Delta-Vector commited on
Commit
2f095b2
·
verified ·
1 Parent(s): 66021fc

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -288,7 +288,7 @@
288
  <body>
289
  <div class="container">
290
  <div class="header">
291
- <h1>François-PE-Huali 12B</h1>
292
  </div>
293
  <div class="info">
294
  <img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/DYgyLUEaHAv9kTffBYH-F.jpeg" alt="Model banner">
@@ -328,6 +328,7 @@
328
  <ul class="composition-list">
329
  <li><span class="model-component"><a href="" target="_blank">GGUF Format</a></span>For use with LLama.cpp & Forks(Coming Soon!)</li>
330
  <li><span class="model-component"><a href="" target="_blank">EXL2 Format</a></span>For use with TabbyAPI (Coming Soon!)</li>
 
331
  </ul>
332
  </div>
333
  </div>
@@ -345,8 +346,8 @@ Can I ask a question?&lt;|im_end|&gt;
345
  </code></pre>
346
  </div>
347
  <div class="section">
348
- <h2>System Prompting</h2>
349
- <p>I would highly recommend using either Euryale's system prompt or the EVA system prompt with the model.</p>
350
  <div class="metrics-section">
351
  <details>
352
  <summary>See Axolotl Config</summary>
@@ -358,7 +359,7 @@ Can I ask a question?&lt;|im_end|&gt;
358
  </div>
359
  <div class="section">
360
  <h2>Training</h2>
361
- <p>The training was done for 1 epoch using 8 x <a href="https://www.nvidia.com/en-us/data-center/h200/">H200s</a> GPUs graciously provided by <a href="https://huggingface.co/kalomaze">Kalomaze</a> for the fine-tuning of the model.</p>
362
  <div class="axolotl-container">
363
  <a href="https://github.com/OpenAccess-AI-Collective/axolotl" target="_blank">
364
  <img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl">
 
288
  <body>
289
  <div class="container">
290
  <div class="header">
291
+ <h1>Sol Reaver 15B</h1>
292
  </div>
293
  <div class="info">
294
  <img src="https://cdn-uploads.huggingface.co/production/uploads/66c26b6fb01b19d8c3c2467b/DYgyLUEaHAv9kTffBYH-F.jpeg" alt="Model banner">
 
328
  <ul class="composition-list">
329
  <li><span class="model-component"><a href="" target="_blank">GGUF Format</a></span>For use with LLama.cpp & Forks(Coming Soon!)</li>
330
  <li><span class="model-component"><a href="" target="_blank">EXL2 Format</a></span>For use with TabbyAPI (Coming Soon!)</li>
331
+ <li><span class="model-component"><a href="" target="_blank">EXL3 Format</a></span>For use with TabbyAPI (Slower on Ampere))</li>
332
  </ul>
333
  </div>
334
  </div>
 
346
  </code></pre>
347
  </div>
348
  <div class="section">
349
+ <h2>Samplers</h2>
350
+ <p>For testing of this model, I used Temp=1, 0.1 Min-P.</p>
351
  <div class="metrics-section">
352
  <details>
353
  <summary>See Axolotl Config</summary>
 
359
  </div>
360
  <div class="section">
361
  <h2>Training</h2>
362
+ <p>The training was done for 2 epoch using 8 x <a href="https://www.nvidia.com/en-us/data-center/h200/">H200s</a> GPUs graciously provided by <a href="https://huggingface.co/kalomaze">Kalomaze</a> for the fine-tuning of the model.</p>
363
  <div class="axolotl-container">
364
  <a href="https://github.com/OpenAccess-AI-Collective/axolotl" target="_blank">
365
  <img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl">