初始化项目,由ModelHub XC社区提供模型
Model: Delta-Vector/Rei-24B-KTO Source: Original Platform
This commit is contained in:
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
|
||||||
326
README.md
Normal file
326
README.md
Normal file
@@ -0,0 +1,326 @@
|
|||||||
|
---
|
||||||
|
library_name: transformers
|
||||||
|
tags:
|
||||||
|
- fine-tuning
|
||||||
|
- prose
|
||||||
|
- KTO
|
||||||
|
- axolotl
|
||||||
|
- finetune
|
||||||
|
- roleplaying
|
||||||
|
- creative-writing
|
||||||
|
base_model:
|
||||||
|
- Delta-Vector/Rei-24B-Base
|
||||||
|
---
|
||||||
|
<style>
|
||||||
|
@import url('https://fonts.googleapis.com/css2?family=Share+Tech+Mono&display=swap');
|
||||||
|
|
||||||
|
body {
|
||||||
|
font-family: 'Share Tech Mono', monospace;
|
||||||
|
background: #121212;
|
||||||
|
color: #E0E0E0;
|
||||||
|
margin: 0;
|
||||||
|
padding: 0;
|
||||||
|
font-size: 16px;
|
||||||
|
}
|
||||||
|
.container {
|
||||||
|
margin: 20px auto;
|
||||||
|
background-color: #1E1E1E;
|
||||||
|
padding: 20px;
|
||||||
|
border-radius: 8px;
|
||||||
|
box-shadow: 0 0 25px rgba(255, 0, 51, 0.3);
|
||||||
|
border: 1px solid #FF0033;
|
||||||
|
position: relative;
|
||||||
|
max-width: 1000px;
|
||||||
|
}
|
||||||
|
.header h1 {
|
||||||
|
font-size: 32px;
|
||||||
|
color: #FF0033;
|
||||||
|
margin: 0 0 20px 0;
|
||||||
|
text-align: center;
|
||||||
|
text-shadow: 0 0 10px rgba(255, 0, 51, 0.7);
|
||||||
|
text-transform: uppercase;
|
||||||
|
}
|
||||||
|
.section {
|
||||||
|
margin-top: 30px;
|
||||||
|
}
|
||||||
|
.section h2 {
|
||||||
|
font-size: 26px;
|
||||||
|
color: #FF0033;
|
||||||
|
text-align: center;
|
||||||
|
border-bottom: 1px solid #FF0033;
|
||||||
|
padding-bottom: 10px;
|
||||||
|
margin-bottom: 20px;
|
||||||
|
}
|
||||||
|
.info p {
|
||||||
|
color: #E0E0E0;
|
||||||
|
line-height: 1.7;
|
||||||
|
font-size: 16px;
|
||||||
|
}
|
||||||
|
.info img {
|
||||||
|
width: 100%;
|
||||||
|
max-width: 600px;
|
||||||
|
border-radius: 4px;
|
||||||
|
margin: 0 auto 15px;
|
||||||
|
display: block;
|
||||||
|
box-shadow: 0 0 20px rgba(0, 0, 0, 0.5);
|
||||||
|
border: 1px solid #444;
|
||||||
|
}
|
||||||
|
a {
|
||||||
|
color: #FF0033;
|
||||||
|
text-decoration: none;
|
||||||
|
transition: color 0.2s ease, text-shadow 0.2s ease;
|
||||||
|
}
|
||||||
|
a:hover {
|
||||||
|
color: #FFFFFF;
|
||||||
|
text-shadow: 0 0 8px rgba(255, 0, 51, 0.8);
|
||||||
|
}
|
||||||
|
.button {
|
||||||
|
display: inline-block;
|
||||||
|
background-color: transparent;
|
||||||
|
color: #FF0033;
|
||||||
|
padding: 10px 20px;
|
||||||
|
border-radius: 4px;
|
||||||
|
cursor: pointer;
|
||||||
|
text-decoration: none;
|
||||||
|
border: 1px solid #FF0033;
|
||||||
|
transition: background-color 0.2s ease, box-shadow 0.2s ease, color 0.2s ease;
|
||||||
|
}
|
||||||
|
.button:hover {
|
||||||
|
background-color: #FF0033;
|
||||||
|
color: #121212;
|
||||||
|
box-shadow: 0 0 15px rgba(255, 0, 51, 0.7);
|
||||||
|
}
|
||||||
|
pre {
|
||||||
|
background-color: #0d0d0d;
|
||||||
|
padding: 15px;
|
||||||
|
border-radius: 4px;
|
||||||
|
overflow-x: auto;
|
||||||
|
border: 1px solid #444;
|
||||||
|
border-left: 3px solid #FF0033;
|
||||||
|
color: #E0E0E0;
|
||||||
|
}
|
||||||
|
code {
|
||||||
|
font-family: 'Share Tech Mono', monospace;
|
||||||
|
color: #E0E0E0;
|
||||||
|
}
|
||||||
|
.info-card {
|
||||||
|
background: #2a2a2a;
|
||||||
|
border: 1px solid #444;
|
||||||
|
border-radius: 8px;
|
||||||
|
overflow: hidden;
|
||||||
|
}
|
||||||
|
.info-header {
|
||||||
|
background: #1a1a1a;
|
||||||
|
padding: 20px;
|
||||||
|
border-bottom: 1px solid #444;
|
||||||
|
}
|
||||||
|
.info-header h3 {
|
||||||
|
color: #FFFFFF;
|
||||||
|
margin: 0 0 10px 0;
|
||||||
|
font-size: 22px;
|
||||||
|
text-align: center;
|
||||||
|
}
|
||||||
|
.model-tags {
|
||||||
|
display: flex;
|
||||||
|
justify-content: center;
|
||||||
|
gap: 10px;
|
||||||
|
flex-wrap: wrap;
|
||||||
|
}
|
||||||
|
.model-tag {
|
||||||
|
background: #121212;
|
||||||
|
color: #FF0033;
|
||||||
|
