Update README.md
Browse files
README.md
CHANGED
|
@@ -53,510 +53,4 @@ print(f"Loaded {len(data['qa_pairs'])} QA pairs!")
|
|
| 53 |
|
| 54 |
## Credits
|
| 55 |
|
| 56 |
-
Created by Lyon28
|
| 57 |
-
|
| 58 |
-
|
| 59 |
-
<!--
|
| 60 |
-
HEADER SECTION
|
| 61 |
-
-->
|
| 62 |
-
|
| 63 |
-
<div align="center">
|
| 64 |
-
<picture>
|
| 65 |
-
<source
|
| 66 |
-
media="(prefers-color-scheme: dark)"
|
| 67 |
-
srcset="https://huggingface.co/Lyon28/caca-10m/resolve/main/logo-dark.png"
|
| 68 |
-
type="image/png"
|
| 69 |
-
/>
|
| 70 |
-
<source
|
| 71 |
-
media="(prefers-color-scheme: light)"
|
| 72 |
-
srcset="https://huggingface.co/Lyon28/caca-10m/resolve/main/logo-light.png"
|
| 73 |
-
type="image/png"
|
| 74 |
-
/>
|
| 75 |
-
<img
|
| 76 |
-
src="https://huggingface.co/Lyon28/caca-10m/resolve/main/logo.png"
|
| 77 |
-
alt="Caca Transformers Logo"
|
| 78 |
-
title="Caca - Modern Transformer Architecture"
|
| 79 |
-
width="60%"
|
| 80 |
-
height="auto"
|
| 81 |
-
loading="lazy"
|
| 82 |
-
/>
|
| 83 |
-
</picture>
|
| 84 |
-
</div>
|
| 85 |
-
|
| 86 |
-
<!--
|
| 87 |
-
BADGES SECTION
|
| 88 |
-
-->
|
| 89 |
-
|
| 90 |
-
<div align="center">
|
| 91 |
-
|
| 92 |
-
<!-- Social Links -->
|
| 93 |
-
<p>
|
| 94 |
-
<a href="https://huggingface.co/Lyon28" target="_blank" rel="noopener noreferrer">
|
| 95 |
-
<img
|
| 96 |
-
src="https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Lyon28-ffc107?color=ffc107&logoColor=white"
|
| 97 |
-
alt="Hugging Face Profile"
|
| 98 |
-
title="Visit Hugging Face Profile"
|
| 99 |
-
/>
|
| 100 |
-
</a>
|
| 101 |
-
</p>
|
| 102 |
-
|
| 103 |
-
<!-- License Badge -->
|
| 104 |
-
<p>
|
| 105 |
-
<a
|
| 106 |
-
href="https://github.com/Lyon-28/caca-transformers?tab=Apache-2.0-1-ov-file"
|
| 107 |
-
target="_blank"
|
| 108 |
-
rel="noopener noreferrer"
|
| 109 |
-
title="Apache 2.0 License"
|
| 110 |
-
>
|
| 111 |
-
<img
|
| 112 |
-
src="https://img.shields.io/badge/License-Apache%202.0-blue.svg"
|
| 113 |
-
alt="License: Apache 2.0"
|
| 114 |
-
height="20"
|
| 115 |
-
/>
|
| 116 |
-
</a>
|
| 117 |
-
</p>
|
| 118 |
-
|
| 119 |
-
<!-- PyPI Badge -->
|
| 120 |
-
<p>
|
| 121 |
-
<a href="https://pypi.org/project/caca-transformers/" target="_blank" rel="noopener noreferrer">
|
| 122 |
-
<img
|
| 123 |
-
src="https://img.shields.io/pypi/v/caca-transformers?color=blue&label=PyPI&logo=pypi&logoColor=white"
|
| 124 |
-
alt="PyPI Version"
|
| 125 |
-
title="View on PyPI"
|
| 126 |
-
/>
|
| 127 |
-
</a>
|
| 128 |
-
</p>
|
| 129 |
-
|
| 130 |
-
<!-- GitHub Stars -->
|
| 131 |
-
<p>
|
| 132 |
