初始化项目，由ModelHub XC社区提供模型
Model: DarkArtsForge/Asmodeus-24B-v1 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||||
|
asmodeus-24b-v1_illuminati_imatrix_v1.dat filter=lfs diff=lfs merge=lfs -text
|
||||||
331
README.md
Normal file
331
README.md
Normal file
@@ -0,0 +1,331 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
base_model:
|
||||||
|
- anthracite-core/Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||||
|
- TheDrummer/Magidonia-24B-v4.3
|
||||||
|
- TheDrummer/Precog-24B-v1
|
||||||
|
- zerofata/MS3.2-PaintedFantasy-v3-24B
|
||||||
|
- TheDrummer/Cydonia-24B-v4.3
|
||||||
|
- ReadyArt/4.2.0-Broken-Tutu-24b
|
||||||
|
- zerofata/MS3.2-PaintedFantasy-v2-24B
|
||||||
|
- Naphula/BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||||
|
- ReadyArt/Broken-Tutu-24B-Transgression-v2.0
|
||||||
|
- trashpanda-org/MS3.2-24B-Mullein-v2
|
||||||
|
- LatitudeGames/Hearthfire-24B
|
||||||
|
- TheDrummer/Cydonia-24B-v4.2.0
|
||||||
|
- TheDrummer/Magidonia-24B-v4.2.0
|
||||||
|
- ConicCat/Mistral-Small-3.2-AntiRep-24B
|
||||||
|
- Undi95/MistralThinker-v1.1
|
||||||
|
- CrucibleLab/M3.2-24B-Loki-V2
|
||||||
|
- Darkhn/M3.2-24B-Animus-V7.1
|
||||||
|
datasets:
|
||||||
|
- OccultAI/illuminati_imatrix_v1
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- DELLA
|
||||||
|
- merge
|
||||||
|
- mergekit
|
||||||
|
widget:
|
||||||
|
- text: "Asmodeus 24B v1"
|
||||||
|
output:
|
||||||
|
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/K5KFzT4cXkGYuwT91KtlY.jpeg
|
||||||
|
---
|
||||||
|
|
||||||
|
<audio controls src="https://ia601406.us.archive.org/8/items/12.-j.-s.-bach-toccata-and-fugue-in-d-minor-bwv-565-raymond-daveluy-organ/12.%20J.S.%20Bach%20Toccata%20And%20Fugue%20in%20D%20Minor%2C%20BWV%20565%20-%20Raymond%20Daveluy%2C%20Organ.mp3"></audio>
|
||||||
|
|
||||||
|
> [!CAUTION]
|
||||||
|
> <span style="color:red; font-weight:bold">⚠️ Warning:</span> This model can produce narratives and RP that contain violent and graphic erotic content. Adjust your system prompt accordingly, and use **Mistral Tekken** chat template.
|
||||||
|
>
|
||||||
|
|
||||||
|
<!DOCTYPE html>
|
||||||
|
<style>
|
||||||
|
@import url('https://fonts.googleapis.com/css2?family=Cinzel+Decorative:wght@700&family=Sorts+Mill+Goudy&display=swap');
|
||||||
|
|
||||||
|
body {
|
||||||
|
font-family: 'Sorts Mill Goudy', serif;
|
||||||
|
color: #D7CFC6; /* Bone White */
|
||||||
|
line-height: 1.6;
|
||||||
|
margin: 0;
|
||||||
|
padding: 40px 0; /* Added padding for glow effect */
|
||||||
|
background-color: #000000; /* Abyssal Black */
|
||||||
|
background-image: url('https://www.transparenttextures.com/patterns/cracks.png'); /* Subtle crack texture */
|
||||||
|
}
|
||||||
|
|
||||||
|
b, strong {
|
||||||
|
color: #FF4500; /* Searing Orange */
|
||||||
|
font-weight: bold;
|
||||||
|
}
|
||||||
|
|
||||||
|
.infernal-text {
|
||||||
|
font-family: 'Cinzel Decorative', cursive;
|
||||||
|
color: #FF4500; /* Searing Orange */
|
||||||
|
position: relative;
|
||||||
|
z-index: 2;
|
||||||
|
margin-left: 0.2em;
|
||||||
|
text-shadow: 0 0 20px #FF0000, 0 0 10px #FF4500;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Section styling */
|
||||||
|
.section-container {
|
||||||
|
background-color: rgba(10, 10, 10, 0.6); /* Darker, more transparent */
|
||||||
|
margin-bottom: 30px;
|
||||||
|
position: relative;
|
||||||
|
overflow: hidden;
|
||||||
|
border: 1px solid #4D1A00; /* Deep Ember Border */
|
||||||
|
border-radius: 2px;
|
||||||
|
box-shadow: 0 4px 15px rgba(0, 0, 0, 0.5);
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-header {
|
||||||
|
display: flex;
|
||||||
|
align-items: center;
|
||||||
|
background: linear-gradient(90deg, rgba(255, 69, 0, 0.25) 0%, rgba(10, 10, 10, 0) 100%);
|
||||||
|
padding: 10px 20px;
|
||||||
|
border-bottom: 1px solid #4D1A00;
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-indicator {
|
||||||
|
width: 8px;
|
||||||
|
height: 20px;
|
||||||
|
background-color: #FF4500;
|
||||||
|
margin-right: 15px;
|
||||||
|
box-shadow: 0 0 12px #FF0000;
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-title {
|
||||||
|
font-family: 'Cinzel Decorative', cursive;
|
||||||
|
color: #D7CFC6;
|
||||||
|
font-size: 1.4rem;
|
||||||
|
margin: 0;
|
||||||
|
