|
|
--- |
|
|
base_model: |
|
|
- snwy/frankenqwen3-8B-235B-dense-conversion-interleaved-untuned |
|
|
library_name: transformers |
|
|
tags: |
|
|
- fine-tuning |
|
|
- prose |
|
|
- GRPO |
|
|
- axolotl |
|
|
- finetune |
|
|
- roleplaying |
|
|
- creative-writing |
|
|
--- |
|
|
<style> |
|
|
body { |
|
|
font-family: 'Quicksand', sans-serif; |
|
|
background: linear-gradient(135deg, #f9ffd1 0%, #e2fab5 100%); |
|
|
color: #000000; |
|
|
margin: 0; |
|
|
padding: 0; |
|
|
font-size: 16px; |
|
|
} |
|
|
.container { |
|
|
margin: 20px; |
|
|
background-color: rgba(255, 255, 255, 0.9); |
|
|
padding: 20px; |
|
|
border-radius: 12px; |
|
|
box-shadow: 0 4px 20px rgba(0, 0, 0, 0.3); |
|
|
border: 3px solid #000000; |
|
|
position: relative; |
|
|
} |
|
|
.header h1 { |
|
|
font-size: 28px; |
|
|
color: #000000; |
|
|
margin: 0 0 20px 0; |
|
|
text-align: center; |
|
|
text-decoration: underline; |
|
|
} |
|
|
.section { |
|
|
margin-top: 30px; |
|
|
} |
|
|
.section h2 { |
|
|
font-size: 24px; |
|
|
color: #000000; |
|
|
text-align: center; |
|
|
text-decoration: underline; |
|
|
} |
|
|
.info p { |
|
|
color: #000000; |
|
|
line-height: 1.6; |
|
|
font-size: 16px; |
|
|
} |
|
|
.info img { |
|
|
width: 85%; |
|
|
border-radius: 10px; |
|
|
margin: 0 auto 15px; |
|
|
display: block; |
|
|
box-shadow: 0 0 20px rgba(0, 0, 0, 0.3); |
|
|
border: 1px solid #000000; |
|
|
} |
|
|
a { |
|
|
color: #000000; |
|
|
text-decoration: none; |
|
|
transition: color 0.2s ease; |
|
|
} |
|
|
a:hover { |
|
|
color: #538125; |
|
|
} |
|
|
.button { |
|
|
display: inline-block; |
|
|
background-color: rgba(106, 168, 79, 0.8); |
|
|
color: #000000; |
|
|
padding: 10px 20px; |
|
|
border-radius: 5px; |
|
|
cursor: pointer; |
|
|
text-decoration: none; |
|
|
transition: background-color 0.2s ease, box-shadow 0.2s ease; |
|
|
} |
|
|
.button:hover { |
|
|
background-color: #538125; |
|
|
box-shadow: 0 0 15px rgba(106, 168, 79, 0.5); |
|
|
} |
|
|
pre { |
|
|
background-color: rgba(240, 248, 225, 0.95); |
|
|
padding: 15px; |
|
|
border-radius: 5px; |
|
|
overflow-x: auto; |
|
|
border: 1px solid #000000; |
|
|
} |
|
|
code { |
|
|
font-family: 'Courier New', monospace; |
|
|
color: #000000; |
|
|
} |
|
|
.info-card { |
|
|
background: rgba(249, 255, 235, 0.95); |
|
|
border: 1px solid #000000; |
|
|
border-radius: 8px; |
|
|
overflow: hidden; |
|
|
} |
|
|
.info-header { |
|
|
background: rgba(106, 168, 79, 0.1); |
|
|
padding: 20px; |
|
|
border-bottom: 1px solid #000000; |
|
|
} |
|
|
.info-header h3 { |
|
|
color: #000000; |
|
|
margin: 0 0 10px 0; |
|
|
font-size: 20px; |
|
|
text-align: center; |
|
|
text-decoration: underline; |
|
|
} |
|
|
.model-tags { |
|
|
display: flex; |
|
|
gap: 8px; |
|
|
flex-wrap: wrap; |
|
|
} |
|
|
.model-tag { |
|
|
background: rgba(106, 168, 79, 0.1); |
|
|
color: #000000; |
|
|
padding: 4px 8px; |
|
|
border-radius: 4px; |
|
|
font-size: 12px; |
|
|
border: 1px solid #000000; |
|
|
} |
|
|
.model-composition { |
|
|
padding: 20px; |
|
|
border-bottom: 1px solid #000000; |
|
|
} |
|
|
.model-composition h4 { |
|
|
color: #000000; |
|
|
margin: 0 0 15px 0; |
|
|
font-size: 16px; |
|
|
text-align: center; |
|
|
text-decoration: underline; |
|
|
} |
|
|
.composition-list { |
|
|
list-style: none; |
|
|
padding: 0; |
|
|
margin: 0; |
|
|
display: grid; |
|
|
gap: 10px; |
|
|
} |
|
|
.composition-list li { |
|
|
color: #000000; |
|
|
display: flex; |
|
|
align-items: baseline; |
|
|
gap: 8px; |
|
|
} |
|
|
.model-component { |
|
|
font-weight: 500; |
|
|
min-width: 120px; |
|
|
} |
|
|
.model-description { |
|
|
padding: 20px; |
|
|
background: rgba(255, 255, 255, 0.5); |
|
|
} |
|
|
.metrics-section { |
|
|
margin-bottom: 30px; |
|
|
} |
|
|
.metrics-section details { |
|
|
background: rgba(249, 255, 235, 0.95); |
|
|
border: 1px solid #000000; |
|
|
border-radius: 8px; |
|
|
padding: 15px; |
|
|
margin-bottom: 15px; |
|
|
} |
|
|
.metrics-section summary { |
|
|
color: #000000; |
|
|
font-size: 18px; |
|
|
cursor: pointer; |
|
|
outline: none; |
|
|
padding: 5px 0; |
|
|
text-align: center; |
|
|
} |
|
|
.creator-section { |
|
|
margin: 20px 0; |
|
|
} |
|
|
.creator-badge { |
|
|
display: inline-flex; |
|
|
align-items: center; |
|
|
background: rgba(249, 255, 235, 0.95); |
|
|
border: 1px solid #000000; |
|
|
border-radius: 8px; |
|
|
