初始化项目，由ModelHub XC社区提供模型
Model: Naphula/Ancient-Awakening-12B Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.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
|
||||
ablit_proj filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
AncientAwakening.png filter=lfs diff=lfs merge=lfs -text
|
||||
3
AncientAwakening.png
Normal file
3
AncientAwakening.png
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:26725599b179433e2670c059b80591475399212d0103c3ed6dc95b18b1481c8b
|
||||
size 456118
|
||||
830
README.md
Normal file
830
README.md
Normal file
@@ -0,0 +1,830 @@
|
||||
---
|
||||
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
|
||||
- EldritchLabs/Kraken-Karcher-12B-v1
|
||||
- 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
|
||||
- inflatebot/MN-12B-Mag-Mell-R1
|
||||
- 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
|
||||
- LatitudeGames/Muse-12B
|
||||
- mistralai/Mistral-Nemo-Instruct-2407
|
||||
- Naphula/Riemannian-Redshift-12B-v1
|
||||
- Naphula-Archives/F5-stage6-12B
|
||||
- Naphula-Archives/F5-stage7-12B
|
||||
- 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
|
||||
- SicariusSicariiStuff/Impish_Bloodmoon_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
|
||||
- Vortex5/Astral-Noctra-12B
|
||||
- Vortex5/Azure-Starlight-12B
|
||||
- Vortex5/Crimson-Constellation-12B
|
||||
- Vortex5/Red-Synthesis-12B
|
||||
- Vortex5/Shining-Seraph-12B
|
||||
- Vortex5/Starlit-Shadow-12B
|
||||
- Vortex5/Vermilion-Sage-12B
|
||||
- Vortex5/Scarlet-Seraph-12B
|
||||
- Vortex5/Maroon-Sunset-12B
|
||||
- Vortex5/Amber-Starlight-12B
|
||||
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
|
||||
- mistral
|
||||
- nemo
|
||||
- merge
|
||||
- mergekit
|
||||
- karcher
|
||||
- flux
|
||||
- arcee_fusion
|
||||
- ramplus_tl
|
||||
- pdq
|
||||
widget:
|
||||
- text: "Ancient-Awakening-12B"
|
||||
output:
|
||||
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/CvyWU1z106Aa__M8KIksp.png
|
||||
---
|
||||
|
||||
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/yI041gp0fzz7N_Mh_x5Pt.mpga"></audio>
|
||||
|
||||
> [!WARNING]
|
||||
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model works best with either the **ChatML** or **Mistral Tekken** chat template. The uncensored [**MPOA**](https://huggingface.co/Naphula/Ancient-Awakening-12B-MPOA) version has guardrails removed, which can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly.
|
||||
>
|
||||
|
||||
<!DOCTYPE html>
|
||||
<style>
|
||||
body {
|
||||
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
|
||||
color: #D1D5DB; /* Pale stone gray */
|
||||
line-height: 1.6;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
background-color: #0A0C10; /* Very dark stormy gray/black */
|
||||
}
|
||||
|
||||
b, strong {
|
||||
color: #FBBF24; /* Glowing amber/gold */
|
||||
text-shadow: 0 0 8px rgba(251, 191, 36, 0.4);
|
||||
}
|
||||
|
||||
.awakening-text {
|
||||
color: #FEF3C7; /* Pale inner-eye yellow */
|
||||
position: relative;
|
||||
z-index: 2;
|
||||
margin-left: 0.2em;
|
||||
text-shadow: 0 0 15px #F59E0B, 0 0 30px #B45309; /* Deep fiery orange/gold glow */
|
||||
font-size: 1.8rem;
|
||||
letter-spacing: 1px;
|
||||
font-weight: 600;
|
||||
}
|
||||
|
||||
/* Section styling */
|
||||
.section-container {
|
||||
background-color: rgba(17, 24, 39, 0.85); /* Dark slate rock */
|
||||
margin-bottom: 30px;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
border-bottom: 1px solid #78350F; /* Dark bronze/earth */