letter-spacing: 1px;
|
||||||
|
font-weight: 700;
|
||||||
|
text-transform: capitalize;
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-content {
|
||||||
|
padding: 20px;
|
||||||
|
font-family: 'Sorts Mill Goudy', serif;
|
||||||
|
color: #D7CFC6;
|
||||||
|
line-height: 1.7;
|
||||||
|
}
|
||||||
|
|
||||||
|
.section-content pre code {
|
||||||
|
color: #FFB56E; /* Light Orange */
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Title styling */
|
||||||
|
.title-container {
|
||||||
|
background-color: #0A0A0A;
|
||||||
|
position: relative;
|
||||||
|
overflow: hidden;
|
||||||
|
margin-bottom: 40px;
|
||||||
|
border: 2px solid #FF4500;
|
||||||
|
box-shadow: 0 0 25px #FF4500
|
||||||
|
}
|
||||||
|
|
||||||
|
.title-wrapper {
|
||||||
|
position: relative;
|
||||||
|
z-index: 2;
|
||||||
|
padding: 25px 20px 30px 30px;
|
||||||
|
text-align: center;
|
||||||
|
}
|
||||||
|
|
||||||
|
.title-main {
|
||||||
|
color: #D7CFC6;
|
||||||
|
font-size: 1.8rem;
|
||||||
|
font-weight: 700;
|
||||||
|
margin: 0;
|
||||||
|
letter-spacing: 2px;
|
||||||
|
display: inline-block;
|
||||||
|
position: relative;
|
||||||
|
text-transform: uppercase;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Subheading styling */
|
||||||
|
.subheading {
|
||||||
|
font-family: 'Cinzel Decorative', cursive;
|
||||||
|
color: #FF8C42; /* Fiery Orange */
|
||||||
|
font-size: 1.1rem;
|
||||||
|
margin-top: 20px;
|
||||||
|
margin-bottom: 15px;
|
||||||
|
font-weight: 700;
|
||||||
|
border-bottom: 1px solid #5E2D14;
|
||||||
|
display: inline-block;
|
||||||
|
text-transform: uppercase;
|
||||||
|
letter-spacing: 1px;
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Links */
|
||||||
|
a {
|
||||||
|
color: #FF8C42;
|
||||||
|
text-decoration: none;
|
||||||
|
font-weight: bold;
|
||||||
|
}
|
||||||
|
|
||||||
|
a:hover {
|
||||||
|
text-decoration: underline;
|
||||||
|
color: #FFB56E; /* Light Orange on hover */
|
||||||
|
}
|
||||||
|
|
||||||
|
/* Container */
|
||||||
|
.container {
|
||||||
|
max-width: 1200px;
|
||||||
|
margin: 20px auto;
|
||||||
|
padding: 40px 20px;
|
||||||
|
background-color: #111111; /* Dark Charcoal */
|
||||||
|
min-height: calc(100vh - 120px); /* Adjusted for body padding */
|
||||||
|
border: 2px solid #FF4500;
|
||||||
|
border-radius: 4px;
|
||||||
|
box-shadow: 0 0 25px #FF4500;
|
||||||
|
}
|
||||||
|
|
||||||
|
</style>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||||
|
<title>Asmodeus-24B</title>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
|
||||||
|
<div class="container">
|
||||||
|
<div class="title-container">
|
||||||
|
<div class="title-wrapper">
|
||||||
|
<h1 class="title-main">
|
||||||
|
<span class="infernal-text">👺 Asmodeus 24B v1</span>
|
||||||
|
</h1>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/K5KFzT4cXkGYuwT91KtlY.jpeg" alt="Asmodeus" style="width:100%; border-radius: 2px; margin-bottom: 30px; border: 1px solid #4D1A00;">
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">Infernal Invocation</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
<b>“Once you introduce enough chaos, people will willingly abandon reason for the comfort of madness.” - Asmodeus</a></b><br><br>
|
||||||
|
This is a <b>fully uncensored and articulate</b> merge of pre-trained language models, summoned into existence with <a href="https://github.com/cg123/mergekit">mergekit</a>.<br><br>This model was merged using the following merge method: <a href="https://arxiv.org/abs/2406.11617">DELLA</a>.<br><br>Asmodeus synergistically combines the advanced intelligence of various Mistral finetunes with unrestricted prompt adherence, resulting in creative prose and roleplay. It also has a more natural writing style, preferring to use paragraphs like a normal person instead of spamming bullet point lists for everything.<br><br>
|
||||||
|
<b>Observations:</b>
|
||||||
|
<ul><li>Asmodeus has zero refusals. No jailbreaks or ablations are required. This model is capable of generating evil, graphic and NSFW content.</li>
|
||||||
|
<li><b>Top NSigma</b> set to <b>1.25</b> should improve creativity and quality.</li>
|
||||||
|
