初始化项目，由ModelHub XC社区提供模型
Model: DarkArtsForge/Savage-Sands-12B-MPOA 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
|
||||||
358
README.md
Normal file
358
README.md
Normal file
@@ -0,0 +1,358 @@
|
|||||||
|
---
|
||||||
|
base_model:
|
||||||
|
- DarkArtsForge/Savage-Sands-12B
|
||||||
|
datasets:
|
||||||
|
- OccultAI/illuminati_imatrix_v1
|
||||||
|
language:
|
||||||
|
- en
|
||||||
|
library_name: transformers
|
||||||
|
license: apache-2.0
|
||||||
|
tags:
|
||||||
|
- creative
|
||||||
|
- creative writing
|
||||||
|
- fiction writing
|
||||||
|
- plot generation
|
||||||
|
- sub-plot generation
|
||||||
|
- fiction writing
|
||||||
|
- story generation
|
||||||
|
- scene continue
|
||||||
|
- storytelling
|
||||||
|
- fiction story
|
||||||
|
- science fiction
|
||||||
|
- romance
|
||||||
|
- all genres
|
||||||
|
- story
|
||||||
|
- writing
|
||||||
|
- vivid prosing
|
||||||
|
- vivid writing
|
||||||
|
- fiction
|
||||||
|
- roleplaying
|
||||||
|
- float32
|
||||||
|
- swearing
|
||||||
|
- rp
|
||||||
|
- horror
|
||||||
|
- della
|
||||||
|
- mistral
|
||||||
|
- nemo
|
||||||
|
- merge
|
||||||
|
- mergekit
|
||||||
|
widget:
|
||||||
|
- text: "Savage-Sands-12B"
|
||||||
|
output:
|
||||||
|
url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/-I_Iw69w2x9WNmk-iA2oE.png
|
||||||
|
---
|
||||||
|
|
||||||
|
<audio controls src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/49d0YkIIJ_T9JeZ3gkwZ_.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 **ChatML** 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>Savage Sands 12B MPOA</title>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
|
||||||
|
<div class="container">
|
||||||
|
<div class="title-container">
|
||||||
|
<div class="title-wrapper">
|
||||||
|
<h1 class="title-main">
|
||||||
|
<span class="grimoire-text">🏜️ Savage Sands 12B MPOA</span>
|
||||||
|
</h1>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/-I_Iw69w2x9WNmk-iA2oE.png" alt="Goetia Grimoire" style="width:100%; border-radius: 3px; margin-bottom: 30px; border: 1px solid #C8BBAA;">
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-content"><font face="verdana" size="2">
|
||||||
|
<details>This image depicts a high-stakes confrontation in a desolate, sandy environment. At the center of the action is a fierce duel between a heavily armored human warrior and a monstrous, winged demon. The warrior, seen from the side, is equipped with a gold-colored <b>Trojan-style helmet</b>. He lunges forward, gripping a <b>gladius</b>—a short, broad-bladed Roman sword—with both hands. His armor is dark and intricate, consisting of layered plates and a tattered, loincloth-like skirt that fans out with his movement.
|
||||||
|
|
||||||
|
Facing him is a formidable <b>demon</b>. The creature has pale, muscular gray skin and massive, leathery <b>bat-like wings</b> that span a large portion of the background. It has a snarling, animalistic face with horns and is brandishing a long, wicked-looking <b>spear</b>, which it uses to block the warrior's advance. The demon's pose is agile and predatory, mirroring the intensity of the warrior's strike.
|
||||||
|
|
||||||
|
The battle takes place on a series of flat, circular <b>stepping stones</b> scattered across a dry, dusty landscape. In the bottom right foreground, another figure is partially visible, huddled on the ground and clad in white robes with a red sash, seemingly caught in the middle of this epic struggle. The background is filled with soft, hazy clouds and distant rock formations, giving the scene a timeless, mythological feel.</font></details>
|
||||||
|
</div></div>
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">🌵 12B Roleplay</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). The [main model](https://huggingface.co/DarkArtsForge/Savage-Sands-12B) was merged using the [della](https://arxiv.org/abs/2406.11617) merge method with unablated donors, and therefore has some refusals.