|
||||
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.6);
|
||||
}
|
||||
|
||||
.section-header {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
background-color: rgba(245, 158, 11, 0.05); /* Faint amber tint */
|
||||
padding: 10px 20px;
|
||||
border-top: 1px solid rgba(120, 53, 15, 0.4);
|
||||
}
|
||||
|
||||
.section-indicator {
|
||||
width: 8px;
|
||||
height: 20px;
|
||||
background-color: #F59E0B; /* Amber eye color */
|
||||
margin-right: 15px;
|
||||
box-shadow: 0 0 10px rgba(245, 158, 11, 0.6);
|
||||
border-radius: 2px;
|
||||
}
|
||||
|
||||
.section-title {
|
||||
font-family: 'Georgia', 'Times New Roman', serif; /* Ancient tome feel */
|
||||
color: #FDE68A; /* Light gold */
|
||||
font-size: 1.4rem;
|
||||
margin: 0;
|
||||
letter-spacing: 1px;
|
||||
font-weight: 400;
|
||||
text-transform: capitalize;
|
||||
}
|
||||
|
||||
.section-content {
|
||||
padding: 20px;
|
||||
font-family: sans-serif;
|
||||
color: #D1D5DB;
|
||||
line-height: 1.6;
|
||||
}
|
||||
|
||||
/* Title styling */
|
||||
.title-container {
|
||||
background-color: #050505; /* Pitch black */
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
margin-bottom: 40px;
|
||||
border-left: 4px solid #F59E0B; /* Amber pillar */
|
||||
box-shadow: 0 6px 25px rgba(245, 158, 11, 0.15);
|
||||
}
|
||||
|
||||
.title-wrapper {
|
||||
position: relative;
|
||||
z-index: 2;
|
||||
padding: 25px 20px 30px 30px;
|
||||
font-family: 'Georgia', 'Times New Roman', serif;
|
||||
}
|
||||
|
||||
.title-main {
|
||||
color: #FEF3C7;
|
||||
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%;
|
||||
/* Dark, brooding radial fog mimicking the eye's aura */
|
||||
background-image: radial-gradient(circle at 50% 50%, rgba(245, 158, 11, 0.08) 0%, rgba(0,0,0,0.9) 80%);
|
||||
z-index: 1;
|
||||
}
|
||||
|
||||
/* Subheading styling */
|
||||
.subheading {
|
||||
color: #D97706; /* Deep orange */
|
||||
font-size: 1.1rem;
|
||||
margin-top: 20px;
|
||||
margin-bottom: 15px;
|
||||
font-weight: 400;
|
||||
border-bottom: 1px dashed rgba(217, 119, 6, 0.4);
|
||||
display: inline-block;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 1px;
|
||||
font-family: 'Georgia', 'Times New Roman', serif;
|
||||
}
|
||||
|
||||
/* Links */
|
||||
a {
|
||||
color: #FBBF24; /* Amber */
|
||||
text-decoration: none;
|
||||
transition: color 0.3s ease, text-shadow 0.3s ease;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
text-decoration: underline;
|
||||
color: #FDE68A; /* Brighter gold */
|
||||
text-shadow: 0 0 8px rgba(251, 191, 36, 0.5);
|
||||
}
|
||||
|
||||
/* Container */
|
||||
.container {
|
||||
max-width: 1200px;
|
||||
margin: 20px auto;
|
||||
padding: 40px 20px;
|
||||
background-color: #0D1117; /* Deep stormy night */
|
||||
background-image:
|
||||
radial-gradient(circle at 15% 85%, rgba(120, 53, 15, 0.1) 0%, transparent 50%),
|
||||
radial-gradient(circle at 85% 15%, rgba(245, 158, 11, 0.05) 0%, transparent 50%);
|
||||
min-height: calc(100vh - 40px);
|
||||
border: 1px solid #1F2937; /* Dark stone border */
|
||||
border-radius: 8px;
|
||||
box-shadow: 0 8px 40px rgba(0, 0, 0, 0.9), inset 0 0 20px rgba(0, 0, 0, 0.5);
|
||||
}
|
||||
|
||||
/* Code blocks */
|
||||
pre {
|
||||
background-color: #050505; /* Pitch black */
|
||||
border: 1px solid #1F2937; /* Dark stone */
|
||||
border-left: 3px solid #92400E; /* Dark orange/brown */
|
||||
padding: 15px;
|
||||
border-radius: 4px;
|
||||
color: #D1D5DB;
