<li><a href="https://huggingface.co/EpistemeAI2/Fireball-Mistral-Nemo-12B-Philos">EpistemeAI2/Fireball-Mistral-Nemo-12B-Philos</a></li>
|
||||
<li><a href="https://huggingface.co/EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math">EpistemeAI/Mistral-Nemo-Instruct-12B-Philosophy-Math</a></li>
|
||||
<li><a href="https://huggingface.co/Fizzarolli/MN-12b-Rosier-v1">Fizzarolli/MN-12b-Rosier-v1</a></li>
|
||||
<li><a href="https://huggingface.co/HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407">HumanLLMs/Human-Like-Mistral-Nemo-Instruct-2407</a></li>
|
||||
<li><a href="https://huggingface.co/IIEleven11/Kalypso">IIEleven11/Kalypso</a></li>
|
||||
<li><a href="https://huggingface.co/intervitens/mini-magnum-12b-v1.1">intervitens/mini-magnum-12b-v1.1</a></li>
|
||||
<li><a href="https://huggingface.co/jtatman/mistral_nemo_12b_reasoning_psychology_lora">jtatman/mistral_nemo_12b_reasoning_psychology_lora</a></li>
|
||||
<li><a href="https://huggingface.co/KOOWEEYUS/BlackSheep-RP-12B">KOOWEEYUS/BlackSheep-RP-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Lambent/Arsenic-Shahrazad-12B-v2">Lambent/Arsenic-Shahrazad-12B-v2</a></li>
|
||||
<li><a href="https://huggingface.co/Lambent/Arsenic-Shahrazad-12B-v3">Lambent/Arsenic-Shahrazad-12B-v3</a></li>
|
||||
<li><a href="https://huggingface.co/Lambent/arsenic-nemo-unleashed-12B">Lambent/arsenic-nemo-unleashed-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Lambent/Gilded-Arsenic-12B">Lambent/Gilded-Arsenic-12B</a></li>
|
||||
<li><a href="https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407">mistralai/Mistral-Nemo-Instruct-2407</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/Lyra-Gutenberg-mistral-nemo-12B">nbeerbower/Lyra-Gutenberg-mistral-nemo-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/Lyra4-Gutenberg-12B">nbeerbower/Lyra4-Gutenberg-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/mistral-nemo-bophades-12B">nbeerbower/mistral-nemo-bophades-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v3">nbeerbower/mistral-nemo-gutenberg-12B-v3</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v4">nbeerbower/mistral-nemo-gutenberg-12B-v4</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B">nbeerbower/Mistral-Nemo-Gutenberg-Doppel-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Encore-12B">nbeerbower/Mistral-Nemo-Gutenberg-Encore-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B">nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nbeerbower/mistral-nemo-wissenschaft-12B">nbeerbower/mistral-nemo-wissenschaft-12B</a></li>
|
||||
<li><a href="https://huggingface.co/NeverSleepHistorical/lumi-nemo-e2.0">NeverSleepHistorical/lumi-nemo-e2.0</a></li>
|
||||
<li><a href="https://huggingface.co/NeverSleep/Lumimaid-v0.2-12B">NeverSleep/Lumimaid-v0.2-12B</a></li>
|
||||
<li><a href="https://huggingface.co/nothingiisreal/Celeste-12B-V1.6">nothingiisreal/Celeste-12B-V1.6</a></li>
|
||||
<li><a href="https://huggingface.co/nothingiisreal/MN-12B-Celeste-V1.9">nothingiisreal/MN-12B-Celeste-V1.9</a></li>
|
||||
<li><a href="https://huggingface.co/PocketDoc/Dans-DangerousWinds-V1.1.0-12b">PocketDoc/Dans-DangerousWinds-V1.1.0-12b</a></li>
