Downloads · 30 days
17
33% of all-time downloads
RichardErkhov/wandb_-_gemma-2b-zephyr-dpo-awq
wandb_-_gemma-2b-zephyr-dpo-awq 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.
Downloads · 30 days
17
33% of all-time downloads
All-time downloads
52
Public
Parameters
2.5B
2.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors2.1 GB · 98%
How the weights are stored.
I322B · 79%
From the Hugging Face model README
Quantization made by Richard Erkhov.
gemma-2b-zephyr-dpo - AWQ
license: other library_name: transformers datasets:
The Zephyr DPO recipe applied on top of SFT finetuned Gemma 2B
We trained using the DPO script in alignment handbook recipe and logging to W&B
Visit the W&B workspace here
This model has the same license as the original Gemma model collection
around 13 hours of training