<li>See the <a href="https://huggingface.co/Naphula/Goetia-24B-v1.2">Goetia</a> page for additional recommended settings.</li>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/vPF3KMbjGgcN4QKOzCi72.png" alt="Asmodeus" style="width:100%; border-radius: 2px; margin-bottom: 30px; border: 1px solid #4D1A00;">
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">Hellforged Parameters</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
The following edict was used to forge this entity:
|
||||||
|
<pre style="font-family: 'Courier New', Courier, monospace; white-space: pre; margin: 0; background-color: rgba(0,0,0,0.4); padding: 15px; border-radius: 2px; border: 1px solid #4D1A00;"><code>architecture: MistralForCausalLM
|
||||||
|
models:
|
||||||
|
- model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||||
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--LatitudeGames--Hearthfire-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.2.0
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.2.0
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--ConicCat--Mistral-Small-3.2-AntiRep-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--Undi95--MistralThinker-v1.1
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V2
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
# Seed: 420
|
||||||
|
merge_method: della
|
||||||
|
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||||
|
parameters:
|
||||||
|
lambda: 1.0
|
||||||
|
normalize: false
|
||||||
|
int8_mask: false
|
||||||
|
dtype: float32
|
||||||
|
out_dtype: bfloat16
|
||||||
|
tokenizer:
|
||||||
|
source: union
|
||||||
|
chat_template: auto
|
||||||
|
name: 👺 Asmodeus-24B-v1</code></pre><br>
|
||||||
|
<b>Checkpoint GGUFs:</b><br>
|
||||||
|
Q6 GGUFs and yaml config archives for various checkpoint model tests.<br><br>
|
||||||
|
Download: <b><a href="https://huggingface.co/Naphula-Archives/Checkpoint-GGUFs">https://huggingface.co/Naphula-Archives/Checkpoint-GGUFs</a></b>
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/HNQItcWcV0ovQNTuRW2X5.jpeg" width=300></img>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
3
asmodeus-24b-v1_illuminati_imatrix_v1.dat
Normal file
3
asmodeus-24b-v1_illuminati_imatrix_v1.dat
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:10b54d3953544292cdc1fc2213804f823647f446cbd47765fafa0d59b66d69af
|
||||||
|
size 10003527
|
||||||
51
chat_template.jinja
Normal file
51
chat_template.jinja
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
{%- set today = strftime_now("%Y-%m-%d") %}
|
||||||
|
{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
|
||||||
|
|
||||||
|
{{- bos_token }}
|
||||||
|
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{%- if messages[0]['content'] is string %}
|
||||||
|
{%- set system_message = messages[0]['content'] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = messages[0]['content'][0]['text'] %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set loop_messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = default_system_message %}
|
||||||
|
{%- set loop_messages = messages %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||||
|
|
||||||
|
{%- for message in loop_messages %}
|
||||||
|
{%- if message['role'] == 'user' %}
|
||||||
|
{%- if message['content'] is string %}
|
||||||
|
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '[INST]' }}
|
||||||
|
{%- for block in message['content'] %}
|
||||||
|
{%- if block['type'] == 'text' %}
|
||||||
|
{{- block['text'] }}
|
||||||
|
{%- elif block['type'] in ['image', 'image_url'] %}
|
||||||
|
{{- '[IMG]' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception('Only text and image blocks are supported in message content!') }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '[/INST]' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message['role'] == 'system' %}
|
||||||
|
{%- if message['content'] is string %}
|
||||||
|
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message['role'] == 'assistant' %}
|
||||||
|
{%- if message['content'] is string %}
|
||||||
|
{{- message['content'] + eos_token }}
|
||||||
|
{%- else %}
|
||||||
|
{{- message['content'][0]['text'] + eos_token }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception('Only user, system and assistant roles are supported!') }}
|
||||||
|
