PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: PocketDoc/Dans-PersonalityEngine-V1.2.0-24b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-05 08:06:12 +08:00
commit 05920f3587
21 changed files with 10960 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
.gitattributes vendored Normal file
View File

@@ -0,0 +1,47 @@
*.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
resources/chub-black.gif filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text
model-00001-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00002-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00003-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00004-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00005-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00006-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00007-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00008-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00009-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text
model-00010-of-00010.safetensors filter=lfs diff=lfs merge=lfs -text

415
README.md Normal file
View File

@@ -0,0 +1,415 @@
---
thumbnail: >-
https://huggingface.co/PocketDoc/Dans-PersonalityEngine-V1.2.0-24b/resolve/main/resources/pe24.png
license: apache-2.0
tags:
- general-purpose
- roleplay
- storywriting
- chemistry
- biology
- code
- climate
- axolotl
- text-generation-inference
- finetune
datasets:
- PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
- AquaV/US-Army-Survival-Sharegpt
- AquaV/Multi-Environment-Operations-Sharegpt
- AquaV/Resistance-Sharegpt
- AquaV/Interrogation-Sharegpt
- AquaV/Chemical-Biological-Safety-Applications-Sharegpt
- AquaV/Energetic-Materials-Sharegpt
- PocketDoc/Dans-Mathmaxx
- PocketDoc/Dans-Mathmaxx-Numina-CoT
- PJMixers/Math-Multiturn-1K-ShareGPT
- PocketDoc/Dans-Benchmaxx-COT
- PocketDoc/Dans-Codemaxx-LeetCode
- PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations
- PocketDoc/Dans-Codemaxx-CodeFeedback-SingleTurn
- PocketDoc/Dans-Codemaxx-Bigcode-SelfInstruct
- PocketDoc/Dans-Taskmaxx
- PocketDoc/Dans-Taskmaxx-DataPrepper
- PocketDoc/Dans-Taskmaxx-ConcurrentQA-Reworked
- PocketDoc/Dans-Taskmaxx-TableGPT
- PocketDoc/Dans-Taskmaxx-SciRIFF
- PocketDoc/Dans-Taskmaxx-Edit
- PocketDoc/Dans-Toolmaxx-Agent
- PocketDoc/Dans-Toolmaxx-ShellCommands
- PocketDoc/Dans-Toolmaxx-Functions-Toolbench
- PocketDoc/Dans-Toolmaxx-Functions-ToolACE
- PocketDoc/Dans-ASCIIMaxx-Wordart
- PocketDoc/Dans-Prosemaxx-Gutenberg
- PocketDoc/Dans-Prosemaxx-Cowriter-3-XL
- PocketDoc/Dans-Prosemaxx-Adventure
- PocketDoc/Dans-Failuremaxx-Adventure-3
- PocketDoc/Dans-Prosemaxx-InstructWriter-ZeroShot-2
- PocketDoc/Dans-Prosemaxx-InstructWriter-Continue-2
- PocketDoc/Dans-Assistantmaxx-Sharegpt
- PocketDoc/Dans-Assistantmaxx-OpenAssistant2
- PocketDoc/Dans-Assistantmaxx-Opus-Merge
- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset
- PocketDoc/Dans-Assistantmaxx-sonnetorca-subset-2
- PocketDoc/Dans-Assistantmaxx-NoRobots
- PocketDoc/Dans-Assistantmaxx-Synthia
- PocketDoc/Dans-Assistantmaxx-ASL
- PocketDoc/Dans-Assistantmaxx-PersonaLLM-Opus
- PocketDoc/Dans-Assistantmaxx-UnnaturalInstructions-GPT4
- PocketDoc/Dans-Assistantmaxx-LongAlign
- PocketDoc/Dans-Assistantmaxx-EvolKit
- PocketDoc/Dans-Assistantmaxx-Camel-GPT4
- PocketDoc/Dans-Assistantmaxx-OpenLeecher-Instruct
- PocketDoc/Dans-Assistantmaxx-Tulu3-IF
- PocketDoc/Dans-Systemmaxx
- PocketDoc/Dans-Logicmaxx-Skunkworks
- PocketDoc/Dans-Logicmaxx-FI-VeriMed
- PocketDoc/Dans-Logicmaxx-SAT-AP
- PocketDoc/Dans-Logicmaxx-Magpie-Ultra
- PJMixers/grimulkan_theory-of-mind-ShareGPT