padding: 5px 10px;
|
||||||
|
border-radius: 4px;
|
||||||
|
font-size: 12px;
|
||||||
|
border: 1px solid #FF0033;
|
||||||
|
text-transform: uppercase;
|
||||||
|
}
|
||||||
|
.model-composition {
|
||||||
|
padding: 20px;
|
||||||
|
border-bottom: 1px solid #444;
|
||||||
|
}
|
||||||
|
.model-composition h4 {
|
||||||
|
color: #FFFFFF;
|
||||||
|
margin: 0 0 15px 0;
|
||||||
|
font-size: 18px;
|
||||||
|
text-align: center;
|
||||||
|
}
|
||||||
|
.composition-list {
|
||||||
|
list-style: none;
|
||||||
|
padding: 0;
|
||||||
|
margin: 0;
|
||||||
|
display: grid;
|
||||||
|
gap: 10px;
|
||||||
|
}
|
||||||
|
.composition-list li {
|
||||||
|
color: #E0E0E0;
|
||||||
|
display: flex;
|
||||||
|
align-items: baseline;
|
||||||
|
gap: 8px;
|
||||||
|
}
|
||||||
|
.model-component {
|
||||||
|
font-weight: bold;
|
||||||
|
min-width: 120px;
|
||||||
|
}
|
||||||
|
.model-description {
|
||||||
|
padding: 20px;
|
||||||
|
background: #2a2a2a;
|
||||||
|
}
|
||||||
|
.metrics-section {
|
||||||
|
margin-bottom: 30px;
|
||||||
|
}
|
||||||
|
.metrics-section details {
|
||||||
|
background: #2a2a2a;
|
||||||
|
border: 1px solid #444;
|
||||||
|
border-radius: 8px;
|
||||||
|
padding: 15px;
|
||||||
|
margin-bottom: 15px;
|
||||||
|
}
|
||||||
|
.metrics-section summary {
|
||||||
|
color: #FF0033;
|
||||||
|
font-size: 18px;
|
||||||
|
cursor: pointer;
|
||||||
|
outline: none;
|
||||||
|
padding: 5px 0;
|
||||||
|
text-align: center;
|
||||||
|
font-weight: bold;
|
||||||
|
}
|
||||||
|
.creator-section {
|
||||||
|
margin: 20px 0;
|
||||||
|
}
|
||||||
|
.creator-badge {
|
||||||
|
display: inline-flex;
|
||||||
|
align-items: center;
|
||||||
|
background: #1a1a1a;
|
||||||
|
border: 1px solid #444;
|
||||||
|
border-radius: 4px;
|
||||||
|
padding: 10px 15px;
|
||||||
|
}
|
||||||
|
.creator-label {
|
||||||
|
color: #E0E0E0;
|
||||||
|
font-size: 14px;
|
||||||
|
margin-right: 8px;
|
||||||
|
}
|
||||||
|
.creator-link {
|
||||||
|
display: flex;
|
||||||
|
align-items: center;
|
||||||
|
gap: 5px;
|
||||||
|
color: #FF0033;
|
||||||
|
text-decoration: none;
|
||||||
|
transition: all 0.2s ease;
|
||||||
|
}
|
||||||
|
.creator-name {
|
||||||
|
font-weight: 600;
|
||||||
|
}
|
||||||
|
.creator-arrow {
|
||||||
|
font-size: 16px;
|
||||||
|
transition: transform 0.2s ease;
|
||||||
|
}
|
||||||
|
.creator-link:hover .creator-arrow {
|
||||||
|
transform: translateX(5px);
|
||||||
|
}
|
||||||
|
.link-arrow {
|
||||||
|
display: inline-block;
|
||||||
|
transition: transform 0.2s ease;
|
||||||
|
}
|
||||||
|
a:hover .link-arrow {
|
||||||
|
transform: translateX(5px);
|
||||||
|
}
|
||||||
|
.axolotl-container {
|
||||||
|
text-align: center;
|
||||||
|
margin: 30px 0;
|
||||||
|
filter: invert(1) hue-rotate(180deg);
|
||||||
|
}
|
||||||
|
.axolotl-container img {
|
||||||
|
max-width: 300px;
|
||||||
|
border-radius: 8px;
|
||||||
|
box-shadow: 0 2px 10px rgba(0, 0, 0, 0.3);
|
||||||
|
border: 1px solid #000000;
|
||||||
|
}
|
||||||
|
</style>
|
||||||
|
<html lang="en">
|
||||||
|
<head>
|
||||||
|
<meta charset="UTF-8">
|
||||||
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||||||
|
<title>Rei-KTO-24B</title>
|
||||||
|
</head>
|
||||||
|
<body>
|
||||||
|
<div class="container">
|
||||||
|
<div class="header">
|
||||||
|
<h1>Rei-KTO-24B</h1>
|
||||||
|
</div>
|
||||||
|
<div class="info">
|
||||||
|
<img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/EFNIBpVv1OITZl_su5DyR.png" alt="Model banner">
|
||||||
|
<div style="text-align: center;">
|
||||||
|
<div class="creator-section">
|
||||||
|
<div class="creator-badge">
|
||||||
|
<span class="creator-label">Created by</span>
|
||||||
|
<a href="https://huggingface.co/Delta-Vector" target="_blank" class="creator-link">
|
||||||
|
<span class="creator-name">Delta-Vector</span>
|
||||||
|
<span class="creator-arrow">→</span>
|
||||||
|
</a>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="model-info">
|
||||||
|
<h2>Model Information</h2>
|
||||||
|
<div class="info-card">
|
||||||
|
<div class="info-header">
