Downloads · 30 days
9
3% of all-time downloads
Qwen3-8B-RewardedSoups-baseline
promotion/Qwen3-8B-RewardedSoups-baseline
Qwen3-8B-RewardedSoups-baseline 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.
Rewarded Soups (Rame et al., NeurIPS 2023): one DPO expert per objective from the shared Qwen3-8B initialisation, linearly interpolated at lambda = (0.15, 0.15, 0.15, 0.55), chosen on 100 validation prompts only.
All-time downloads
307
Public
Parameters
8.2B
16.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.4 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- llama3.1
- Model type
- qwen3
- Access
- Public
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026
- SHA
- 1740acac
Try a prompt
Base models
Model card
From the Hugging Face model README
Rewarded Soups on the Qwen3-8B backbone
Rewarded Soups (Rame et al., NeurIPS 2023): one DPO expert per objective from the shared Qwen3-8B initialisation, linearly interpolated at lambda = (0.15, 0.15, 0.15, 0.55), chosen on 100 validation prompts only.
- Panel: UltraFeedback / Qwen3-8B
- Objectives: instruction following, truthfulness, honesty, helpfulness
- Backbone / reference policy:
Qwen/Qwen3-8B - Training budget: 300 optimiser updates, global batch 16
- Reported in: Nash Bargaining Preference Optimization (NBPO), Table 1 (general-capability 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
- qwen3
- License
- llama3.1
- Created
- Sep 6, 2026
- Updated
- Sep 6, 2026