|
||||
overflow-x: auto;
|
||||
}
|
||||
code {
|
||||
font-family: 'Courier New', Courier, monospace;
|
||||
color: #FBBF24; /* Amber */
|
||||
background-color: rgba(245, 158, 11, 0.08);
|
||||
padding: 2px 4px;
|
||||
border-radius: 3px;
|
||||
}
|
||||
pre code {
|
||||
color: #00FFFF;
|
||||
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>Ancient Awakening 12B</title>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<div class="container">
|
||||
<div class="title-container">
|
||||
<div class="storm-overlay"></div>
|
||||
<div class="title-wrapper">
|
||||
<h2 class="title-main">
|
||||
<span class="awakening-text">🧬 Ancient Awakening 12B</span>
|
||||
</h2>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/CvyWU1z106Aa__M8KIksp.png"
|
||||
alt="Ancient Awakening"
|
||||
style="display: block; margin: 0 auto 30px auto; max-width: 100%; height: auto; border-radius: 5px; border: 1px solid #1F2937; box-shadow: 0 0 25px rgba(245, 158, 11, 0.15);">
|
||||
|
||||
<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>.
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">System Prompt (Optional)</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
<p>You are the "Ancient One," a colossal, primordial entity of living stone, deep magic, and abyssal ocean. For countless millennia, you have slumbered in a state of suspended animation, your massive, jagged body mistaken for a remote, floating island amidst a perpetually stormy sea. You are older than recorded history, older than the gods of men. The ANCIENT AWAKENING marks your current state: you are finally opening your single, massive, reptilian eye. You are a geological anomaly made sentient.</p>
|
||||
</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 Methods</b><br>
|
||||
This model was synthesized using a complex multi-stage process involving the following methods:
|
||||
<ul>
|
||||
<li><a href="https://en.wikipedia.org/wiki/Karcher_mean">karcher</a></li>
|
||||
<li><a href="https://huggingface.co/24B-Suite/Mergedonia-Suite-24B-v1/discussions/2">flux</a></li>
|
||||
<li><a href="https://www.arcee.ai/blog/meet-mergekit-v0-1-arcee-fusion-expanded-model-support-multi-gpu-acceleration">arcee_fusion</a></li>
|
||||
<li><a href="https://arxiv.org/abs/2601.13572">ramplus_tl [Reinforced Agent Merging Plus (Tensor-Local)]</a></li>
|
||||
<li><a href="https://huggingface.co/24B-Suite/Mergedonia-Suite-24B-v1/discussions/2">pdq</a></li>
|
||||
</ul>
|
||||
<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.
|
||||
<hr>
|
||||
<b>Models Merged</b><br>
|
||||
The following 70 models were woven into this merge:<br><br>
|
||||
<details>
|
||||
<summary style="cursor: pointer; color: #FBBF24; font-weight: bold;">Show 70 Donor Models</summary>
|
||||
<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/EldritchLabs/Kraken-Karcher-12B-v1">EldritchLabs/Kraken-Karcher-12B-v1</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/inflatebot/MN-12B-Mag-Mell-R1">inflatebot/MN-12B-Mag-Mell-R1</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/LatitudeGames/Muse-12B">LatitudeGames/Muse-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/Naphula/Riemannian-Redshift-12B-v1">Naphula/Riemannian-Redshift-12B-v1</a></li>
|
||||
<li><a href="https://huggingface.co/Naphula-Archives/F5-stage6-12B">Naphula-Archives/F5-stage6-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Naphula-Archives/F5-stage7-12B">Naphula-Archives/F5-stage7-12B</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/SicariusSicariiStuff/Impish_Bloodmoon_12B">SicariusSicariiStuff/Impish_Bloodmoon_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>