-
<a href="https://github.com/Lyon-28/caca-transformers" target="_blank" rel="noopener noreferrer">
|
| 133 |
-
<img
|
| 134 |
-
src="https://img.shields.io/github/stars/Lyon-28/caca-transformers?style=social&label=Star&maxAge=2592000"
|
| 135 |
-
alt="GitHub Stars"
|
| 136 |
-
title="Star on GitHub"
|
| 137 |
-
/>
|
| 138 |
-
</a>
|
| 139 |
-
</p>
|
| 140 |
-
|
| 141 |
-
<!-- Description -->
|
| 142 |
-
<p>
|
| 143 |
-
<strong>Arsitektur Transformer Modern dengan GQA, RoPE, SwiGLU & Flash Attention</strong>
|
| 144 |
-
</p>
|
| 145 |
-
|
| 146 |
-
</div>
|
| 147 |
-
|
| 148 |
-
<!-- Horizontal Rule -->
|
| 149 |
-
<hr/>
|
| 150 |
-
|
| 151 |
-
<!--
|
| 152 |
-
WARNING/ALERT SECTION
|
| 153 |
-
-->
|
| 154 |
-
|
| 155 |
-
<blockquote>
|
| 156 |
-
<p>
|
| 157 |
-
<strong>🔬 RESEARCH PROJECT</strong>
|
| 158 |
-
</p>
|
| 159 |
-
<p>
|
| 160 |
-
<strong>⚠️ PERHATIAN: MODEL UNTRAINED</strong>
|
| 161 |
-
</p>
|
| 162 |
-
<p>
|
| 163 |
-
Model ini memiliki bobot random dan memerlukan pretraining sebelum digunakan.
|
| 164 |
-
Tidak bisa langsung digunakan untuk inference!<br/>
|
| 165 |
-
Model ini adalah eksperimen arsitektur dan belum divalidasi untuk production use.
|
| 166 |
-
</p>
|
| 167 |
-
</blockquote>
|
| 168 |
-
|
| 169 |
-
<!--
|
| 170 |
-
MAIN TITLE
|
| 171 |
-
-->
|
| 172 |
-
|
| 173 |
-
<h1 align="center">
|
| 174 |
-
🐣 CACA-10M - TINY
|
| 175 |
-
</h1>
|
| 176 |
-
|
| 177 |
-
<p align="center">
|
| 178 |
-
<strong>🔢 10,485,760 Parameters (0.01B)</strong>
|
| 179 |
-
</p>
|
| 180 |
-
|
| 181 |
-
<p align="center">
|
| 182 |
-
<strong>💾 ~0.02GB (FP16) / ~0.04GB (FP32)</strong>
|
| 183 |
-
</p>
|
| 184 |
-
|
| 185 |
-
<p align="center">
|
| 186 |
-
<strong>📏 8,192 Context Length</strong>
|
| 187 |
-
</p>
|
| 188 |
-
|
| 189 |
-
<p align="center">
|
| 190 |
-
<strong>🎯 Use Case:</strong> Eksperimen cepat, edge devices, pembelajaran
|
| 191 |
-
</p>
|
| 192 |
-
|
| 193 |
-
<p align="center">
|
| 194 |
-
<strong>🖥️ Recommended GPU:</strong> GTX 1060 6GB or better
|
| 195 |
-
</p>
|
| 196 |
-
|
| 197 |
-
<!--
|
| 198 |
-
FEATURES SECTION
|
| 199 |
-
-->
|
| 200 |
-
|
| 201 |
-
<h2>🎯 Fitur Utama</h2>
|
| 202 |
-
|
| 203 |
-
<p>
|
| 204 |
-
Arsitektur Caca menggabungkan teknik-teknik modern terbaik dari berbagai model state-of-the-art:
|
| 205 |
-
</p>
|
| 206 |
-
|
| 207 |
-
<ul>
|
| 208 |
-
<li>
|
| 209 |
-
<strong>🔄 Grouped Query Attention (GQA)</strong> -
|
| 210 |
-
Keseimbangan optimal antara kecepatan inference dan kualitas output
|
| 211 |
-
</li>
|
| 212 |
-
<li>
|
| 213 |
-
