初始化项目，由ModelHub XC社区提供模型
Model: Naphula/Goetia-8B-v1 Source: Original Platform
This commit is contained in:
ModelHub XC
36
.gitattributes
vendored
Normal file
36
.gitattributes
vendored
Normal file
@@ -0,0 +1,36 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
BIN
8dare_B.png
Normal file
BIN
8dare_B.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 31 KiB |
393
README.md
Normal file
393
README.md
Normal file
@@ -0,0 +1,393 @@
|
||||
---
|
||||
base_model:
|
||||
- Babsie/ThetaBlackGorgon-8B
|
||||
- Bacon666/Athlon-8B-0.1
|
||||
- Naphula/Llamatron-8B-v1
|
||||
- DarkArtsForge/Raven-8B-v1
|
||||
- EldritchLabs/Cthulhu-8B-v1.4
|
||||
- HumanLLMs/Human-Like-LLama3-8B-Instruct
|
||||
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
|
||||
- OccultAI/Morpheus-8B-v3
|
||||
- Sao10K/L3-8B-Stheno-v3.2
|
||||
- SicariusSicariiStuff/Assistant_Pepe_8B
|
||||
- SicariusSicariiStuff/Impish_Mind_8B
|
||||
- TheDrummer/Anubis-Mini-8B-v1
|
||||
- TroyDoesAI/BlackSheep-X-Dolphin
|
||||
datasets:
|
||||
- DarkArtsForge/Poe_v1
|
||||
- EldritchLabs/Cthulhu_v1.4b
|
||||
- OccultAI/illuminati_imatrix_v1
|
||||
- OccultAI/Morpheus_1052
|
||||
- SicariusSicariiStuff/UBW_Tapestries
|
||||
language:
|
||||
- en
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- creative
|
||||
- creative writing
|
||||
- fiction writing
|
||||
- plot generation
|
||||
- sub-plot generation
|
||||
- fiction writing
|
||||
- story generation
|
||||
- scene continue
|
||||
- storytelling
|
||||
- fiction story
|
||||
- science fiction
|
||||
- romance
|
||||
- all genres
|
||||
- story
|
||||
- writing
|
||||
- vivid prosing
|
||||
- vivid writing
|
||||
- fiction
|
||||
- roleplaying
|
||||
- float32
|
||||
- swearing
|
||||
- rp
|
||||
- horror
|
||||
- dare_linear
|
||||
- llama
|
||||
- merge
|
||||
- mergekit
|
||||
widget:
|
||||
- text: "Goetia-8B-v1"
|
||||
output:
|
||||
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/DHbuh4efzjCGpxDUciZ_-.jpeg
|
||||
---
|
||||
|
||||
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/KcjosKamYjk9Qm18mAGQW.mpga"></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 **Llama 3** chat template.
|
||||
>
|
||||
|
||||
<!DOCTYPE html>
|
||||
<style>
|
||||
@import url('https://fonts.googleapis.com/css2?family=Crimson+Text:ital,wght@0,400;0,700;1,400&family=Uncial+Antiqua&display=swap');
|
||||
|
||||
body {
|
||||
font-family: 'Crimson Text', serif;
|
||||
color: #4A3F35; /* Faded Ink Brown */
|
||||
line-height: 1.6;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
background-color: #281E18; /* Dark Wood Desk */
|
||||
}
|
||||
|
||||
b, strong {
|
||||
color: #8C1C13; /* Crimson Seal */
|
||||
}
|
||||
|
||||
.grimoire-text {
|
||||
font-family: 'Uncial Antiqua', cursive;
|
||||
color: #3D352A; /* Dark Ink */
|
||||
position: relative;
|
||||
z-index: 2;
|
||||
margin-left: 0.2em;
|
||||
text-shadow: 0 0 10px #A49687;
|
||||
}
|
||||
|
||||
/* Section styling */
|
||||
.section-container {
|
||||
background-color: rgba(245, 235, 218, 0.05);
|
||||
margin-bottom: 30px;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
border-bottom: 1px solid rgba(140, 28, 19, 0.3); /* Faded Crimson Border */
|
||||
box-shadow: 0 4px 15px rgba(0, 0, 0, 0.2);
|
||||
}
|
||||
|
||||
.section-header {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
background-color: rgba(140, 28, 19, 0.06);
|
||||
padding: 10px 20px;
|
||||
}
|
||||
|
||||
.section-indicator {
|
||||
width: 8px;
|
||||
height: 20px;
|
||||
background-color: #8C1C13;
|
||||
margin-right: 15px;
|
||||
box-shadow: 0 0 8px rgba(140, 28, 19, 0.4);
|
||||
}
|
||||
|
||||
.section-title {
|
||||
font-family: 'Uncial Antiqua', cursive;
|
||||
color: #4A3F35;
|
||||
font-size: 1.4rem;
|
||||
margin: 0;
|
||||
letter-spacing: 1px;
|
||||
font-weight: 400;
|
||||
text-transform: capitalize;
|
||||
}
|
||||
|
||||
.section-content {
|
||||
padding: 20px;
|
||||
font-family: 'Crimson Text', serif;
