Downloads · 30 days
3
1% of all-time downloads
Llama-3.1-8B-NBPO-UltraFeedback-clean
promotion/Llama-3.1-8B-NBPO-UltraFeedback-clean
Llama-3.1-8B-NBPO-UltraFeedback-clean 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 UltraFeedback NBPO arm retrained on pairs filtered to be prompt-disjoint from the 698 evaluation prompts (37,800 - 34,026 rows over 5,671 prompts). Identical configuration to the released arm otherwise: etat = 1,…
All-time downloads
303
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 6, 2026
- Updated
- Sep 6, 2026
- SHA
- 90c0ccdd
Try a prompt
Base models
Model card
From the Hugging Face model README
NBPO on UltraFeedback (contamination-free rebuild)
The UltraFeedback NBPO arm retrained on pairs filtered to be prompt-disjoint from the 698 evaluation prompts (37,800 -> 34,026 rows over 5,671 prompts). Identical configuration to the released arm otherwise: eta_t = 1, lr 5e-7, 300 updates, batch 2 x 8, Adafactor.
- 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), Table 2 (primary cross-method evaluation)
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 6, 2026
- Updated
- Sep 6, 2026