- PJMixers/grimulkan_physical-reasoning-ShareGPT
- PocketDoc/Dans-Personamaxx
- PocketDoc/Dans-Personamaxx-Rainy
- PocketDoc/Dans-Personamaxx-C1
- PocketDoc/Dans-Personamaxx-VN
language:
- en
base_model:
- mistralai/Mistral-Small-24B-Base-2501
pipeline_tag: text-generation
library_name: transformers
new_version: PocketDoc/Dans-PersonalityEngine-V1.3.0-24b
---
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
</head>
<div class="crt-container">
<div class="crt-case">
<div class="crt-inner-case">
<div class="crt-bezel">
<div class="terminal-screen">
<div style="text-align: center;">
<h2>Dans-PersonalityEngine-V1.2.0-24b</h2>
<pre class="code-block" style="display: inline-block; text-align: left; font-size: clamp(2px, 0.8vw, 14px); line-height: 1.2; max-width: 100%; overflow: hidden; white-space: pre;">
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⠀⠄⠀⡂⠀⠁⡄⢀⠁⢀⣈⡄⠌⠐⠠⠤⠄⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⡄⠆⠀⢠⠀⠛⣸⣄⣶⣾⡷⡾⠘⠃⢀⠀⣴⠀⡄⠰⢆⣠⠘⠰⠀⡀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠃⠀⡋⢀⣤⡿⠟⠋⠁⠀⡠⠤⢇⠋⠀⠈⠃⢀⠀⠈⡡⠤⠀⠀⠁⢄⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠁⡂⠀⠀⣀⣔⣧⠟⠋⠀⢀⡄⠀⠪⣀⡂⢁⠛⢆⠀⠀⠀⢎⢀⠄⢡⠢⠛⠠⡀⠀⠄⠀⠀
⠀⠀⡀⠡⢑⠌⠈⣧⣮⢾⢏⠁⠀⠀⡀⠠⠦⠈⠀⠞⠑⠁⠀⠀⢧⡄⠈⡜⠷⠒⢸⡇⠐⠇⠿⠈⣖⠂⠀
⠀⢌⠀⠤⠀⢠⣞⣾⡗⠁⠀⠈⠁⢨⡼⠀⠀⠀⢀⠀⣀⡤⣄⠄⠈⢻⡇⠀⠐⣠⠜⠑⠁⠀⣀⡔⡿⠨⡄
⠈⠂⠀⠆⠀⣼⣾⠟⠀⠑⠀⡐⠗⠉⠀⠐⠶⣤⡵⠋⠀⠠⠹⡌⡀⠘⠇⢠⣾⡣⣀⡴⠋⠅⠈⢊⠠⡱⡀
⠪⠑⢌⠂⣼⣿⡟⠀⠀⠙⠀⠀⠀⡀⠀⠀⠐⡞⡐⠀⠀⡧⠀⢀⠠⠀⣁⠾⡇⠀⠙⡁⠀⠀⢀⣨⣄⡠⢱
⣸⠈⠊⠙⣛⣿⡧⠔⠚⠛⠳⣄⣀⡬⠤⠬⠼⡣⠃⠀⢀⡗⠀⡤⠞⠙⠄⠂⠃⢀⣠⣤⠶⠙⠅⠁⠃⠋⠈
⢋⠼⣀⠰⢯⢿⠁⠀⢢⠀⠀⢐⠋⡀⠀⠈⠁⠀⣀⣰⠏⠒⠙⠈⠀⣀⡤⠞⢁⣼⠏⠘⢀⣀⢤⢤⡐⢈⠂
⠀⠢⠀⠀⠸⣿⡄⠲⠚⠘⠚⠃⢀⠀⠈⢋⠶⠛⠉⠉⢃⣀⢤⢾⠋⣁⡤⡚⠁⢹⠁⠠⢛⠠⠬⠁⢬⠀⠀
⠀⠈⢳⣒⠋⠉⣿⢐⠠⣀⣃⠀⠀⠉⠂⢁⣀⣀⡤⢞⠩⢑⡨⠰⡞⠁⠁⢀⡠⠾⠎⡈⡌⡈⡓⡀⠄⠀⠀
⠀⠀⠀⠉⠘⠃⢻⡒⠦⢼⣿⣛⣻⣿⡷⢄⣀⣀⣠⣴⢾⣿⣆⣡⡄⣠⣪⡿⣷⣾⣷⣧⡡⠅⣇⠍⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠙⠒⠒⠛⠛⠓⠉⢹⠀⣷⠴⣻⣽⡻⢧⢻⡿⡏⣼⢿⣻⢾⣿⣿⣿⡿⢠ ⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠂⠻⠨⠰⢋⡅⠉⣑⡇⡗⣿⢂⣸⡿⣿⣛⠿⠃⠁ ⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠳⣌⣙⣸⢧⣿⣕⣼⣇⢹⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣠⣸⢧⢟⢟⡟⣾⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⢰⠙⣾⡟⣻⡕⣹⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⢸⢰⡏⢠⡿⠾⠋⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⢸⠸⡇⡏⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠸⢸⢸⡇⡇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠘⠇⡇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
</pre>
</div>
<p>This model series is intended to be multifarious in its capabilities and should be quite capable at both co-writing and roleplay as well as find itself quite at home performing sentiment analysis or summarization as part of a pipeline.</p>
<p>It has been trained on a wide array of one shot instructions, multi turn instructions, tool use, role playing scenarios, text adventure games, co-writing, and much more.</p>
<h3>Key Details</h3>
<pre class="code-block">
BASE MODEL: mistralai/Mistral-Small-24B-Base-2501
LICENSE: apache-2.0
LANGUAGE: English
CONTEXT LENGTH: 32768 tokens</pre>
<a href="https://chub.ai/">
<img src="./resources/chub-black.gif" alt="Sponsored by Chub.AI" class="sponsor-image-small">
</a>
<h3>Recommended Settings</h3>
<pre class="code-block">
TEMPERATURE: 1.0
TOP_P: 0.95
MIN_P: 0.05</pre>
<h3>Prompting Format</h3>
<p>The model uses standard "ChatML" format:</p>
<pre class="code-block">
<|im_start|>system
system prompt<|im_end|>
<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|></pre>
A word of caution: As of Feb 19 2025 backends can't seem to agree on automatically addind a "bos" token to the start, which they should! I'm investigating if there is a way I can change the config to mitigate this but for now if you have incoherent outputs not typical of a 24b model (verbatim repeating what you said back to you for instance) then try adding "&lt;s&gt;" to the very beginning of your context.
<h3>SillyTavern Templates</h3>