|
||||||
|
<h>Rei-KTO-24B</h3>
|
||||||
|
<div class="model-tags">
|
||||||
|
<span class="model-tag">KTO enhanced</span>
|
||||||
|
<span class="model-tag">Painted Fantasy Finetune</span>
|
||||||
|
<span class="model-tag">Creative Prose</span>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="model-description">
|
||||||
|
<p>A model meant to replicate the style and prose of the Anthropic Claude models, Opus and Sonnet. This model is meant for Roleplaying/Creative-writing, Has some nice smarts without being too sloppy, etc - It's pretty good. Trained in 2 steps, Firstly SFT trained on Zerofata's PaintedFantasy which i found great at anime-otaku-esque characters, and then KTO'd to improve coherency and Instruct Following </p>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="section">
|
||||||
|
<h2>Quantized Versions</h2>
|
||||||
|
<div class="info-card">
|
||||||
|
<div class="model-composition">
|
||||||
|
<h4>Available Downloads</h4>
|
||||||
|
<ul class="composition-list">
|
||||||
|
<li><span class="model-component"><a href="https://huggingface.co/mradermacher/Rei-24B-KTO-GGUF" target="_blank">GGUF Format</a></span>For use with LLama.cpp & Forks (Ty Mradermacher <3)</li>
|
||||||
|
<li><span class="model-component"><a href="https://huggingface.co/DeathGodlike/Rei-24B-KTO_EXL3" target="_blank">EXL3 Format</a></span>For use with TabbyAPI</li>
|
||||||
|
</ul>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="section">
|
||||||
|
<h2>Prompting</h2>
|
||||||
|
<p>The model is tuned with V7 Tekken formatting. A typical input would look like this:</p>
|
||||||
|
<pre><code><span style="color:#FF0033;"><s>[SYSTEM_PROMPT]system_prompt[/SYSTEM_PROMPT][INST]Hi there![/INST]Nice to meet you!</s>[INST]Can I ask a question?[/INST]
|
||||||
|
</code></pre>
|
||||||
|
</div>
|
||||||
|
<div class="section">
|
||||||
|
<h2>Training</h2>
|
||||||
|
<p>Training was done in 2 steps, SFT>KTO</p>
|
||||||
|
<div class="metrics-section">
|
||||||
|
<details>
|
||||||
|
<summary>Access Configs</summary>
|
||||||
|
<pre><code> SFT: https://wandb.ai/new-eden/Painted-Fantasy-Rei/artifacts/axolotl-config/config-u7to9d5q/v0/files/axolotl_config_f0p7vnaf.yml
|
||||||
|
KTO : https://wandb.ai/new-eden/Painted-Rei/artifacts/axolotl-config/config-8n37w77c/v0/files/axolotl_config_hvrd2tzn.yml
|
||||||
|
</code></pre>
|
||||||
|
</details>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
<div class="section">
|
||||||
|
<h2>Training</h2>
|
||||||
|
<p>The training was done for 2 epochs using 8 x A100s for 24 hours/p>
|
||||||
|
<p style="text-align: center; margin-top: 20px;">
|
||||||
|
<div class="axolotl-container">
|
||||||
|
<a href="https://github.com/OpenAccess-AI-Collective/axolotl" target="_blank">
|
||||||
|
<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl">
|
||||||
|
</a>
|
||||||
|
</div>
|
||||||
|
<div class="section">
|
||||||
|
<h2>Credits</h2>
|
||||||
|
<p>Thank you to <a href="https://huggingface.co/lucyknada">Lucy Knada</a>, <a href="https://huggingface.co/Ateron">Ateron</a>, <a href="https://huggingface.co/AliCat2">Alicat</a>, <a href="https://huggingface.co/intervitens">Intervitens</a>, <a href="https://huggingface.co/cgato">Cgato</a>, <a href="https://huggingface.co/kubernetes-bad">Kubernetes Bad</a> and the rest of <a href="https://huggingface.co/anthracite-org">Anthracite</a>.</p>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</div>
|
||||||
|
</body>
|
||||||
|
</html>
|
||||||
51
chat_template.jinja
Normal file
51
chat_template.jinja
Normal file
@@ -0,0 +1,51 @@
|
|||||||
|
{%- set today = strftime_now("%Y-%m-%d") %}
|
||||||
|
{%- set default_system_message = "You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris.\nYour knowledge base was last updated on 2023-10-01. The current date is " + today + ".\n\nWhen you're not sure about some information, you say that you don't have the information and don't make up anything.\nIf the user's question is not clear, ambiguous, or does not provide enough context for you to accurately answer the question, you do not try to answer it right away and you rather ask the user to clarify their request (e.g. \"What are some good restaurants around me?\" => \"Where are you?\" or \"When is the next flight to Tokyo\" => \"Where do you travel from?\")" %}
