Downloads · 30 days
179
12% of all-time downloads
dddsaty_-_KoSOLAR-10.7B_DPO_Adapter_Attach-gguf
RichardErkhov/dddsaty_-_KoSOLAR-10.7B_DPO_Adapter_Attach-gguf
dddsaty_-_KoSOLAR-10.7B_DPO_Adapter_Attach-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
1.4K
Public
Repo size
123 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf142 GB · 100%
At a glance
- Access
- Public
- Created
- Jul 27, 2024
- Updated
- Jul 28, 2024
- SHA
- feffaf36
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
KoSOLAR-10.7B_DPO_Adapter_Attach - GGUF
- Model creator: https://huggingface.co/dddsaty/
- Original model: https://huggingface.co/dddsaty/KoSOLAR-10.7B_DPO_Adapter_Attach/
Original model description:
license: apache-2.0 datasets: We-Want-GPU/Yi-Ko-DPO-Orca-DPO-Pairs language:
- ko pipeline_tag: text-generation
Explanation
- With the base model, applied DPO to the small amount of layers with the open dataset , saved the adapter part
- Attached the base model and the tuned adapter together
Base Model
Used Corpus
Score
| Average | Ko-ARC | Ko-HellaSwag | Ko-MMLU | Ko-TruthfulQA | Ko-CommonGen V2 |
|---|---|---|---|---|---|
| 56.24 | 53.33 | 64.36 | 55.63 | 45.42 | 62.46 |
Log
- 2024.02.13: Initial version Upload
LICENSE
- Apache 2.0
- Created
- Jul 27, 2024
- Updated
- Jul 28, 2024