padding: 10px 15px; |
|
|
} |
|
|
.creator-label { |
|
|
color: #000000; |
|
|
font-size: 14px; |
|
|
margin-right: 8px; |
|
|
} |
|
|
.creator-link { |
|
|
display: flex; |
|
|
align-items: center; |
|
|
gap: 5px; |
|
|
color: #000000; |
|
|
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(3px); |
|
|
} |
|
|
.link-arrow { |
|
|
display: inline-block; |
|
|
transition: transform 0.2s ease; |
|
|
} |
|
|
a:hover .link-arrow { |
|
|
transform: translateX(3px); |
|
|
} |
|
|
.axolotl-container { |
|
|
text-align: center; |
|
|
margin: 30px 0; |
|
|
display: flex; |
|
|
justify-content: center; |
|
|
align-items: center; |
|
|
} |
|
|
.axolotl-container img { |
|
|
max-width: 200px; |
|
|
width: 200px; |
|
|
height: auto; |
|
|
border-radius: 8px; |
|
|
box-shadow: 0 2px 10px rgba(0, 0, 0, 0.3); |
|
|
border: 1px solid #000000; |
|
|
background-color: #000000; |
|
|
padding: 15px; |
|
|
object-fit: contain; |
|
|
display: block; |
|
|
margin: 0 auto; |
|
|
} |
|
|
</style> |
|
|
<html lang="en"> |
|
|
<head> |
|
|
<meta charset="UTF-8"> |
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"> |
|
|
<title>Nanuq-R1 14B</title> |
|
|
<link href="https://fonts.googleapis.com/css2?family=Quicksand:wght@400;500;600&display=swap" rel="stylesheet"> |
|
|
</head> |
|
|
<body> |
|
|
<div class="container"> |
|
|
<div class="header"> |
|
|
<h1>Nanuq-R1 14B</h1> |
|
|
</div> |
|
|
<div class="info"> |
|
|
<img src="https://files.catbox.moe/i77ubj.webp" 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"> |
|
|
<h3>Nanuq-R1 14B</h3> |
|
|
<div class="model-tags"> |
|
|
<span class="model-tag">GRPO Experiment</span> |
|
|
<span class="model-tag">Q3-235B-8B Merge/heal</span> |
|
|
<span class="model-tag">Competant assistant with decent writing!</span> |
|
|
</div> |
|
|
</div> |
|
|
<div class="model-description"> |
|
|
<p>A sequel! The new Nanuq series is meant to be as a testing grounds for my GRPO experiments, This model is a full post-train heal of Snwy's Frankenmerge between Q3 235B and Q3 8B.</p> |
|
|
<p>Pretrained for 2 epochs on 1B tokens of Creative Writing data, Then SFT with alot of my own and Pocketdoc's Instruct dataset, and then GRPO'd with the Claude-2.7K dataset in an attempt to align it to be more like Claude with POLARS and Verifiers</p> |
|
|
<p>There's alot of things i could do different, As the reward almost falls flat as soon as you get out of warm-up but this model was pretty decent so decided to release it(Esp considering it's starting place), Hope people enjoy it!</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="" target="_blank">GGUF Format</a></span>For use with LLama.cpp & Forks(Coming Soon!)</li> |
|
|
<li><span class="model-component"><a href="" target="_blank">EXL2 Format</a></span>For use with TabbyAPI (Coming soon!)</li> |
|
|
</ul> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="section"> |
|
|
<h2>Prompting</h2> |
|
|
<p>Model has been tuned with the ChatML formatting. A typical input would look like this:</p> |
|
|
<pre><code>"""<|im_start|>user |
|
|
Hi there!<|im_end|> |
|
|
<|im_start|>assistant |
|
|
Nice to meet you!<|im_end|> |
|
|
<|im_start|>user |
|
|
Can I ask a question?<|im_end|> |
|
|
<|im_start|>assistant |
|
|
"""</code></pre> |
|
|
</div> |
|
|
<div class="section"> |
|
|
<h2>Training</h2> |
|
|
<p>The training was done for 2 epochs of Pretraining and 2 epochs of SFT and finally 500 steps of GRPO using Verifiers with 8 x <a href="https://www.nvidia.com/en-us/data-center/h200/">H200s</a> GPUs for the fine-tuning of the model.</p> |
|
|
<p style="text-align: center; margin-top: 20px;"> |
|
|
<div class="axolotl-container"> |
|
|
<a href="https://github.com/PrimeIntellect-ai/verifiers" target="_blank"> |
|
|
<img src="https://files.catbox.moe/j36qbe.png" alt="Built with Verifiers"> |
|
|
</a> |
|
|
<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> |
|
|
<div class="section"> |
|
|
<h2>Credits</h2> |
|
|
<p>Thank you to <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>, <a href="https://huggingface.co/cgato">Cgato</a>, <a href="https://huggingface.co/snwy">Snwy</a>, <a href="https://huggingface.co/AuriAetherwiing">Auri</a>, <a href="https://x.com/willccbb">Will Brown</a> and most of all: <a href="https://huggingface.co/kalomaze">Kalomaze</a> </p> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