<details>
<summary>Context Template</summary>
<pre class="code-block">
{
"story_string": "<|im_start|>system\n{{#if system}}{{system}}\n{{/if}}{{#if wiBefore}}{{wiBefore}}\n{{/if}}{{#if description}}{{description}}\n{{/if}}{{#if personality}}{{char}}'s personality: {{personality}}\n{{/if}}{{#if scenario}}Scenario: {{scenario}}\n{{/if}}{{#if wiAfter}}{{wiAfter}}\n{{/if}}{{#if persona}}{{persona}}\n{{/if}}{{trim}}<|im_end|>\n",
"example_separator": "",
"chat_start": "",
"use_stop_strings": false,
"allow_jailbreak": false,
"always_force_name2": false,
"trim_sentences": false,
"include_newline": false,
"single_line": false,
"name": "Dan-ChatML"
}</pre>
</details>
<details>
<summary>Instruct Template</summary>
<pre class="code-block">
{
"system_prompt": "Write {{char}}'s actions and dialogue, user will write {{user}}'s.",
"input_sequence": "<|im_start|>user\n",
"output_sequence": "<|im_start|>assistant\n",
"first_output_sequence": "",
"last_output_sequence": "",
"system_sequence_prefix": "",
"system_sequence_suffix": "",
"stop_sequence": "<|im_end|>",
"wrap": false,
"macro": true,
"names": false,
"names_force_groups": false,
"activation_regex": "",
"skip_examples": false,
"output_suffix": "<|im_end|>\n",
"input_suffix": "<|im_end|>\n",
"system_sequence": "<|im_start|>system\n",
"system_suffix": "<|im_end|>\n",
"user_alignment_message": "",
"last_system_sequence": "",
"system_same_as_user": false,
"first_input_sequence": "",
"last_input_sequence": "",
"name": "Dan-ChatML"
}</pre>
</details>
<h3>A Chub.AI Sponsored Model</h3>
<div>
<a href="https://chub.ai/">
<img src="./resources/chub-black.gif" alt="Sponsored by Chub.AI" class="sponsor-image">
</a>
</div>
<div>
<p>Character Hub supported this model with 65 hours on a 4x H200 144GB system. This is only some of what they've provided me for training and I am very grateful for their contributions, this model especially would have been difficult without it.</p>
<p>Character Hub has been supporting model development for quite a while now and they may be interested in your projects! Contact them through <a href="https://forms.gle/GSEZ388EkyYoe2Kz6">this google form</a>.</p>
</div>
<h3>Support Development</h3>
<p>Development is limited by funding and resources. To help support:</p>
<p>- Contact on HF</p>
<p>- Email: visuallyadequate@gmail.com</p>
<p class="coffee-container">
<a href="https://www.buymeacoffee.com/visually" target="_blank" rel="noopener noreferrer">
<img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" height="45" width="162">
</a>
</p>
</div>
</div>
</div>
</div>
</div>
<style>
@import url('https://fonts.googleapis.com/css2?family=VT323&display=swap');
.crt-container {
padding: 10px;
max-width: 1000px;
margin: 0 auto;
width: 95%;
}
.crt-case {
background: #e8d7c3;
border-radius: 10px;
padding: 15px;
box-shadow: inset -2px -2px 5px rgba(0,0,0,0.3), 2px 2px 5px rgba(0,0,0,0.2);
}
.crt-inner-case {
background: #e8d7c3;
border-radius: 8px;
padding: 3px;
box-shadow: inset -1px -1px 4px rgba(0,0,0,0.3), 1px 1px 4px rgba(0,0,0,0.2);
}
.crt-bezel {
background: linear-gradient(145deg, #1a1a1a, #2a2a2a);
padding: 15px;
border-radius: 5px;
border: 3px solid #0a0a0a;
position: relative;
box-shadow:
inset 0 0 20px rgba(0,0,0,0.5),
inset 0 0 4px rgba(0,0,0,0.4),
inset 2px 2px 4px rgba(255,255,255,0.05),
inset -2px -2px 4px rgba(0,0,0,0.8),
0 0 2px rgba(0,0,0,0.6),
-1px -1px 4px rgba(255,255,255,0.1),
1px 1px 4px rgba(0,0,0,0.3);
}
.crt-bezel::before {
content: '';
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: linear-gradient(45deg,
rgba(255,255,255,0.03) 0%,
rgba(255,255,255,0) 40%,