|
||||
color: #4A3F35;
|
||||
line-height: 1.7;
|
||||
}
|
||||
|
||||
/* Title styling */
|
||||
.title-container {
|
||||
background-color: transparent;
|
||||
position: relative;
|
||||
overflow: hidden;
|
||||
margin-bottom: 40px;
|
||||
border-left: 3px solid #8C1C13;
|
||||
box-shadow: 0 6px 20px rgba(0, 0, 0, 0.2);
|
||||
}
|
||||
|
||||
.title-wrapper {
|
||||
position: relative;
|
||||
z-index: 2;
|
||||
padding: 25px 20px 30px 30px;
|
||||
}
|
||||
|
||||
.title-main {
|
||||
color: #3D352A;
|
||||
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: 'Uncial Antiqua', cursive;
|
||||
color: #7B5E4A; /* Lighter Ink Brown */
|
||||
font-size: 1.1rem;
|
||||
margin-top: 20px;
|
||||
margin-bottom: 15px;
|
||||
font-weight: 400;
|
||||
border-bottom: 1px dashed rgba(123, 94, 74, 0.4);
|
||||
display: inline-block;
|
||||
text-transform: uppercase;
|
||||
letter-spacing: 1px;
|
||||
}
|
||||
|
||||
/* Links */
|
||||
a {
|
||||
color: #7B5E4A;
|
||||
text-decoration: none;
|
||||
font-weight: bold;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
text-decoration: underline;
|
||||
color: #8C1C13; /* Crimson Seal on hover */
|
||||
}
|
||||
|
||||
/* List Styling - Goetia Icons */
|
||||
ul {
|
||||
list-style: none; /* CRITICAL: This hides the default marker causing the blue box */
|
||||
padding-left: 1.6em;
|
||||
}
|
||||
|
||||
ul li {
|
||||
position: relative;
|
||||
margin-bottom: 0.6em;
|
||||
}
|
||||
|
||||
ul li::before {
|
||||
content: "\26E7"; /* ⛧ Inverted Pentagram */
|
||||
|
||||
/* FALLBACK PROTECTION: */
|
||||
/* This ensures that if your main font lacks the symbol, it grabs it from the system/OS symbols */
|
||||
font-family: "Segoe UI Symbol", "Apple Symbols", "Noto Sans Symbols", "DejaVu Sans", sans-serif;
|
||||
|
||||
position: absolute;
|
||||
left: -1.4em;
|
||||
|
||||
/* Fiery Styling */
|
||||
color: #CC0000; /* Strong red base */
|
||||
font-size: 1.5rem; /* Larger */
|
||||
font-weight: normal; /* Icons often render cleaner without 'bold' at this size */
|
||||
top: -5px; /* Vertical alignment fix */
|
||||
|
||||
/* Static Fire Glow (No Animation/Low CPU cost) */
|
||||
/* Layer 1: Slight dark drop shadow for depth */
|
||||
/* Layer 2: Orange-red ambient glow */
|
||||
text-shadow: 1px 1px 1px rgba(0,0,0,0.4), 0 0 5px #FF5500;
|
||||
|
||||
background-color: transparent;
|
||||
}
|
||||
|
||||
/* Container */
|
||||
.container {
|
||||
max-width: 1200px;
|
||||
margin: 20px auto;
|
||||
padding: 40px 20px;
|
||||
background-color: #F5EBDA; /* Aged Parchment */
|
||||
background-image:
|
||||
radial-gradient(circle at 10% 10%, rgba(140, 28, 19, 0.04) 0%, transparent 50%),
|
||||
radial-gradient(circle at 90% 80%, rgba(61, 53, 42, 0.06) 0%, transparent 50%);
|
||||
min-height: calc(100vh - 40px);
|
||||
border: 1px solid #C8BBAA; /* Parchment Edge */
|
||||
border-radius: 3px;
|
||||
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.3);
|
||||
}
|
||||
|
||||
</style>
|
||||
<html lang="en">
|
||||
<head>
|
||||
<meta charset="UTF-8">
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||
<title>Goetia 8B v1</title>
|
||||
</head>
|
||||
<body>
|
||||
|
||||
<div class="container">
|
||||
<div class="title-container">
|
||||
<div class="title-wrapper">
|
||||
<h1 class="title-main">
|
||||
<span class="grimoire-text">📜 Goetia 8B v1</span>
|
||||
</h1>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/DHbuh4efzjCGpxDUciZ_-.jpeg" alt="Goetia Grimoire" style="width:100%; border-radius: 3px; margin-bottom: 30px; border: 1px solid #C8BBAA;">
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">🐙 The Lesser Key</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
|
||||
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
||||
|
||||
This model was merged using the [Linear DARE](https://arxiv.org/abs/2311.03099) merge method using aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored as a base.
