Downloads · 30 days
14
0% of all-time downloads
etri-xainlp/SOLAR-10.7B-merge-dpo
SOLAR-10.7B-merge-dpo is a text generation model from etri-xainlp. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as cc-by-nc-4.0.
Downloads · 30 days
14
0% of all-time downloads
All-time downloads
34.9K
Public
Parameters
10.7B
21.5 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors21.5 GB · 100%
From the Hugging Face model README
Model Developers ETRI xainlp team
Input text only.
Output text only.
Model Architecture
We used MergeKit to merge Model heavytail/kullm-solar into Model upstage/SOLAR-10.7B-Instruct-v1.0 as the base.
Base Model upstage/SOLAR-10.7B-Instruct-v1.0
Merge Model heavytail/kullm-solar
Training Dataset
dpo+lora: 90k user preference set
We use A100 GPU 80GB * 1, when training.