Downloads · 30 days
15
5% of all-time downloads
Llama-3.1-8B-FixedReferenceNBPO
promotion/Llama-3.1-8B-FixedReferenceNBPO
Llama-3.1-8B-FixedReferenceNBPO 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.
Matched game-aggregation control: same response pool, temperatures, disagreement point and optimiser budget as NBPO, differing only in how the objective weights are chosen.
All-time downloads
317
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 5, 2026
- Updated
- Sep 5, 2026
- SHA
- a42dcda1
Try a prompt
Base models
Model card
From the Hugging Face model README
FixedReferenceNBPO on UltraFeedback
Matched game-aggregation control: same response pool, temperatures, disagreement point and optimiser budget as NBPO, differing only in how the objective weights are chosen.
- 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 5, 2026
- Updated
- Sep 5, 2026