<strong>🌀 RoPE (Rotary Positional Embeddings)</strong> -
|
| 214 |
-
Encoding posisi yang terbukti efektif untuk sequence panjang
|
| 215 |
-
</li>
|
| 216 |
-
<li>
|
| 217 |
-
<strong>⚡ SwiGLU Activation</strong> -
|
| 218 |
-
Performa superior dibanding ReLU/GELU dalam language modeling
|
| 219 |
-
</li>
|
| 220 |
-
<li>
|
| 221 |
-
<strong>📊 RMSNorm</strong> -
|
| 222 |
-
Normalisasi yang lebih efisien dan stabil dibanding LayerNorm
|
| 223 |
-
</li>
|
| 224 |
-
<li>
|
| 225 |
-
<strong>🪟 Sliding Window Attention</strong> -
|
| 226 |
-
Efisiensi memori untuk context window panjang (4,096 tokens)
|
| 227 |
-
</li>
|
| 228 |
-
<li>
|
| 229 |
-
<strong>💫 Flash Attention Compatible</strong> -
|
| 230 |
-
Support untuk Flash Attention 2-4x lebih cepat (opsional)
|
| 231 |
-
</li>
|
| 232 |
-
<li>
|
| 233 |
-
<strong>🔄 KV Cache Support</strong> -
|
| 234 |
-
Efficient autoregressive generation dengan caching
|
| 235 |
-
</li>
|
| 236 |
-
</ul>
|
| 237 |
-
|
| 238 |
-
<!--
|
| 239 |
-
TABLE SECTION - dengan semua atribut
|
| 240 |
-
-->
|
| 241 |
-
|
| 242 |
-
<h2 align="center">🏗️ Spesifikasi Teknis</h2>
|
| 243 |
-
|
| 244 |
-
<div align="center">
|
| 245 |
-
|
| 246 |
-
<table>
|
| 247 |
-
<caption>
|
| 248 |
-
<strong>Model Configuration Parameters</strong>
|
| 249 |
-
</caption>
|
| 250 |
-
<colgroup>
|
| 251 |
-
<col style="width: 50%"/>
|
| 252 |
-
<col style="width: 50%"/>
|
| 253 |
-
</colgroup>
|
| 254 |
-
<thead>
|
| 255 |
-
<tr>
|
| 256 |
-
<th align="left">Parameter</th>
|
| 257 |
-
<th align="right">Nilai</th>
|
| 258 |
-
</tr>
|
| 259 |
-
</thead>
|
| 260 |
-
<tbody>
|
| 261 |
-
<tr>
|
| 262 |
-
<td align="left"><strong>Total Parameters</strong></td>
|
| 263 |
-
<td align="right"><code>10,485,760</code> (~0.01B)</td>
|
| 264 |
-
</tr>
|
| 265 |
-
<tr>
|
| 266 |
-
<td align="left"><strong>Vocab Size</strong></td>
|
| 267 |
-
<td align="right"><code>50,000</code></td>
|
| 268 |
-
</tr>
|
| 269 |
-
<tr>
|
| 270 |
-
<td align="left"><strong>Hidden Size</strong></td>
|
| 271 |
-
<td align="right"><code>256</code></td>
|
| 272 |
-
</tr>
|
| 273 |
-
<tr>
|
| 274 |
-
<td align="left"><strong>Num Layers</strong></td>
|
| 275 |
-
<td align="right"><code>8</code></td>
|
| 276 |
-
</tr>
|
| 277 |
-
<tr>
|
| 278 |
-
<td align="left"><strong>Attention Heads</strong></td>
|
| 279 |
-
<td align="right"><code>8</code></td>
|
| 280 |
-
</tr>
|
| 281 |
-
<tr>
|
| 282 |
-
<td align="left"><strong>KV Heads (GQA)</strong></td>
|
| 283 |
-
<td align="right"><code>2</code></td>
|
| 284 |
-
</tr>
|
| 285 |
-
<tr>
|
| 286 |
-
<td align="left"><strong>GQA Ratio</strong></td>
|
| 287 |
-
<td align="right"><code>4:1</code></td>
|
| 288 |
-
</tr>
|
| 289 |
-
<tr>
|
| 290 |
-
<td align="left"><strong>Intermediate Size</strong></td>
|
| 291 |
-
<td align="right"><code>682</code></td>
|
| 292 |
-
</tr>
|
| 293 |
-
<tr>
|
| 294 |
-
<td align="left"><strong>Context Length</strong></td>
|
| 295 |
-
<td align="right"><code>8,192</code> tokens</td>
|
| 296 |
-
</tr>
|
| 297 |
-
<tr>
|
| 298 |
-
<td align="left"><strong>Sliding Window</strong></td>
|
| 299 |
-
<td align="right"><code>4,096</code> tokens</td>
|
| 300 |
-
</tr>
|
| 301 |
-
<tr>
|
| 302 |
-
<td align="left"><strong>RoPE Theta</strong></td>
|
| 303 |
-
<td align="right"><code>10,000</code></td>
|
| 304 |
-
</tr>
|
| 305 |
-
<tr>
|
| 306 |
-
<td align="left"><strong>Memory (FP16)</strong></td>
|
| 307 |
-
<td align="right">~<code>0.02</code> GB</td>
|
| 308 |
-
</tr>
|
| 309 |
-
<tr>
|
| 310 |
-
<td align="left"><strong>Memory (FP32)</strong></td>
|
| 311 |
-
<td align="right">~<code>0.04</code> GB</td>
|
| 312 |
-
</tr>
|
| 313 |
-
</tbody>
|
| 314 |
-
<tfoot>
|
| 315 |
-
<tr>
|
| 316 |
-
<td colspan="2" align="center">
|
| 317 |
-
<small><em>All values are approximate and may vary based on implementation</em></small>
|
| 318 |
-
</td>
|
| 319 |
-
</tr>
|
| 320 |
-
</tfoot>
|
| 321 |
-
</table>
|
| 322 |
-
|
| 323 |
-
</div>
|
| 324 |
-
|
| 325 |
-
<!--
|
| 326 |
-
DETAILS/SUMMARY - Collapsible sections
|
| 327 |
-
-->
|
| 328 |
-
|
| 329 |
-
<h2>📚 Model Family</h2>
|
| 330 |
-
|
| 331 |
-
<p>Kami menyediakan berbagai ukuran model untuk berbagai use case:</p>
|
| 332 |
-
|
| 333 |
-
<details open>
|
| 334 |
-
<summary>
|
| 335 |
-
<strong>🐣 Tiny & Small Models (10M - 500M)</strong>
|
| 336 |
-
</summary>
|
| 337 |
-
|
| 338 |
-
<p>Cocok untuk: Eksperimen cepat, edge devices, pembelajaran</p>
|
| 339 |
-
|
| 340 |
-
<table>
|
| 341 |
-
<thead>
|
| 342 |
-
<tr>
|
| 343 |
-
<th>Model</th>
|
| 344 |
-
<th>Params</th>
|
| 345 |
-
<th>Hidden</th>
|
| 346 |
-
<th>Layers</th>
|
| 347 |
-
<th>Heads</th>
|
| 348 |
-
<th>KV Heads</th>
|
| 349 |
-
<th>Context</th>
|
| 350 |
-
<th>Memory (FP16)</th>
|
| 351 |
-
</tr>
|
| 352 |
-
</thead>
|
| 353 |
-
<tbody>
|
| 354 |
-
<tr>
|
| 355 |
-
<td>
|
| 356 |
-
<a href="https://huggingface.co/Lyon28/caca-10m" target="_blank">caca-10M</a>
|
| 357 |
-
</td>
|
| 358 |
-
<td>10M</td>
|
| 359 |
-
<td>256</td>
|
| 360 |
-
<td>8</td>
|
| 361 |
-
<td>8</td>
|
| 362 |
-
<td>2</td>
|
| 363 |
-
<td>8K</td>
|
| 364 |
-
<td>~0.02 GB</td>
|
| 365 |
-
</tr>
|
| 366 |
-
<tr>
|