|
||||||
|
|
||||||
|
{{- bos_token }}
|
||||||
|
|
||||||
|
{%- if messages[0]['role'] == 'system' %}
|
||||||
|
{%- if messages[0]['content'] is string %}
|
||||||
|
{%- set system_message = messages[0]['content'] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = messages[0]['content'][0]['text'] %}
|
||||||
|
{%- endif %}
|
||||||
|
{%- set loop_messages = messages[1:] %}
|
||||||
|
{%- else %}
|
||||||
|
{%- set system_message = default_system_message %}
|
||||||
|
{%- set loop_messages = messages %}
|
||||||
|
{%- endif %}
|
||||||
|
{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}
|
||||||
|
|
||||||
|
{%- for message in loop_messages %}
|
||||||
|
{%- if message['role'] == 'user' %}
|
||||||
|
{%- if message['content'] is string %}
|
||||||
|
{{- '[INST]' + message['content'] + '[/INST]' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '[INST]' }}
|
||||||
|
{%- for block in message['content'] %}
|
||||||
|
{%- if block['type'] == 'text' %}
|
||||||
|
{{- block['text'] }}
|
||||||
|
{%- elif block['type'] in ['image', 'image_url'] %}
|
||||||
|
{{- '[IMG]' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception('Only text and image blocks are supported in message content!') }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
|
{{- '[/INST]' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message['role'] == 'system' %}
|
||||||
|
{%- if message['content'] is string %}
|
||||||
|
{{- '[SYSTEM_PROMPT]' + message['content'] + '[/SYSTEM_PROMPT]' }}
|
||||||
|
{%- else %}
|
||||||
|
{{- '[SYSTEM_PROMPT]' + message['content'][0]['text'] + '[/SYSTEM_PROMPT]' }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- elif message['role'] == 'assistant' %}
|
||||||
|
{%- if message['content'] is string %}
|
||||||
|
{{- message['content'] + eos_token }}
|
||||||
|
{%- else %}
|
||||||
|
{{- message['content'][0]['text'] + eos_token }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- else %}
|
||||||
|
{{- raise_exception('Only user, system and assistant roles are supported!') }}
|
||||||
|
{%- endif %}
|
||||||
|
{%- endfor %}
|
||||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
|||||||
|
{
|
||||||
|
"architectures": [
|
||||||
|
"MistralForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"head_dim": 128,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 5120,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 32768,
|
||||||
|
"max_position_embeddings": 131072,
|
||||||
|
"model_type": "mistral",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 40,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_theta": 1000000000.0,
|
||||||
|
"sliding_window": null,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.53.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 131072
|
||||||
|
}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"do_sample": true,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"transformers_version": "4.53.1"
|
||||||
|
}
|
||||||
3
model-00001-of-00010.safetensors
Normal file
3
model-00001-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b9b4cc3c9c276caa374f2eb7c82a838ccc5f1cc3d426267ad4adefd934a97b4d
|
||||||
|
size 4781571736
|
||||||
3
model-00002-of-00010.safetensors
Normal file
3
model-00002-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:cab8dcb3bbede0455b28dfb80692414db91fb2ae6e79342b98ca7fbecae79d3e
|
||||||
|
size 4781592784
|
||||||
3
model-00003-of-00010.safetensors
Normal file
3
model-00003-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:db1cf23e5c2de4c57abb13800c847facb7ea914733ccf8c5e3fc7660a0837b22
|
||||||
|
size 4781592800
|
||||||
3
model-00004-of-00010.safetensors
Normal file
3
model-00004-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b35b71354f8f860ed53fd1c578590e99eb4b3954920ce5067a781f9087168295