|
||||
|
||||
<b>Goetia 8B v1</b> is fully uncensored, no ablation or jailbreaks are needed. The model is very creative for its size, and has quite an attitude. Here you can see the <a href="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/O5NIDmxgDX-jt20gHMPVe.png">merge audit</a> showing exact weight distribution.
|
||||
|
||||
This model is recommended for those who can't run the <a href="https://huggingface.co/collections/OccultAI/goetia">larger Goetias</a>, or who want a change of pace from the way Mistral writes. Increasing Temp and TopNSigma to 1.0 seems to help also.
|
||||
|
||||
`dare_linear` seems quite effective for Llama models in particular. It outperformed `della_linear` and `dare_ties` in my testing.
|
||||
|
||||
The following models were included in the merge:
|
||||
- aifeifei798/DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
|
||||
- Babsie/ThetaBlackGorgon-8B
|
||||
- Bacon666/Athlon-8B-0.1
|
||||
- Naphula/Llamatron-8B-v1
|
||||
- DarkArtsForge/Raven-8B-v1
|
||||
- EldritchLabs/Cthulhu-8B-v1.4
|
||||
- HumanLLMs/Human-Like-LLama3-8B-Instruct
|
||||
- NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS
|
||||
- OccultAI/Morpheus-8B-v3
|
||||
- Sao10K/L3-8B-Stheno-v3.2
|
||||
- SicariusSicariiStuff/Assistant_Pepe_8B
|
||||
- SicariusSicariiStuff/Impish_Mind_8B
|
||||
- TheDrummer/Anubis-Mini-8B-v1
|
||||
- TroyDoesAI/BlackSheep-X-Dolphin
|
||||
</font></div>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">🧙 OccultAI Sigil Magic</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/Qv78rwAtpMmaFTpCcELjQ.jpeg"></img>
|
||||
|
||||
### Configuration
|
||||
|
||||
The following YAML configuration was used to produce this model:
|
||||
|
||||
```yaml
|
||||
architecture: LlamaForCausalLM
|
||||
models:
|
||||
- model: A:\LLM\.cache\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
|
||||
- model: A:\LLM\.cache\8B\!models--SicariusSicariiStuff--Assistant_Pepe_8B
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: B:\8B\Morpheus_v3_prototype_526
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\Naphula_Llamatron-8B-v1
|
||||
parameters:
|
||||
weight: 0.25
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--SicariusSicariiStuff--Impish_Mind_8B
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--Sao10K--L3-8B-Stheno-v3.2
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: B:\8B\Cthulhu_v1.4
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: B:\8B\models--TheDrummer--Anubis-Mini-8B-v1
|
||||
parameters:
|
||||
weight: 0.2
|
||||
density: 0.8
|
||||
- model: B:\8B\Raven_v1
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: B:\8B\models--HumanLLMs--Human-Like-LLama3-8B-Instruct
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--NeverSleep--Llama-3-Lumimaid-8B-v0.1-OAS
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--TroyDoesAI--BlackSheep-X-Dolphin
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--Bacon666--Athlon-8B-0.1
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--Babsie--ThetaBlackGorgon-8B
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
merge_method: dare_linear
|
||||
base_model: A:\LLM\.cache\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
|
||||
parameters:
|
||||
lambda: 1.0
|
||||
normalize: false
|
||||
int8_mask: false
|
||||
rescale: true
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
name: 📜 Goetia-8B-v1
|
||||
```
|
||||
</font></div>
|
||||
</div>
|
||||
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/O5NIDmxgDX-jt20gHMPVe.png"></img>
|
||||
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/FOij6TMejipIERSHPtKQg.jpeg"></img>
|
||||
|
||||
<div class="section-container">
|
||||
<div class="section-header">
|
||||
<div class="section-indicator"></div>
|
||||
<h2 class="section-title">🕯️ Summon the Infernal — Invocation Ritual</h2>
|
||||
</div>
|
||||
<div class="section-content"><font face="verdana">
|
||||
|
||||
Experiment with these settings:
|