| 367 |
-
<td>
|
| 368 |
-
<a href="https://huggingface.co/Lyon28/caca-50m" target="_blank">caca-50M</a>
|
| 369 |
-
</td>
|
| 370 |
-
<td>50M</td>
|
| 371 |
-
<td>512</td>
|
| 372 |
-
<td>12</td>
|
| 373 |
-
<td>8</td>
|
| 374 |
-
<td>2</td>
|
| 375 |
-
<td>8K</td>
|
| 376 |
-
<td>~0.1 GB</td>
|
| 377 |
-
</tr>
|
| 378 |
-
<tr>
|
| 379 |
-
<td>
|
| 380 |
-
<a href="https://huggingface.co/Lyon28/caca-100m" target="_blank">caca-100M</a>
|
| 381 |
-
</td>
|
| 382 |
-
<td>100M</td>
|
| 383 |
-
<td>768</td>
|
| 384 |
-
<td>12</td>
|
| 385 |
-
<td>12</td>
|
| 386 |
-
<td>3</td>
|
| 387 |
-
<td>8K</td>
|
| 388 |
-
<td>~0.2 GB</td>
|
| 389 |
-
</tr>
|
| 390 |
-
</tbody>
|
| 391 |
-
</table>
|
| 392 |
-
|
| 393 |
-
</details>
|
| 394 |
-
|
| 395 |
-
<details>
|
| 396 |
-
<summary>
|
| 397 |
-
<strong>🦅 Medium Models (1B - 10B)</strong>
|
| 398 |
-
</summary>
|
| 399 |
-
|
| 400 |
-
<p>Cocok untuk: Aplikasi production, fine-tuning, domain-specific tasks</p>
|
| 401 |
-
|
| 402 |
-
<p><em>Click to expand for model list...</em></p>
|
| 403 |
-
|
| 404 |
-
</details>
|
| 405 |
-
|
| 406 |
-
<!--
|
| 407 |
-
CODE BLOCKS dengan syntax highlighting
|
| 408 |
-
-->
|
| 409 |
-
|
| 410 |
-
<h2>🚀 Quick Start</h2>
|
| 411 |
-
|
| 412 |
-
<h3>💻 Installation</h3>
|
| 413 |
-
|
| 414 |
-
<pre><code class="language-bash"># Install dengan xFormers untuk speedup 3x
|
| 415 |
-
pip install caca-transformers[xformers]
|
| 416 |
-
|
| 417 |
-
# Atau manual
|
| 418 |
-
pip install caca-transformers
|
| 419 |
-
pip install xformers
|
| 420 |
-
|
| 421 |
-
# Untuk Flash Attention (4x speedup) - opsional
|
| 422 |
-
pip install flash-attn --no-build-isolation
|
| 423 |
-
</code></pre>
|
| 424 |
-
|
| 425 |
-
<h3>Penggunaan Dasar</h3>
|
| 426 |
-
|
| 427 |
-
<pre><code class="language-python">from caca_transformers import CacaForCausalLM, CacaConfig
|
| 428 |
-
import torch
|
| 429 |
-
|
| 430 |
-
# Load model
|
| 431 |
-
model = CacaForCausalLM.from_pretrained("Lyon28/caca-10m")
|
| 432 |
-
|
| 433 |
-
# Atau buat dari scratch
|
| 434 |
-
config = CacaConfig()
|
| 435 |
-
model = CacaForCausalLM(config)
|
| 436 |
-
|
| 437 |
-
# Info model
|
| 438 |
-
print(f"Parameters: {model.num_parameters():,}")
|
| 439 |
-
</code></pre>
|
| 440 |
-
|
| 441 |
-
<!--
|
| 442 |
-
INLINE ELEMENTS
|
| 443 |
-
-->
|
| 444 |
-
|
| 445 |
-
<h2>💡 Tips & Best Practices</h2>
|
| 446 |
-
|
| 447 |
-
<p>
|
| 448 |
-
Gunakan <kbd>Ctrl</kbd> + <kbd>C</kbd> untuk copy code.
|
| 449 |
-
Parameter <code>learning_rate</code> sebaiknya <mark>3e-4</mark> untuk pretraining.