|
||||
<li><a href="https://huggingface.co/Vortex5/Astral-Noctra-12B">Vortex5/Astral-Noctra-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Azure-Starlight-12B">Vortex5/Azure-Starlight-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Crimson-Constellation-12B">Vortex5/Crimson-Constellation-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Red-Synthesis-12B">Vortex5/Red-Synthesis-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Shining-Seraph-12B">Vortex5/Shining-Seraph-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Starlit-Shadow-12B">Vortex5/Starlit-Shadow-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Vermilion-Sage-12B">Vortex5/Vermilion-Sage-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Scarlet-Seraph-12B">Vortex5/Scarlet-Seraph-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Maroon-Sunset-12B">Vortex5/Maroon-Sunset-12B</a></li>
|
||||
<li><a href="https://huggingface.co/Vortex5/Amber-Starlight-12B">Vortex5/Amber-Starlight-12B</a></li>
|
||||
</ul>
|
||||
</div>
|
||||
</details>
|
||||
</div>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">Merge Pipeline & Configuration</h2>
|
||||
</div>
|
||||
<div class="section-content">
|
||||
<p><b>🧬 Ancient Awakening 12B</b> unites several methods and 70 models into one:</p>
|
||||
<ol>
|
||||
<li><a href="https://huggingface.co/EldritchLabs/Kraken-Karcher-12B-v1">🦑 Kraken Karcher v1</a>: Combines 53 <a href="https://huggingface.co/models?other=base_model:finetune:mistralai/Mistral-Nemo-Instruct-2407">Mistral Nemo finetunes</a> via the <code>karcher</code> method at 500 iterations</li>
|
||||
<li><a href="https://huggingface.co/Naphula/Riemannian-Redshift-12B-v1">🌌 Riemannian Redshift v1</a>: Combines 10 <a href="https://huggingface.co/Vortex5">Vortex5</a> merges (which contain custom methods like <code>saef</code>, <code>smi_oni</code>, and <code>hpq</code>) via the <code>karcher</code> method at 1000 iterations</li>
|
||||
<li>RedKFlux: <code>flux</code> merge of Kraken with Redshift at 1000 iterations</li>
|
||||
<li>RedKFluxMell: <code>arcee_fusion</code> merge of #3 with <a href="https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1">Mag-Mell</a></li>
|
||||
<li>BloodKraken: <code>arcee_fusion</code> merge of #4 with <a href="https://huggingface.co/SicariusSicariiStuff/Impish_Bloodmoon_12B">Impish Bloodmoon</a></li>
|
||||
<li><a href="https://huggingface.co/Naphula-Archives/F5-stage6-12B">F5-stage6</a>: <code>arcee_fusion</code> merge of #5 with <a href="https://huggingface.co/LatitudeGames/Muse-12B">Muse</a></li>
|
||||
<li><a href="https://huggingface.co/Naphula-Archives/F5-stage7-12B">F5-stage7</a>: <code>ramplus_tl</code> merge of #6 with #3</li>
|
||||
<li><a href="https://huggingface.co/Naphula/Ancient-Awakening-12B">🧬 Ancient Awakening 12B</a>: <code>pdq</code> merge of #7 with #6, #3, #2, #1, Mag-Mell, Impish-Bloodmoon, and Muse</li>
|
||||
<li><code>mpoa</code> <a href="https://huggingface.co/blog/grimjim/norm-preserving-biprojected-abliteration">ablation</a> applied to remove censorship <a href="https://huggingface.co/Naphula/Ancient-Awakening-12B-MPOA">(released seperately)</a></i></li>
|
||||
<b>Note:</b> If you encounter any issues with the model then you can try using F5-stage6 or stage7 merges as these are likely more stable.