rgba(0,0,0,0.1) 60%,
rgba(0,0,0,0.2) 100%);
border-radius: 3px;
pointer-events: none;
}
.terminal-screen {
background: #111112;
padding: 20px;
border-radius: 15px;
position: relative;
overflow: hidden;
font-family: 'VT323', monospace;
font-size: clamp(12px, 1.5vw, 16px);
color: #e49b3e;
line-height: 1.4;
text-shadow: 0 0 2px #e49b3e;
animation: flicker 0.15s infinite;
filter: brightness(1.1) contrast(1.1);
box-shadow:
inset 0 0 30px rgba(0,0,0,0.9),
inset 0 0 8px rgba(0,0,0,0.8),
0 0 5px rgba(0,0,0,0.6);
max-width: 80ch;
margin: 0 auto;
}
.terminal-screen h2, .terminal-screen h3 {
font-size: clamp(16px, 2vw, 20px);
margin-bottom: 1em;
color: #e49b3e;
}
.terminal-screen pre.code-block {
font-size: clamp(10px, 1.3vw, 14px);
white-space: pre; /* Changed from pre-wrap to pre */
margin: 1em 0;
background-color: #1a1a1a;
padding: 1em;
border-radius: 4px;
color: #e49b3e;
overflow-x: auto; /* Added to enable horizontal scrolling */
}
.terminal-screen::before {
content: "";
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: linear-gradient(rgba(18, 16, 16, 0) 50%, rgba(0, 0, 0, 0.25) 50%), url('data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAADIAAAAyBAMAAADsEZWCAAAAGFBMVEUAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA4o8JoAAAAB3RSTlMAGwQIEQMYADcPzwAAACJJREFUKM9jYBgFo2AU0Beg+A8YMCLxGYZCbNQEo4BaAAD5TQiR5wU9vAAAAABJRU5ErkJggg==');
background-size: 100% 2.5px;
animation: scan 1s linear infinite;
pointer-events: none;
z-index: 2;
}
.terminal-screen::after {
content: "";
position: absolute;
top: 0;
left: 0;
right: 0;
bottom: 0;
background: radial-gradient(circle at center,
rgba(17, 17, 18, 0) 0%,
rgba(17, 17, 18, 0.2) 50%,
rgba(17, 17, 18, 0.15) 100%
);
border-radius: 20px;
animation: vignette-pulse 3s infinite;
pointer-events: none;
z-index: 1;
}
.terminal-screen details {
margin: 1em 0;
padding: 0.5em;
border: 1px solid #e49b3e;
border-radius: 4px;
}
.terminal-screen summary {
cursor: pointer;
font-weight: bold;
margin: -0.5em;
padding: 0.5em;
border-bottom: 1px solid #e49b3e;
color: #e49b3e;
}
.terminal-screen details[open] summary {
margin-bottom: 0.5em;
}
.badge-container, .coffee-container {
text-align: center;
margin: 1em 0;
}
.badge-container img, .coffee-container img {
max-width: 100%;
height: auto;
}
.terminal-screen a {
color: #e49b3e;
text-decoration: underline;
transition: opacity 0.2s;
}
.terminal-screen a:hover {
opacity: 0.8;
}
.terminal-screen strong, .terminal-screen em {
color: #f0f0f0; /* off-white color for user/system messages */
}
.terminal-screen p {
color: #f0f0f0; /* off-white color for assistant responses */
}
.terminal-screen p, .terminal-screen li {
color: #e49b3e;
}
.terminal-screen code,
.terminal-screen kbd,
.terminal-screen samp {
color: #e49b3e;
font-family: 'VT323', monospace;
text-shadow: 0 0 2px #e49b3e;
background-color: #1a1a1a;
padding: 0.2em 0.4em;
border-radius: 4px;
}
.terminal-screen pre.code-block,
.terminal-screen pre {
font-size: clamp(10px, 1.3vw, 14px);
white-space: pre; /* Changed from pre-wrap to pre */
margin: 1em 0;
background-color: #1a1a1a;
padding: 1em;
border-radius: 4px;
color: #e49b3e;
overflow-x: auto; /* Added to enable horizontal scrolling */
}
.sponsor-image {
width: 360px;
height: auto;
border: 2px solid #e49b3e;
border-radius: 10px;
filter: brightness(0.9) sepia(0.2);
transition: all 0.3s ease;
}
.sponsor-image-small {
width: 180px;
height: auto;
border: 2px solid #e49b3e;
border-radius: 5px;
filter: brightness(0.9) sepia(0.2);
transition: all 0.3s ease;
}
.sponsor-image:hover {
filter: brightness(1) sepia(0);
box-shadow: 0 0 10px rgba(228, 155, 62, 0.5);
}
</style>

