Downloads · 30 days
7
17% of all-time downloads
Qwen2.5-3B-PROSPER
MisDrifter/Qwen2.5-3B-PROSPER
Qwen2.5-3B-PROSPER is a machine learning model from MisDrifter. 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 apache-2.0.
This model improves the instruction-following capabilities of Qwen-2.5-3B-Instruct via preference tuning on the WildChecklists dataset. Full details are provided in Back to Blackwell: Closing the Loop on Intransitivit…
All-time downloads
41
Public
Parameters
3.1B
21.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors21.4 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Feb 1, 2026
- Updated
- Feb 2, 2026
- SHA
- 9a3d509a
Model card
From the Hugging Face model README
Model Card for Model ID
This model improves the instruction-following capabilities of Qwen-2.5-3B-Instruct via preference tuning on the WildChecklists dataset. Full details are provided in Back to Blackwell: Closing the Loop on Intransitivity in Multi-Objective Preference Fine-Tuning.
Evaluation
We report performance on instruction-following and general-chat benchmarks, using GPT-5-mini as the judge. Additional evaluation details and settings are provided in the paper. Alpacaeval/Arena-Hard:
| Model | Alpacaeval (Vanilla) | Alpacaeval (Length-Controlled) | Arena-Hard (Vanilla) | Arena-Hard (Style-Controlled) |
|---|---|---|---|---|
| Qwen-2.5-3B-Instruct | 24.1 | 12.79 | 20.6 | 19.6 |
| + PROSPER | 35.8 | 20.94 | 26.0 | 24.6 |
- Type
- qwen2
- License
- apache-2.0
- Created
- Feb 1, 2026
- Updated
- Feb 2, 2026