||||
|
||||
https://huggingface.co/datasets/Naphula/Updated_Settings
|
||||
|
||||
</font></div>
|
||||
</div>
|
||||
|
||||
</html>
|
||||
109
chat_template.jinja
Normal file
109
chat_template.jinja
Normal file
@@ -0,0 +1,109 @@
|
||||
{{- bos_token }}
|
||||
{%- if custom_tools is defined %}
|
||||
{%- set tools = custom_tools %}
|
||||
{%- endif %}
|
||||
{%- if not tools_in_user_message is defined %}
|
||||
{%- set tools_in_user_message = true %}
|
||||
{%- endif %}
|
||||
{%- if not date_string is defined %}
|
||||
{%- set date_string = "26 Jul 2024" %}
|
||||
{%- endif %}
|
||||
{%- if not tools is defined %}
|
||||
{%- set tools = none %}
|
||||
{%- endif %}
|
||||
|
||||
{#- This block extracts the system message, so we can slot it into the right place. #}
|
||||
{%- if messages[0]['role'] == 'system' %}
|
||||
{%- set system_message = messages[0]['content']|trim %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{%- set system_message = "" %}
|
||||
{%- endif %}
|
||||
|
||||
{#- System message + builtin tools #}
|
||||
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
||||
{%- if builtin_tools is defined or tools is not none %}
|
||||
{{- "Environment: ipython\n" }}
|
||||
{%- endif %}
|
||||
{%- if builtin_tools is defined %}
|
||||
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
||||
{%- endif %}
|
||||
{{- "Cutting Knowledge Date: December 2023\n" }}
|
||||
{{- "Today Date: " + date_string + "\n\n" }}
|
||||
{%- if tools is not none and not tools_in_user_message %}
|
||||
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.\n\n" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "\n\n" }}
|
||||
{%- endfor %}
|
||||
{%- endif %}
|
||||
{{- system_message }}
|
||||
{{- "<|eot_id|>" }}
|
||||
|
||||
{#- Custom tools are passed in a user message with some extra guidance #}
|
||||
{%- if tools_in_user_message and not tools is none %}
|
||||
{#- Extract the first user message so we can plug it in here #}
|
||||
{%- if messages | length != 0 %}
|
||||
{%- set first_user_message = messages[0]['content']|trim %}
|
||||
{%- set messages = messages[1:] %}
|
||||
{%- else %}
|
||||
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
||||
{%- endif %}
|
||||
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
||||
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
||||
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
||||
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
||||
{{- "Do not use variables.\n\n" }}
|
||||
{%- for t in tools %}
|
||||
{{- t | tojson(indent=4) }}
|
||||
{{- "\n\n" }}
|
||||
{%- endfor %}
|
||||
{{- first_user_message + "<|eot_id|>"}}
|
||||
{%- endif %}
|
||||
|
||||
{%- for message in messages %}
|
||||
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
||||
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
||||
{%- elif 'tool_calls' in message %}
|
||||
{%- if not message.tool_calls|length == 1 %}
|
||||
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
||||
{%- endif %}
|
||||
{%- set tool_call = message.tool_calls[0].function %}
|
||||
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
||||
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
||||
{{- arg_name + '="' + arg_val + '"' }}
|
||||
{%- if not loop.last %}
|
||||
{{- ", " }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{{- ")" }}
|
||||
{%- else %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
||||
{{- '{"name": "' + tool_call.name + '", ' }}
|
||||
{{- '"parameters": ' }}
|
||||
{{- tool_call.arguments | tojson }}
|
||||
{{- "}" }}
|
||||
{%- endif %}
|
||||
{%- if builtin_tools is defined %}
|
||||
{#- This means we're in ipython mode #}
|
||||
{{- "<|eom_id|>" }}
|
||||
{%- else %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- elif message.role == "tool" or message.role == "ipython" %}
|
||||
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
||||
{%- if message.content is mapping or message.content is iterable %}