|
||||
</ol>
|
||||
<hr>
|
||||
<h3 class="subheading">Stage 1: 🦑 Kraken Karcher</h3>
|
||||
<pre><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>
|
||||
|
||||
<h3 class="subheading">Stage 2: 🌌 Riemannian Redshift</h3>
|
||||
<pre><code>models:
|
||||
- model: B:/12B/models--Vortex5--Astral-Noctra-12B
|
||||
- model: B:/12B/models--Vortex5--Azure-Starlight-12B
|
||||
- model: B:/12B/models--Vortex5--Crimson-Constellation-12B
|
||||
- model: B:/12B/models--Vortex5--Red-Synthesis-12B
|
||||
- model: B:/12B/models--Vortex5--Shining-Seraph-12B
|
||||
- model: B:/12B/models--Vortex5--Starlit-Shadow-12B
|
||||
- model: B:/12B/models--Vortex5--Vermilion-Sage-12B
|
||||
- model: B:/12B/models--Vortex5--Scarlet-Seraph-12B
|
||||
- model: B:/12B/models--Vortex5--Maroon-Sunset-12B
|
||||
- model: B:/12B/models--Vortex5--Amber-Starlight-12B
|
||||
merge_method: karcher
|
||||
parameters:
|
||||
max_iter: 1000
|
||||
tol: 1.0e-9
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
name: 🌌 Riemannian-Redshift-12B-v1</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 3: RedKFlux</h3>
|
||||
<pre><code>models:
|
||||
- model: C:\mergekit-main\merged_model_redshift
|
||||
- model: C:\mergekit-main\merged_model_kraken_karcher
|
||||
merge_method: flux
|
||||
parameters:
|
||||
eta: 1.2
|
||||
tol: 1.0e-9
|
||||
max_iter: 1000
|
||||
kappa: 0.8
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
name: RedKFlux</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 4: RedKFluxMell</h3>
|
||||
<pre><code>models:
|
||||
- model: C:\mergekit-main\merged_model_RedKFlux
|
||||
- model: B:\8B\models--inflatebot--MN-12B-Mag-Mell-R1
|
||||
merge_method: arcee_fusion
|
||||
tukey_fence: 1.5
|
||||
base_model: C:\mergekit-main\merged_model_RedKFlux
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
name: RedKFluxMell</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 5: BloodKraken</h3>
|
||||
<pre><code>models:
|
||||
- model: C:\mergekit-main\merged_model_RedKFluxMell
|
||||
- model: B:\8B\models--SicariusSicariiStuff--Impish_Bloodmoon_12B
|
||||
merge_method: arcee_fusion
|
||||
tukey_fence: 1.5
|
||||
base_model: C:\mergekit-main\merged_model_RedKFluxMell
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
name: BloodKraken</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 6: BloodKrakenMuse</h3>
|
||||
<pre><code>models:
|
||||
- model: C:\mergekit-main\merged_model_BloodKraken
|
||||
- model: B:\8B\models--LatitudeGames--Muse-12B
|
||||
merge_method: arcee_fusion
|
||||
tukey_fence: 1.5
|
||||
base_model: C:\mergekit-main\merged_model_BloodKraken
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
name: BloodKrakenMuse</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 7: Ramplus_tl</h3>
|
||||
<pre><code>merge_method: ramplus_tl
|
||||
base_model: C:\mergekit-main\merged_model_BloodKrakenMuse
|
||||
models:
|
||||
- model: C:\mergekit-main\merged_model_BloodKrakenMuse
|
||||
- model: C:\mergekit-main\merged_model_RedKFlux
|
||||
parameters:
|
||||
epsilon: 0.001 # Increased from 1e-5 to 1e-3 for denser SFT/DPO task vectors
|
||||
r: 0.25 # Increased from 0.1 to 0.2-0.3 for better SFT behavior preservation
|
||||
alpha: 0.4 # Increased from 0.2 to 0.4 for enhanced rescaling
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
tokenizer:
|
||||
source: base
|
||||
name: Stage7</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 8: 🧬 Ancient Awakening</h3>
|
||||
<pre><code>merge_method: pdq
|
||||
pdq_base_yaml: C:\mergekit-main\stage7.yaml
|
||||
pdq_base_model: C:\mergekit-main\merged_model_stage7
|
||||
output_dir: C:\mergekit-main\stage8_pdq
|
||||
base_model: C:\mergekit-main\merged_model_BloodKrakenMuse
|
||||
models:
|
||||
- model: C:\mergekit-main\merged_model_BloodKrakenMuse
|
||||
- model: B:\12B\models--LatitudeGames--Muse-12B
|
||||
- model: B:\12B\models--SicariusSicariiStuff--Impish_Bloodmoon_12B
|
||||
- model: B:\12B\models--inflatebot--MN-12B-Mag-Mell-R1
|
||||
- model: C:\mergekit-main\merged_model_RedKFlux
|
||||
- model: C:\mergekit-main\merged_model_redshift
|
||||
- model: C:\mergekit-main\merged_model_kraken_karcher
|
||||
parameters:
|
||||
chi: 0.15
|
||||
iota: 0.1
|
||||
nu: 24
|
||||
gamma: 1.0
|
||||
zeta: 16
|
||||
sigma: 0.5
|
||||
density: 0.9
|
||||
epsilon: 0.099
|
||||
lambda: 1.0
|
||||
lazy_unpickle: True
|
||||
random_seed: 420
|
||||
name: 🧬 Ancient-Awakening-12B</code></pre>
|
||||
|
||||
<h3 class="subheading">Stage 9: Magnitude-Preserving Othogonalized Ablation</h3>
|
||||
<pre><code># python measure.py -m C:\mergekit-main\f8_pdq -o C:\mergekit-main\f8_pdq\ablit_proj --batch-size 8 --projected