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "Dans-DiscountModels/Mistral-Small-24B-Base-2501-ChatML",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 32768,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 40,
"num_key_value_heads": 8,
"pad_token_id": 11,
"rms_norm_eps": 1e-05,
"rope_theta": 100000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.48.3",
"unsloth_fixed": true,
"use_cache": false,
"vocab_size": 131072
}

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

9
generation_config.json Normal file
View File

@@ -0,0 +1,9 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"do_sample": true,
"eos_token_id": 2,
"max_length": 32768,
"pad_token_id": 11,
"transformers_version": "4.48.3"
}

3
model-00001-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:914de7628fb3904e01a97cdd2efded98d0d2c149b97f18b34c310bdae6eb42b4
size 4781571736

3
model-00002-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:90dcf48852258e8270c33da640eb851af88ec819a3a2d95b7c2dd2af9febf822
size 4781592784

3
model-00003-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e148ea055ba7ad9cdcccc8d21cd6a74b36e368f5208f8ebead3e6f14375653ae
size 4781592800

3
model-00004-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0b8acb8f8b0d7cde1ddf2a1e0f7ab89756dcda8796f75df3910ccf6b9b531a48
size 4886471600

3
model-00005-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d5f7c0b7050dc06be3ace1a9d553ca57572428abb47090f41ce1674b559d797b
size 4781592824

3
model-00006-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44cc27d75bd9d3318d1daf89e39d46d4ea6cbcf681e1e9c6598c141dc384b9ef
size 4781592816

3
model-00007-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:925f0894bd4787f6a9aee3f8f758007a5e914ccd0a497a4f32d35cd372884ea0
size 4886471600

3
model-00008-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7061c1673e285dd9070d78f948b755e61824feae1e1691acc08f5afdc4a3417b
size 4781592824

3
model-00009-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac548992f9ce29eae49925c82217d258478cf7ad03b49370a206f3f8ea2f3610
size 4781592816

3
model-00010-of-00010.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ac44f4d03d736ef9ba73b631a540b692739ab26fbebc75b588529079795e180d
size 3900777072

370
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 47144806400
},
"weight_map": {
"lm_head.weight": "model-00010-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-00003-of-00010.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
"model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
"model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
"model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
"model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
"model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
"model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
"model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
"model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
"model.norm.weight": "model-00010-of-00010.safetensors"
}
}

3
resources/chub-black.gif Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ce875d531f2b5f30eef7a9d397c3d09bb4f975326350dd8c4fc918be4a2f4114
size 1737755

BIN
resources/pe24.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 64 KiB

1032
special_tokens_map.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a045f4cbf73aaef9b0d11f0d566839f6e3100f1803f9815da53886f04124d7fa
size 17078059

9021
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff