zerofata
/

MS3.2-PaintedFantasy-Visage-33B

Text Generation

text-generation-inference

Model card Files Files and versions

zerofata commited on Jul 3

Commit

af1ea8a

·

verified ·

1 Parent(s): 224b88b

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -386,7 +386,7 @@ base_model:
     <div class="section-content">
       <p>Creation process: Upscale > Pretrain > SFT > DPO</p>
       <p>All training was qlora (including pretrain).</p>
-      <p>Pretrained on 177MB of data. Dataset consisteted mostly of Light Novels, NSFW stories, SFW stories and filled out with general corpos text from Huggingface FineWeb-2 dataset.</p>
       <p>The model then went through SFT using a dataset of approx 3.6 million tokens, 700 RP conversations, 1000 creative writing / instruct samples and about 100 summaries. The bulk of this data has been made public.</p>
       <p>Finally, DPO was used to make the model more consistent.</p>
       <div class="dropdown-container">

     <div class="section-content">
       <p>Creation process: Upscale > Pretrain > SFT > DPO</p>
       <p>All training was qlora (including pretrain).</p>
+      <p>Pretrained on 177MB of data. Dataset consisteted mostly of Light Novels, NSFW stories, SFW stories and filled out with general corpus text from Huggingface FineWeb-2 dataset.</p>
       <p>The model then went through SFT using a dataset of approx 3.6 million tokens, 700 RP conversations, 1000 creative writing / instruct samples and about 100 summaries. The bulk of this data has been made public.</p>
       <p>Finally, DPO was used to make the model more consistent.</p>
       <div class="dropdown-container">