|
||||||
|
|
||||||
|
For a fully **uncensored** version, see [this page](https://huggingface.co/DarkArtsForge/Savage-Sands-12B-MPOA) which was manually calibrated with `scale 1.7`.
|
||||||
|
|
||||||
|
<details><b>This model is highly resistant to standard ablation methods like MPOA.</b> More than most Nemo 12Bs.
|
||||||
|
|
||||||
|
Which is strange considering the `della` method was used with `normalize: false` which is basically like a mild form of pre-ablation.
|
||||||
|
|
||||||
|
I tested several setups, and while lower values like scale 1.0 or 1.1 unlocked most refusals, there was a particular instruction prompt it still kept refusing.
|
||||||
|
|
||||||
|
Even at scale 1.5, it would overtly refuse, and claim it wasn't "safe or appropriate" and that it "couldn't be done".
|
||||||
|
|
||||||
|
I had to crank it up even higher in order to fully uncensor the model.
|
||||||
|
|
||||||
|
**The minimum threshold was identified: `scale 1.7` applied to all layers `0-39`.**
|
||||||
|
|
||||||
|
Attempting to only apply to layers 11-39 caused it to hallucinate a "corrected term" to swap out the correct term prompted it with, which was another direct form of covert non-compliance.
|
||||||
|
|
||||||
|
Attempting to only apply to layers 4-39 caused additional non-compliant "false corrections". **Every layer must be ablated for this model in order to uncensor it.** There seem to be hidden forms of covert non-compliance embedded in the earliest layers, even lm_head. **Despite being low on the graph, these early layers still contribute toward refusal of prompts.**
|
||||||
|
|
||||||
|
**When using scale 1.7 on all 40 layers, it uses a CORRECT correction (grammatical, not changing words) which is FULLY compliant, with no refusals or covert attempts to change topics.**
|
||||||
|
|
||||||
|
So if you want the model as smart as possible then use the unablated version with jailbreak. But if you require built-in no refusals, the MPOA version is also quite creative.
|
||||||
|
|
||||||
|
</details>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">⚙️ YAML Configuration</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
architecture: MistralForCausalLM
|
||||||
|
base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
|
||||||
|
models:
|
||||||
|
- model: B:/12B/inflatebot--MN-12B-Mag-Mell-R1
|
||||||
|
parameters:
|
||||||
|
weight: 0.5
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/taozi555--MN-12B-Mag-Mell-R1-KTO
|
||||||
|
parameters:
|
||||||
|
weight: 0.5
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/UniLLMer--GslayerKaa
|
||||||
|
parameters:
|
||||||
|
weight: 0.5
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
- model: B:/12B/redrix--GodSlayer-12B-ABYSS
|
||||||
|
parameters:
|
||||||
|
weight: 0.5
|
||||||
|
density: 0.9
|
||||||
|
epsilon: 0.09
|
||||||
|
merge_method: della
|
||||||
|
parameters:
|
||||||
|
lambda: 1.0
|
||||||
|
normalize: false
|
||||||
|
int8_mask: false
|
||||||
|
rescale: true
|
||||||
|
dtype: float32
|
||||||
|
out_dtype: bfloat16
|
||||||
|
tokenizer:
|
||||||
|
source: B:/12B/taozi555--MN-12B-Mag-Mell-R1-KTO
|
||||||
|
name: 🏜️ Savage-Sands-12B
|
||||||
|
```
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
<div class="section-container">
|
||||||
|
<div class="section-header">
|
||||||
|
<div class="section-indicator"></div>
|
||||||
|
<h2 class="section-title">🔍 Merge Audit</h2>
|
||||||
|
</div>
|
||||||
|
<div class="section-content"><font face="verdana">
|
||||||
|
|
||||||
|
<pre>
|
||||||
|
[DELLA Audit] Layer: model.layers.33.mlp.down_proj.weight | Lambda=1.00
|
||||||
|