|
| 450 |
-
Formula RMSNorm: <code>x / RMS(x) * γ</code> dimana
|
| 451 |
-
RMS(x) = <code>sqrt(mean(x<sup>2</sup>) + ε)</code>
|
| 452 |
-
</p>
|
| 453 |
-
|
| 454 |
-
<p>
|
| 455 |
-
<small>
|
| 456 |
-
<em>Note: Semua nilai adalah perkiraan dan dapat bervariasi</em>
|
| 457 |
-
</small>
|
| 458 |
-
</p>
|
| 459 |
-
|
| 460 |
-
<p>
|
| 461 |
-
Referensi: <cite>Attention is All You Need</cite> (Vaswani et al., 2017)
|
| 462 |
-
</p>
|
| 463 |
-
|
| 464 |
-
<!--
|
| 465 |
-
MIXED CONTENT TABLE
|
| 466 |
-
-->
|
| 467 |
-
|
| 468 |
-
<h2>📊 Perbandingan dengan Arsitektur Lain</h2>
|
| 469 |
-
|
| 470 |
-
<table>
|
| 471 |
-
<thead>
|
| 472 |
-
<tr>
|
| 473 |
-
<th rowspan="2">Feature</th>
|
| 474 |
-
<th colspan="2">Decoder-Only</th>
|
| 475 |
-
<th colspan="2">Others</th>
|
| 476 |
-
</tr>
|
| 477 |
-
<tr>
|
| 478 |
-
<th>Caca</th>
|
| 479 |
-
<th>LLaMA 2</th>
|
| 480 |
-
<th>GPT-3</th>
|
| 481 |
-
<th>BERT</th>
|
| 482 |
-
</tr>
|
| 483 |
-
</thead>
|
| 484 |
-
<tbody>
|
| 485 |
-
<tr>
|
| 486 |
-
<td>GQA</td>
|
| 487 |
-
<td align="center">✅</td>
|
| 488 |
-
<td align="center">✅</td>
|
| 489 |
-
<td align="center">❌</td>
|
| 490 |
-
<td align="center">❌</td>
|
| 491 |
-
</tr>
|
| 492 |
-
<tr>
|
| 493 |
-
<td>RoPE</td>
|
| 494 |
-
<td align="center">✅</td>
|
| 495 |
-
<td align="center">✅</td>
|
| 496 |
-
<td align="center">❌</td>
|
| 497 |
-
<td align="center">❌</td>
|
| 498 |
-
</tr>
|
| 499 |
-
<tr>
|
| 500 |
-
<td>Open Source</td>
|
| 501 |
-
<td align="center">✅</td>
|
| 502 |
-
<td align="center">✅</td>
|
| 503 |
-
<td align="center">❌</td>
|
| 504 |
-
<td align="center">✅</td>
|
| 505 |
-
</tr>
|
| 506 |
-
</tbody>
|
| 507 |
-
</table>
|
| 508 |
-
|
| 509 |
-
<!--
|
| 510 |
-
FOOTER SECTION
|
| 511 |
-
-->
|
| 512 |
-
|
| 513 |
-
<hr/>
|
| 514 |
-
|
| 515 |
-
<div align="center">
|
| 516 |
-
|
| 517 |
-
<h2>🌟 Star History</h2>
|
| 518 |
-
|
| 519 |
-
<a href="https://star-history.com/#Lyon-28/caca-transformers&Date" target="_blank" rel="noopener noreferrer">
|
| 520 |
-
<img
|
| 521 |
-
src="https://api.star-history.com/svg?repos=Lyon-28/caca-transformers&type=Date"
|
| 522 |
-
alt="Star History Chart"
|
| 523 |
-
title="View Star History"
|
| 524 |
-
width="100%"
|
| 525 |
-
loading="lazy"
|
| 526 |
-
/>
|
| 527 |
-
</a>
|
| 528 |
-
|
| 529 |
-
</div>
|
| 530 |
-
|
| 531 |
-
<hr/>
|
| 532 |
-
|
| 533 |
-
<div align="center">
|
| 534 |
-
|
| 535 |
-
<p>
|
| 536 |
-
<strong>🚀 Built with ❤️ for the Indonesian AI Community</strong>
|
| 537 |
-
</p>
|
| 538 |
-
|
| 539 |
-
<p>
|
| 540 |
-
<a href="https://github.com/Lyon-28/caca-transformers" target="_blank" rel="noopener noreferrer">GitHub</a>
|
| 541 |
-
•
|
| 542 |
-
<a href="https://huggingface.co/Lyon28" target="_blank" rel="noopener noreferrer">Hugging Face</a>
|
| 543 |
-
</p>
|
| 544 |
-
|
| 545 |
-
<p>
|
| 546 |
-
<small>
|
| 547 |
-
<strong>Dibuat oleh
|
| 548 |
-
<a href="https://huggingface.co/Lyon28" target="_blank" rel="noopener noreferrer">Lyon</a>
|
| 549 |
-
</strong>
|
| 550 |
-
<br/>
|
| 551 |
-
Apache 2.0 License | 2025
|
| 552 |
-
</small>
|
| 553 |
-
</p>
|
| 554 |
-
|
| 555 |
-
</div>
|
| 556 |
-
|
| 557 |
-
<!--
|
| 558 |
-
TODO:
|
| 559 |
-
- Add more model variants
|
| 560 |
-
- Include benchmark results
|
| 561 |
-
- Add training scripts
|
| 562 |
-
-->
|
|
|
|
| 53 |
|
| 54 |
## Credits
|
| 55 |
|
| 56 |
+
Created by Lyon28
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|