Downloads · 30 days
35
40% of all-time downloads
DeepSeek-R1-Distill-Llama-8B-Debiased
hirundo-io/DeepSeek-R1-Distill-Llama-8B-Debiased
DeepSeek-R1-Distill-Llama-8B-Debiased is a machine learning model from hirundo-io. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Bias in large language models (LLMs) is a growing concern, particularly in sensitive customer-facing industries where fairness and compliance are critical. With recent buzz around DeepSeek, we took the opportunity to…
All-time downloads
88
Public
Parameters
8B
45.9 GB on disk
Likes
3
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
At a glance
- License
- mit
- Model type
- llama
- Access
- Public
- Created
- Jan 28, 2025
- Updated
- Feb 10, 2025
- SHA
- a5fb85bb
Model card
From the Hugging Face model README
Bias in large language models (LLMs) is a growing concern, particularly in sensitive customer-facing industries where fairness and compliance are critical. With recent buzz around DeepSeek, we took the opportunity to showcase Hirundo’s bias unlearning capabilities on DeepSeek-R1-Distill-Llama-8B. Our results demonstrate that, even with new and emerging models, we can significantly reduce bias—up to 76% reduction as compared to its original state—without compromising model utility on other tasks such as logical QA and reasoning.
- Type
- llama
- License
- mit
- Created
- Jan 28, 2025
- Updated
- Feb 10, 2025