Downloads · 30 days
24
15% of all-time downloads
ConicCat/Apertus-AlphaPO-5e-6-8B
Apertus-AlphaPO-5e-6-8B is a text generation model from ConicCat. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Actually functional this time Alpha/SimPO checkpoint trained from Apertus base.
Downloads · 30 days
24
15% of all-time downloads
All-time downloads
162
Public
Parameters
8.1B
16.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors16.1 GB · 100%
From the Hugging Face model README
Actually functional this time Alpha/SimPO checkpoint trained from Apertus base.
Trained on a mix of curated C2, Gutenberg, and Instruct Skill-Mix
Alpaca chat template, temp .5, min_p .05, rep pen 1.05 seems reasonable.
Now I just have to make a better preference dataset...