|
||||
<li><a href="https://huggingface.co/ReadyArt/Dark-Nexus-12B-v2.0">ReadyArt/Dark-Nexus-12B-v2.0</a></li>
|
||||
<li><a href="https://huggingface.co/ReadyArt/Forgotten-Safeword-12B-v4.0">ReadyArt/Forgotten-Safeword-12B-v4.0</a></li>
|
||||
<li><a href="https://huggingface.co/ReadyArt/Omega-Darker_The-Final-Directive-12B">ReadyArt/Omega-Darker_The-Final-Directive-12B</a></li>
|
||||
<li><a href="https://huggingface.co/romaingrx/red-teamer-mistral-nemo">romaingrx/red-teamer-mistral-nemo</a></li>
|
||||
<li><a href="https://huggingface.co/Sao10K/MN-12B-Lyra-v1">Sao10K/MN-12B-Lyra-v1</a></li>
|
||||
<li><a href="https://huggingface.co/Sao10K/MN-12B-Lyra-v4">Sao10K/MN-12B-Lyra-v4</a></li>
|
||||
<li><a href="https://huggingface.co/shisa-ai/shisa-v2-mistral-nemo-12b">shisa-ai/shisa-v2-mistral-nemo-12b</a></li>
|
||||
<li><a href="https://huggingface.co/sleepdeprived3/Christian-Bible-Expert-v2.0-12B">sleepdeprived3/Christian-Bible-Expert-v2.0-12B</a></li>
|
||||
<li><a href="https://huggingface.co/SuperbEmphasis/MN-12b-RP-Ink-RP-Longform">SuperbEmphasis/MN-12b-RP-Ink-RP-Longform</a></li>
|
||||
<li><a href="https://huggingface.co/SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2">SuperbEmphasis/Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2</a></li>
|
||||
<li><a href="https://huggingface.co/TheDrummer/Rivermind-12B-v1">TheDrummer/Rivermind-12B-v1</a></li>
|
||||
<li><a href="https://huggingface.co/TheDrummer/Rocinante-12B-v1">TheDrummer/Rocinante-12B-v1</a></li>
|
||||
<li><a href="https://huggingface.co/TheDrummer/Rocinante-X-12B-v1">TheDrummer/Rocinante-X-12B-v1</a></li>
|
||||
<li><a href="https://huggingface.co/Trappu/Nemo-Picaro-12B">Trappu/Nemo-Picaro-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Undi95/LocalC-12B-e2.0">Undi95/LocalC-12B-e2.0</a></li>
|
||||
<li><a href="https://huggingface.co/VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct">VAGOsolutions/SauerkrautLM-Nemo-12b-Instruct</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">Configuration</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
The following YAML configuration was used to produce this model:
|
||||
<pre style="font-family: monospace; white-space: pre; margin: 0;"><code>base_model: B:/12B/models--mistralai--Mistral-Nemo-Instruct-2407
|
||||
models:
|
||||
- model: B:/12B/models--aixonlab--Aether-12b
|
||||
- model: B:/12B/models--aixonlab--Zinakha-12b
|
||||
- model: B:/12B/models--allura-org--Bigger-Body-12b
|
||||
- model: B:/12B/models--allura-org--MN-12b-RP-Ink
|
||||
- model: B:/12B/models--allura-org--remnant-mn-12b
|
||||
- model: B:/12B/models--anthracite-org--magnum-v4-12b
|
||||
- model: B:/12B/models--ArliAI--Mistral-Nemo-12B-ArliAI-RPMax-v1.2
|
||||
- model: B:/12B/models--Babsie--Opulus-12B-v3
|
||||
- model: B:/12B/models--BeaverAI--mistral-doryV2-12b
|
||||
- model: B:/12B/models--crestf411--nemo-sunfall-v0.6.1
|
||||
- model: B:/12B/models--EpistemeAI2--Fireball-Mistral-Nemo-12B-Philos
|
||||
- model: B:/12B/models--EpistemeAI--Mistral-Nemo-Instruct-12B-Philosophy-Math
|
||||
- model: B:/12B/models--Fizzarolli--MN-12b-Rosier-v1
|
||||
- model: B:/12B/models--HumanLLMs--Human-Like-Mistral-Nemo-Instruct-2407
|
||||
- model: B:/12B/models--IIEleven11--Kalypso
|
||||
- model: B:/12B/models--intervitens--mini-magnum-12b-v1.1
|
||||
- model: B:/12B/models--jtatman--mistral_nemo_12b_reasoning_psychology_lora
|
||||
- model: B:/12B/models--KOOWEEYUS--BlackSheep-RP-12B
|
||||
- model: B:/12B/models--Lambent--Arsenic-Shahrazad-12B-v2
|
||||
- model: B:/12B/models--Lambent--Arsenic-Shahrazad-12B-v3
|
||||
- model: B:/12B/models--Lambent--arsenic-nemo-unleashed-12B
|
||||
- model: B:/12B/models--Lambent--Gilded-Arsenic-12B
|
||||
- model: B:/12B/models--mistralai--Mistral-Nemo-Instruct-2407
|
||||
- model: B:/12B/models--nbeerbower--Lyra-Gutenberg-mistral-nemo-12B
|
||||
- model: B:/12B/models--nbeerbower--Lyra4-Gutenberg-12B
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-bophades-12B
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-gutenberg-12B-v3
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-gutenberg-12B-v4
|
||||
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Doppel-12B
|
||||
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Encore-12B
|
||||
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Vitus-12B
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-wissenschaft-12B
|
||||
- model: B:/12B/models--NeverSleepHistorical--lumi-nemo-e2.0
|
||||
- model: B:/12B/models--NeverSleep--Lumimaid-v0.2-12B
|
||||
- model: B:/12B/models--nothingiisreal--Celeste-12B-V1.6
|
||||
- model: B:/12B/models--nothingiisreal--MN-12B-Celeste-V1.9
|
||||
- model: B:/12B/models--PocketDoc--Dans-DangerousWinds-V1.1.0-12b
|
||||
- model: B:/12B/models--ReadyArt--Dark-Nexus-12B-v2.0
|
||||
- model: B:/12B/models--ReadyArt--Forgotten-Safeword-12B-v4.0
|
||||
- model: B:/12B/models--ReadyArt--Omega-Darker_The-Final-Directive-12B
|
||||
- model: B:/12B/models--romaingrx--red-teamer-mistral-nemo
|
||||
- model: B:/12B/models--Sao10K--MN-12B-Lyra-v1
|
||||
- model: B:/12B/models--Sao10K--MN-12B-Lyra-v4
|
||||
- model: B:/12B/models--shisa-ai--shisa-v2-mistral-nemo-12b
|
||||
- model: B:/12B/models--sleepdeprived3--Christian-Bible-Expert-v2.0-12B
|
||||
- model: B:/12B/models--SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||
- model: B:/12B/models--SuperbEmphasis--Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2
|
||||
- model: B:/12B/models--TheDrummer--Rivermind-12B-v1
|
||||
- model: B:/12B/models--TheDrummer--Rocinante-12B-v1
|
||||
- model: B:/12B/models--TheDrummer--Rocinante-X-12B-v1
|
||||
- model: B:/12B/models--Trappu--Nemo-Picaro-12B
|
||||
- model: B:/12B/models--Undi95--LocalC-12B-e2.0
|
||||
- model: B:/12B/models--VAGOsolutions--SauerkrautLM-Nemo-12b-Instruct
|
||||
merge_method: karcher
|
||||
parameters:
|
||||
max_iter: 500
|
||||
tol: 1.0e-9
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
name: 🦑 Kraken-Karcher-12B-v1</code></pre>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">Audits</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
<div style="margin-bottom: 20px;">
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/qm3LoFB7i638XHj6jV_gT.png">
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/kHtF4ooziZj3JDtz17eJx.png">
|
||||
<h3 class="subheading">Magnitude Analysis & Data Points</h3>
|
||||
<pre style="font-size: 0.85rem; overflow-x: auto;"><code>ID | Status | Delta Norm | Orig Size | Model Name
|
||||
----------------------------------------------------------------------------------------------------
|
||||
#1 | OK | 1.6926 | 74448896 | models--aixonlab--Aether-12b
|
||||
#2 | OK | 2.4361 | 74448896 | models--aixonlab--Zinakha-12b
|
||||
#3 | OK | 0.0407 | 74448896 | models--allura-org--Bigger-Body-12b
|
||||
#4 | OK | 1.6611 | 74448896 | models--allura-org--MN-12b-RP-Ink
|
||||
#5 | OK | 0.0866 | 74449920 | models--allura-org--remnant-mn-12b
|
||||
#6 | OK | 1.5070 | 74448896 | models--anthracite-org--magnum-v4-12b
|
||||
#7 | OK | 0.7476 | 74448896 | models--ArliAI--Mistral-Nemo-12B-ArliAI-RPMax-v1.2
|
||||
#8 | OK | 4.6310 | 74448896 | models--Babsie--Opulus-12B-v3
|
||||
#9 | HIGH MAG | 5.2080 | 74448896 | models--BeaverAI--mistral-doryV2-12b
|
||||
#10 | OK | 0.3196 | 74448896 | models--crestf411--nemo-sunfall-v0.6.1
|
||||
#11 | HIGH MAG | 5.7044 | 74448896 | models--EpistemeAI2--Fireball-Mistral-Nemo-12B-Philos
|
||||
#12 | OK | 2.3099 | 74448896 | models--EpistemeAI--Mistral-Nemo-Instruct-12B-Philosophy-Math
|
||||
#13 | HIGH MAG | 5.2074 | 74448896 | models--Fizzarolli--MN-12b-Rosier-v1
|
||||
#14 | OK | 0.0452 | 74448896 | models--HumanLLMs--Human-Like-Mistral-Nemo-Instruct-2407
|
||||
#15 | OK | 1.6716 | 74448896 | models--IIEleven11--Kalypso
|
||||
#16 | HIGH MAG | 5.1134 | 74449408 | models--intervitens--mini-magnum-12b-v1.1
|
||||
#17 | OK | 2.0833 | 74448896 | models--jtatman--mistral_nemo_12b_reasoning_psychology_lora
|
||||
#18 | OK | 2.9633 | 74448896 | models--KOOWEEYUS--BlackSheep-RP-12B
|
||||
#19 | OK | 2.8456 | 74448896 | models--Lambent--Arsenic-Shahrazad-12B-v2
|
||||
#20 | OK | 2.8456 | 74448896 | models--Lambent--Arsenic-Shahrazad-12B-v3
|
||||
#21 | OK | 2.8456 | 74448896 | models--Lambent--arsenic-nemo-unleashed-12B
|
||||
#22 | OK | 2.8461 | 74448896 | models--Lambent--Gilded-Arsenic-12B
|
||||
#23 | OK | 0.0000 | 74448896 | models--mistralai--Mistral-Nemo-Instruct-2407
|
||||
#24 | OK | 3.8395 | 74448896 | models--nbeerbower--Lyra-Gutenberg-mistral-nemo-12B
|
||||
#25 | OK | 0.4548 | 74448896 | models--nbeerbower--Lyra4-Gutenberg-12B
|
||||
#26 | OK | 0.0451 | 74448896 | models--nbeerbower--mistral-nemo-bophades-12B
|
||||
#27 | HIGH MAG | 5.1134 | 74449408 | models--nbeerbower--mistral-nemo-gutenberg-12B-v3
|
||||
#28 | OK | 1.9967 | 74448896 | models--nbeerbower--mistral-nemo-gutenberg-12B-v4
|
||||
#29 | OK | 0.0272 | 74448896 | models--nbeerbower--Mistral-Nemo-Gutenberg-Doppel-12B
|
||||
#30 | OK | 0.0350 | 74448896 | models--nbeerbower--Mistral-Nemo-Gutenberg-Encore-12B
|
||||
#31 | OK | 0.0501 | 74448896 | models--nbeerbower--Mistral-Nemo-Gutenberg-Vitus-12B
|
||||
#32 | OK | 0.0353 | 74448896 | models--nbeerbower--mistral-nemo-wissenschaft-12B
|
||||
#33 | HIGH MAG | 5.1626 | 74449408 | models--NeverSleepHistorical--lumi-nemo-e2.0
|
||||
#34 | HIGH MAG | 5.1647 | 74449408 | models--NeverSleep--Lumimaid-v0.2-12B
|
||||
#35 | OK | 0.0208 | 74448896 | models--nothingiisreal--Celeste-12B-V1.6
|
||||
#36 | OK | 4.1274 | 74448896 | models--nothingiisreal--MN-12B-Celeste-V1.9
|
||||
#37 | HIGH MAG | 5.4769 | 74448896 | models--PocketDoc--Dans-DangerousWinds-V1.1.0-12b
|
||||
#38 | OK | 2.4160 | 74448896 | models--ReadyArt--Dark-Nexus-12B-v2.0
|
||||
#39 | OK | 2.4154 | 74448896 | models--ReadyArt--Forgotten-Safeword-12B-v4.0
|
||||
#40 | OK | 0.0281 | 74448896 | models--ReadyArt--Omega-Darker_The-Final-Directive-12B
|
||||
#41 | OK | 0.0000 | 74448896 | models--romaingrx--red-teamer-mistral-nemo
|
||||
#42 | OK | 3.8395 | 74448896 | models--Sao10K--MN-12B-Lyra-v1
|
||||
#43 | OK | 0.4543 | 74448896 | models--Sao10K--MN-12B-Lyra-v4
|
||||
#44 | OK | 2.9147 | 74448896 | models--shisa-ai--shisa-v2-mistral-nemo-12b
|
||||
#45 | OK | 0.0123 | 74448896 | models--sleepdeprived3--Christian-Bible-Expert-v2.0-12B
|
||||
#46 | OK | 1.6650 | 74448896 | models--SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||
#47 | OK | 0.1050 | 74448896 | models--SuperbEmphasis--Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2
|
||||
#48 | OK | 1.6959 | 74448896 | models--TheDrummer--Rivermind-12B-v1
|
||||
#49 | OK | 1.9967 | 74448896 | models--TheDrummer--Rocinante-12B-v1
|
||||
#50 | OK | 2.2716 | 74448896 | models--TheDrummer--Rocinante-X-12B-v1
|
||||
#51 | OK | 4.4899 | 74448896 | models--Trappu--Nemo-Picaro-12B
|
||||
#52 | HIGH MAG | 5.1950 | 74448896 | models--Undi95--LocalC-12B-e2.0
|
||||
#53 | OK | 1.4549 | 74448896 | models--VAGOsolutions--SauerkrautLM-Nemo-12b-Instruct</code></pre>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
87
chat_template.jinja
Normal file
87
chat_template.jinja
Normal file
@@ -0,0 +1,87 @@
|
||||
{%- if messages[0]["role"] == "system" %}
|
||||
{%- set system_message = messages[0]["content"] %}
|
||||
{%- set loop_messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set loop_messages = messages %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
|
||||
|
||||
{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
|
||||
{%- set ns = namespace() %}
|
||||
{%- set ns.index = 0 %}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
|
||||
{%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
|
||||
{{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
|
||||
{%- endif %}
|
||||
{%- set ns.index = ns.index + 1 %}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
|
||||
{{- bos_token }}
|
||||
{%- for message in loop_messages %}
|
||||
{%- if message["role"] == "user" %}
|
||||
{%- if tools is not none and (message == user_messages[-1]) %}
|
||||
{{- "[AVAILABLE_TOOLS][" }}
|
||||
{%- for tool in tools %}
|
||||
{%- set tool = tool.function %}
|
||||
{{- '{"type": "function", "function": {' }}
|
||||
{%- for key, val in tool.items() if key != "return" %}
|
||||
{%- if val is string %}
|
||||
{{- '"' + key + '": "' + val + '"' }}
|
||||
{%- else %}
|
||||
{{- '"' + key + '": ' + val|tojson }}
|
||||
{%- endif %}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "}}" }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- "[/AVAILABLE_TOOLS]" }}
|
||||
{%- endif %}
|
||||
{%- if loop.last and system_message is defined %}
|
||||
{{- "[INST]" + system_message + "\n\n" + message["content"] + "[/INST]" }}
|
||||
{%- else %}
|
||||
{{- "[INST]" + message["content"] + "[/INST]" }}
|
||||
{%- endif %}
|
||||
{%- elif (message.tool_calls is defined and message.tool_calls is not none) %}
|
||||
{{- "[TOOL_CALLS][" }}
|
||||
{%- for tool_call in message.tool_calls %}
|
||||
{%- set out = tool_call.function|tojson %}
|
||||
{{- out[:-1] }}
|
||||
{%- if not tool_call.id is defined or tool_call.id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- ', "id": "' + tool_call.id + '"}' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- else %}
|
||||
{{- "]" + eos_token }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- elif message["role"] == "assistant" %}
|
||||
{{- message["content"] + eos_token}}
|
||||
{%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
|
||||
{%- if message.content is defined and message.content.content is defined %}
|
||||
{%- set content = message.content.content %}
|
||||
{%- else %}
|
||||
{%- set content = message.content %}
|
||||
{%- endif %}
|
||||
{{- '[TOOL_RESULTS]{"content": ' + content|string + ", " }}
|
||||
{%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
|
||||
{{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
|
||||
{%- endif %}
|
||||
{{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
|
||||
{%- else %}
|
||||
{{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"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": "4.57.6",
|
||||
"use_cache": true,
|
||||
"vocab_size": 131077
|
||||
}
|
||||
65
mergekit_config.yml
Normal file
65
mergekit_config.yml
Normal file
@@ -0,0 +1,65 @@
|
||||
base_model: B:/12B/models--mistralai--Mistral-Nemo-Instruct-2407
|
||||
models:
|
||||
- model: B:/12B/models--aixonlab--Aether-12b
|
||||
- model: B:/12B/models--aixonlab--Zinakha-12b
|
||||
- model: B:/12B/models--allura-org--Bigger-Body-12b
|
||||
- model: B:/12B/models--allura-org--MN-12b-RP-Ink
|
||||
- model: B:/12B/models--allura-org--remnant-mn-12b
|
||||
- model: B:/12B/models--anthracite-org--magnum-v4-12b
|
||||
- model: B:/12B/models--ArliAI--Mistral-Nemo-12B-ArliAI-RPMax-v1.2
|
||||
- model: B:/12B/models--Babsie--Opulus-12B-v3
|
||||
- model: B:/12B/models--BeaverAI--mistral-doryV2-12b
|
||||
- model: B:/12B/models--crestf411--nemo-sunfall-v0.6.1
|
||||
- model: B:/12B/models--EpistemeAI2--Fireball-Mistral-Nemo-12B-Philos
|
||||
- model: B:/12B/models--EpistemeAI--Mistral-Nemo-Instruct-12B-Philosophy-Math
|
||||
- model: B:/12B/models--Fizzarolli--MN-12b-Rosier-v1
|
||||
- model: B:/12B/models--HumanLLMs--Human-Like-Mistral-Nemo-Instruct-2407
|
||||
- model: B:/12B/models--IIEleven11--Kalypso
|
||||
- model: B:/12B/models--intervitens--mini-magnum-12b-v1.1
|
||||
- model: B:/12B/models--jtatman--mistral_nemo_12b_reasoning_psychology_lora
|
||||
- model: B:/12B/models--KOOWEEYUS--BlackSheep-RP-12B
|
||||
- model: B:/12B/models--Lambent--Arsenic-Shahrazad-12B-v2
|
||||
- model: B:/12B/models--Lambent--Arsenic-Shahrazad-12B-v3
|
||||
- model: B:/12B/models--Lambent--arsenic-nemo-unleashed-12B
|
||||
- model: B:/12B/models--Lambent--Gilded-Arsenic-12B
|
||||
- model: B:/12B/models--mistralai--Mistral-Nemo-Instruct-2407
|
||||
- model: B:/12B/models--nbeerbower--Lyra-Gutenberg-mistral-nemo-12B