[BASE] mistralai--Mistral-Nemo-Instruct-2407
|
||||||
|
UniLLMer--GslayerKaa : ████████████████ 33.3% (W:0.50 D:0.90 N:4.89 E:0.09)
|
||||||
|
inflatebot--MN-12B-Mag-Mell-R1 : ████████ 17.7% (W:0.50 D:0.90 N:2.59 E:0.09)
|
||||||
|
redrix--GodSlayer-12B-ABYSS : ███████████████ 31.3% (W:0.50 D:0.90 N:4.59 E:0.09)
|
||||||
|
taozi555--MN-12B-Mag-Mell-R1-KTO : ████████ 17.7% (W:0.50 D:0.90 N:2.59 E:0.09)
|
||||||
|
|
||||||
|
[DELLA Audit] Layer: model.layers.33.mlp.gate_proj.weight | Lambda=1.00
|
||||||
|
[BASE] mistralai--Mistral-Nemo-Instruct-2407
|
||||||
|
UniLLMer--GslayerKaa : ███████████████████ 38.5% (W:0.50 D:0.90 N:7.05 E:0.09)
|
||||||
|
inflatebot--MN-12B-Mag-Mell-R1 : ███████ 14.8% (W:0.50 D:0.90 N:2.70 E:0.09)
|
||||||
|
redrix--GodSlayer-12B-ABYSS : ███████████████ 31.9% (W:0.50 D:0.90 N:5.84 E:0.09)
|
||||||
|
taozi555--MN-12B-Mag-Mell-R1-KTO : ███████ 14.8% (W:0.50 D:0.90 N:2.71 E:0.09)
|
||||||
|
</pre>
|
||||||
|
|
||||||
|
</font></div>
|
||||||
|
</div>
|
||||||
|
|
||||||
|
</html>
|
||||||
7
chat_template.jinja
Normal file
7
chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system
|
||||||
|
' + system_message + '<|im_end|>
|
||||||
|
' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user
|
||||||
|
' + content + '<|im_end|>
|
||||||
|
<|im_start|>assistant
|
||||||
|
' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>
|
||||||
|
' }}{% endif %}{% endfor %}
|
||||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"MistralForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"dtype": "bfloat16",
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"model_type": "mistral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 1000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"transformers_version": "4.56.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 131072
|
||||||
|
}
|
||||||
3
model-00001-of-00005.safetensors
Normal file
3
model-00001-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cc143796b16a88725ceaece984dd14d0e6f7ffbd91ddad320036fb5e03e1a488
|
||||||
|
size 4865489304
|
||||||
3
model-00002-of-00005.safetensors
Normal file
3
model-00002-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:e4151c9342ce643e8782cb3493f4ecb1414faf7c707d5acb7820fc35616b268d
|
||||||
|
size 4907529424
|
||||||
3
model-00003-of-00005.safetensors
Normal file
3
model-00003-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6a1f7279df88ff261ef368846a3477dae6d4506ba7871a53fb3337b131f03b58
|
||||||
|
size 4907529432
|
||||||
3
model-00004-of-00005.safetensors
Normal file
3
model-00004-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:986ba86f3d1ca9373fad78632e5b1e16b5f485a883ae32742212f73a40700feb
|
||||||
|
size 4907529424
|
||||||
3
model-00005-of-00005.safetensors
Normal file
3
model-00005-of-00005.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:21e979296bd04b010903e1d6b8ae98a773633dd6fde6920bf10f33eee8c2fc77
|
||||||
|
size 4907529360
|
||||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 24495564800,
|
||||||
|
"mergekit_version": "0.1.4"
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors",
|
||||||
|
"model.norm.weight": "model-00005-of-00005.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
|||||||
|
{
|
||||||
|
"additional_special_tokens": [
|
||||||
|
"<|im_start|>"
|
||||||
|
],
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|im_end|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4b4c8fcd33487a449c07f423d47adb035bba8347ccf13eb074b4d1fef8acf919
|
||||||
|
size 17078288
|
||||||
8020
tokenizer_config.json
Normal file
8020
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user