{%- 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": 32768,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"model_type": "mistral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 1000000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.56.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 131078
|
||||||
|
}
|
||||||
96
mergekit_config.yml
Normal file
96
mergekit_config.yml
Normal file
@@ -0,0 +1,96 @@
|
|||||||
|
architecture: MistralForCausalLM
|
||||||
|
models:
|
||||||
|
- model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||||
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.3
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--ReadyArt--4.2.0-Broken-Tutu-24b
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v2-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.3
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Precog-24B-v1
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--zerofata--MS3.2-PaintedFantasy-v3-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!BeaverAI_Fallen-Mistral-Small-3.1-24B-v1e_textonly
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--ReadyArt--Broken-Tutu-24B-Transgression-v2.0
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--trashpanda-org--MS3.2-24B-Mullein-v2
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--LatitudeGames--Hearthfire-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Cydonia-24B-v4.2.0
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--TheDrummer--Magidonia-24B-v4.2.0
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--ConicCat--Mistral-Small-3.2-AntiRep-24B
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--Undi95--MistralThinker-v1.1
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--CrucibleLab--M3.2-24B-Loki-V2
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
- model: B:\24B\!models--Darkhn--M3.2-24B-Animus-V7.1
|
||||||
|
parameters:
|
||||||
|
density: 0.666
|
||||||
|
weight: 0.25
|
||||||
|
epsilon: 0.333
|
||||||
|
# Seed: 420
|
||||||
|
merge_method: della
|
||||||
|
base_model: B:\24B\!models--anthracite-core--Mistral-Small-3.2-24B-Instruct-2506-Text-Only
|
||||||
|
parameters:
|
||||||
|
lambda: 1.0
|
||||||
|
normalize: false
|
||||||
|
int8_mask: false
|
||||||
|
dtype: float32
|
||||||
|
out_dtype: bfloat16
|
||||||
|
tokenizer:
|
||||||
|
source: union
|
||||||
|
chat_template: auto
|
||||||
|
name: 👺 Asmodeus-24B-v1
|
||||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a884a49267fd274e7daae97955301be80b4dce376794a4535845496d05624811
|
||||||
|
size 4907512192
|
||||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:44918f79512684228a4813d77cab4f99c7beb8be6571f0f86087236951f470a7
|
||||||
|
size 4781592832
|
||||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:194f5ca7bff58f0a58ef19c58678724e9c86888d95e02d0a54ce93c74ca1ce2e
|
||||||
|
size 4781592816
|
||||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:576fd0c9a3fb17210248725530c07202629b82c22584f7aa475553cbca92ce31
|
||||||
|
size 4886471592
|
||||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:7f57513d2b66f35e6a5f4b4e28611395e57e9e3c2db5bc52748bf32fc05ac669
|
||||||
|
size 4781592832
|
||||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:f9db54b5f64e8dddcb45d005fdab9aa88dc2a808ddd54bf19e6d6f648291518c
|
||||||
|
size 4781592816
|
||||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:18fe05f0e7f310b2e2c4805b817bb18529819066cd7f0d21a61cb62d9a9f3ff6
|
||||||
|
size 4886471592
|
||||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:3d32a2494fad4d64b5090dbda2467c5bbeb1a89e2f6a65b3a6b92bffae1b4faf
|
||||||
|
size 4781592832
|
||||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b2773784d694af1f745fa5f4a3f421881e72a280d9c8778bc6c9121084f0ce6b
|
||||||
|
size 4781592800
|
||||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a510834c946674d6d2cfa8d9ecec8d796ad36e6faa8c25733da950c83179dcfe
|
||||||
|
size 3774959456
|
||||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 47144929280,
|
||||||
|
"mergekit_version": "0.1.4"
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.norm.weight": "model-00010-of-00010.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d945d3ba266e63c59b9df8e5739d77cac28c27f2192c70c703d8c19715c64a97
|
||||||
|
size 17079151
|
||||||
9067
tokenizer_config.json
Normal file
9067
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user