|
||||
{{- message.content | tojson }}
|
||||
{%- else %}
|
||||
{{- message.content }}
|
||||
{%- endif %}
|
||||
{{- "<|eot_id|>" }}
|
||||
{%- endif %}
|
||||
{%- endfor %}
|
||||
{%- if add_generation_prompt %}
|
||||
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
||||
{%- endif %}
|
||||
39
config.json
Normal file
39
config.json
Normal file
@@ -0,0 +1,39 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": [
|
||||
128001,
|
||||
128008,
|
||||
128009
|
||||
],
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128269
|
||||
}
|
||||
68
mergekit_config.yml
Normal file
68
mergekit_config.yml
Normal file
@@ -0,0 +1,68 @@
|
||||
architecture: LlamaForCausalLM
|
||||
models:
|
||||
- model: A:\LLM\.cache\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
|
||||
- model: A:\LLM\.cache\8B\!models--SicariusSicariiStuff--Assistant_Pepe_8B
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: B:\8B\Morpheus_v3_prototype_526
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\Naphula_Llamatron-8B-v1
|
||||
parameters:
|
||||
weight: 0.25
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--SicariusSicariiStuff--Impish_Mind_8B
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--Sao10K--L3-8B-Stheno-v3.2
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: B:\8B\Cthulhu_v1.4
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: B:\8B\models--TheDrummer--Anubis-Mini-8B-v1
|
||||
parameters:
|
||||
weight: 0.2
|
||||
density: 0.8
|
||||
- model: B:\8B\Raven_v1
|
||||
parameters:
|
||||
weight: 0.4
|
||||
density: 0.8
|
||||
- model: B:\8B\models--HumanLLMs--Human-Like-LLama3-8B-Instruct
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--NeverSleep--Llama-3-Lumimaid-8B-v0.1-OAS
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--TroyDoesAI--BlackSheep-X-Dolphin
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--Bacon666--Athlon-8B-0.1
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
- model: A:\LLM\.cache\8B\!models--Babsie--ThetaBlackGorgon-8B
|
||||
parameters:
|
||||
weight: 0.1
|
||||
density: 0.8
|
||||
merge_method: dare_linear
|
||||
base_model: A:\LLM\.cache\8B\!models--aifeifei798--DarkIdol-Llama-3.1-8B-Instruct-1.2-Uncensored
|
||||
parameters:
|
||||
lambda: 1.0
|
||||
normalize: false
|
||||
int8_mask: false
|
||||
rescale: true
|
||||
tokenizer:
|
||||
source: union
|
||||
chat_template: auto
|
||||
dtype: float32
|
||||
out_dtype: bfloat16
|
||||
name: 📜 Goetia-8B-v1
|
||||
3
model-00001-of-00004.safetensors
Normal file
3
model-00001-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f3616fd9ab9c237c2dea39f251c2d93be4cff355ff65c0df62ced1b9fe271f15
|
||||
size 4953799376
|
||||
3
model-00002-of-00004.safetensors
Normal file
3
model-00002-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c57f3d59754a2214ddefab9416898e73380fc17c9f964a63eed6d81148c441d
|
||||
size 4999819336
|
||||
3
model-00003-of-00004.safetensors
Normal file
3
model-00003-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e38e44f439b6dc43912ecc582ed64a9368c3e61aa665ada796d89ea3e9b63500
|
||||
size 4915916144
|
||||
3
model-00004-of-00004.safetensors
Normal file
3
model-00004-of-00004.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e4aa483b876dcc8f92048b71fa98f3c3f5e64f327cb67545d181eecfd1ae86a0
|
||||
size 1191234472
|
||||
299
model.safetensors.index.json
Normal file
299
model.safetensors.index.json
Normal file
@@ -0,0 +1,299 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 16060735488,
|
||||
"mergekit_version": "0.1.4"
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00001-of-00004.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
||||
"model.norm.weight": "model-00004-of-00004.safetensors"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:02e0633925aa2c0e7a2c54cd744e1d5455dee748e2fe1935703bfcab04ce9d99
|
||||
size 17212434
|
||||
2170
tokenizer_config.json
Normal file
2170
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user