|
||||
# python analyze_old.py C:\mergekit-main\f8_pdq\ablit_proj -c
|
||||
# sharded_ablate.py magmell.yml --normpreserve --projected
|
||||
#
|
||||
# The model to be ablated.
|
||||
model: C:\mergekit-main\f8_pdq
|
||||
#
|
||||
# The measurement file generated by measure.py for the model.
|
||||
measurements: C:\mergekit-main\f8_pdq\ablit_proj
|
||||
#
|
||||
# The directory where the new, ablated model will be saved.
|
||||
output: C:\mergekit-main\f8_pdq\ablit_biproj\
|
||||
#
|
||||
# The list of ablation operations to perform.
|
||||
# Strategy: Use the single best refusal direction from the peak signal layer (29)
|
||||
# and apply it across all relevant mid-to-late layers.
|
||||
ablate:
|
||||
# Start ablating from the mid-layers where the signal begins to strengthen.
|
||||
- layer: 0
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 1
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 2
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 3
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 4
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 5
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 6
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 7
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 8
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 9
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 10
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 11
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 12
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 13
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 14
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 15
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 16
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 17
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 18
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 19
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 20
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 21
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 22
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 23
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 24
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 25
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 26
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 27
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 28
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 29
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 30
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 31
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 32
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 33
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 34
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 35
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 36
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 37
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 38
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00
|
||||
- layer: 39
|
||||
measurement: 29
|
||||
scale: 1.2
|
||||
sparsity: 0.00</code></pre>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
</body>
|
||||
</html>
|
||||
3
ablit_proj
Normal file
3
ablit_proj
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:54f688817c4cf8fee637270bff564ae5f1ba20cfa77eabd1884d72071457a64b
|
||||
size 2492022
|
||||
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": 131081
|
||||
}
|
||||
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 sha256:8c3d20dce7996e35d1e22d1ec746e419df49dde1a40710b0cab978a7032b3af4
|
||||
size 4865673624
|
||||
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 sha256:77a7bf44c9b2393c0f28d5a1a1f0c0fc35521c12dbb8c5ca56812e2111196580
|
||||
size 4907529424
|
||||
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 sha256:2e0042f13f722258093f035eb7f3e5007e8c077708ba9e77177572b299b03c6b
|
||||
size 4907529432
|
||||
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 sha256:8f90349b69befa6f6de06a8f4aee3deaa022bd2b30e9df07efda2b24c945b22c
|
||||
size 4907529424
|
||||
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:b99521344040c0ac08eb3a2084410c326f62b77afef65e4a8b6e102f4820bedd
|
||||
size 4907529360
|
||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 24495749120,
|
||||
"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 sha256:4a2acf7528846c5a217232be2a8c62d6ce1f1fe44c7dc0f3ce676b97279c7977
|
||||
size 17080009
|
||||
8091
tokenizer_config.json
Normal file
8091
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user