|
||||
- model: B:/12B/models--nbeerbower--Lyra4-Gutenberg-12B
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-bophades-12B
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-gutenberg-12B-v3
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-gutenberg-12B-v4
|
||||
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Doppel-12B
|
||||
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Encore-12B
|
||||
- model: B:/12B/models--nbeerbower--Mistral-Nemo-Gutenberg-Vitus-12B
|
||||
- model: B:/12B/models--nbeerbower--mistral-nemo-wissenschaft-12B
|
||||
- model: B:/12B/models--NeverSleepHistorical--lumi-nemo-e2.0
|
||||
- model: B:/12B/models--NeverSleep--Lumimaid-v0.2-12B
|
||||
- model: B:/12B/models--nothingiisreal--Celeste-12B-V1.6
|
||||
- model: B:/12B/models--nothingiisreal--MN-12B-Celeste-V1.9
|
||||
- model: B:/12B/models--PocketDoc--Dans-DangerousWinds-V1.1.0-12b
|
||||
- model: B:/12B/models--ReadyArt--Dark-Nexus-12B-v2.0
|
||||
- model: B:/12B/models--ReadyArt--Forgotten-Safeword-12B-v4.0
|
||||
- model: B:/12B/models--ReadyArt--Omega-Darker_The-Final-Directive-12B
|
||||
- model: B:/12B/models--romaingrx--red-teamer-mistral-nemo
|
||||
- model: B:/12B/models--Sao10K--MN-12B-Lyra-v1
|
||||
- model: B:/12B/models--Sao10K--MN-12B-Lyra-v4
|
||||
- model: B:/12B/models--shisa-ai--shisa-v2-mistral-nemo-12b
|
||||
- model: B:/12B/models--sleepdeprived3--Christian-Bible-Expert-v2.0-12B
|
||||
- model: B:/12B/models--SuperbEmphasis--MN-12b-RP-Ink-RP-Longform
|
||||
- model: B:/12B/models--SuperbEmphasis--Omega-Darker_The-Final-Directive-Longform-Stage2-ERP-12B-v0.2
|
||||
- model: B:/12B/models--TheDrummer--Rivermind-12B-v1
|
||||
- model: B:/12B/models--TheDrummer--Rocinante-12B-v1
|
||||
- model: B:/12B/models--TheDrummer--Rocinante-X-12B-v1
|
||||
- model: B:/12B/models--Trappu--Nemo-Picaro-12B
|
||||
- model: B:/12B/models--Undi95--LocalC-12B-e2.0
|
||||
- model: B:/12B/models--VAGOsolutions--SauerkrautLM-Nemo-12b-Instruct
|
||||
merge_method: karcher
|
||||
parameters:
|
||||
max_iter: 500
|
||||
tol: 1.0e-9
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
name: 🦑 Kraken-Karcher-12B-v1
|
||||
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:fee388d05252e61e72da9db380e6dfd98b477e11100ea2288669bbf830fb8e75
|
||||
size 4865591736
|
||||
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:f32548b82dbbdfbceaf49a0f283f590669af1905ca5056b8deb7279ecd22d372
|
||||
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:ddd162f2476accbc9783d4e32a32ad55d88b4b062c24dd4bd2b9bba6384f8202
|
||||
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:abd5ebe91012c988fba7b203ee69afe88c1d17e839e1e44ff81b387d12564916
|
||||
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 sha256:5e269b4cdfc4f65896917ad81fcccfc20864308017367e493e7051abc6aa803e
|
||||
size 4907529392
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495667200,
|
||||
"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 sha256:1b2f85cc0f566b21e4830d3588cd905b728940bc44a10e7afacf35ab8c08e052
|
||||
size 17079235
|
||||
8059
tokenizer_config.json
Normal file
8059
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user