Downloads · 30 days
4
1% of all-time downloads
Llama-3.1-8B-NBPO-UltraFeedback-600updates
promotion/Llama-3.1-8B-NBPO-UltraFeedback-600updates
Llama-3.1-8B-NBPO-UltraFeedback-600updates is a text generation model from promotion. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as llama3.1.
The optimiser-budget ablation: identical to the reported arm except for twice the updates. Held-out fit is unchanged (nMSE 0.9836 vs 0.9833) but the policy travels further and the worst-objective win rate is 0.537 vs…
All-time downloads
405
Public
Parameters
8B
32.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors32.1 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3.1
- Model type
- llama
- Access
- Public
- Created
- Sep 7, 2026
- Updated
- Sep 7, 2026
- SHA
- 0322174c
Try a prompt
Base models
Model card
From the Hugging Face model README
NBPO on UltraFeedback, 600 updates
The optimiser-budget ablation: identical to the reported arm except for twice the updates. Held-out fit is unchanged (nMSE 0.9836 vs 0.9833) but the policy travels further and the worst-objective win rate is 0.537 vs 0.524. Not the reported configuration: no training-side quantity selects it.
- Panel: UltraFeedback
- Objectives: instruction following, truthfulness, honesty, helpfulness
- Backbone / reference policy:
meta-llama/Llama-3.1-8B-Instruct - Training budget: 300 optimiser updates, global batch 16
- Reported in: Nash Bargaining Preference Optimization (NBPO), Appendix: optimiser-budget sensitivity
Evaluation protocol: independent objective-wise win rate against the common reference,
judged by Llama-3.3-70B-Instruct on prompt-disjoint held-out prompts, both presentation orders.
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- llama3.1
- Created
- Sep 7, 2026
- Updated
- Sep 7, 2026