|
||||||
|
size 4886471600
|
||||||
3
model-00005-of-00010.safetensors
Normal file
3
model-00005-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fcf983ad514ffeef4d0d3559358882fd54e97017002aaffe6bb2f4349fbbf2a0
|
||||||
|
size 4781592824
|
||||||
3
model-00006-of-00010.safetensors
Normal file
3
model-00006-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5be6481070f5e0a58908791c9a15977bb573025f250ac0145874250d4768a6b1
|
||||||
|
size 4781592816
|
||||||
3
model-00007-of-00010.safetensors
Normal file
3
model-00007-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fe61b97b759fe04cf0aafa22ee1bde2612da688147b16328f72a36d3b3c9cac8
|
||||||
|
size 4886471600
|
||||||
3
model-00008-of-00010.safetensors
Normal file
3
model-00008-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:5694220fb02c1d8a118d474836d902c3aac10628a9663e2bf6721dc59bfdf039
|
||||||
|
size 4781592824
|
||||||
3
model-00009-of-00010.safetensors
Normal file
3
model-00009-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:12d552caf65da1ef090b8bbfdbeb8e4218771f5d7f517d9951b64db6798f79a2
|
||||||
|
size 4781592816
|
||||||
3
model-00010-of-00010.safetensors
Normal file
3
model-00010-of-00010.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d93d37682ef34f2c58fe073d5ada793e7c54526574f61f64fd194a6f36a3f802
|
||||||
|
size 3900777072
|
||||||
371
model.safetensors.index.json
Normal file
371
model.safetensors.index.json
Normal file
@@ -0,0 +1,371 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_parameters": 23572403200,
|
||||||
|
"total_size": 47144806400
|
||||||
|
},
|
||||||
|
"weight_map": {
|
||||||
|
"lm_head.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.embed_tokens.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.10.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.12.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.input_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00010.safetensors",
|
||||||
|
"model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.input_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.2.input_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.20.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.20.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00010.safetensors",
|
||||||
|
"model.layers.21.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.input_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.24.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors",
|
||||||
|
"model.layers.25.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.input_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.29.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00010.safetensors",
|
||||||
|
"model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00010.safetensors",
|
||||||
|
"model.layers.30.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.input_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00010.safetensors",
|
||||||
|
"model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.input_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.37.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00010.safetensors",
|
||||||
|
"model.layers.38.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.input_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00010.safetensors",
|
||||||
|
"model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00010.safetensors",
|
||||||
|
"model.layers.8.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.input_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00010.safetensors",
|
||||||
|
"model.norm.weight": "model-00010-of-00010.safetensors"
|
||||||
|
}
|
||||||
|
}
|
||||||
1032
special_tokens_map.json
Normal file
1032
special_tokens_map.json
Normal file
File diff suppressed because it is too large
Load Diff
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b76085f9923309d873994d444989f7eb6ec074b06f25b58f1e8d7b7741070949
|
||||||
|
size 17078037
|
||||||
9019
tokenizer_config.json
Normal file
9019
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user