Downloads · 30 days
26
12% of all-time downloads
DZ-TDPO-Qwen2.5-7B-Instruct
YijunLiao/DZ-TDPO-Qwen2.5-7B-Instruct
DZ-TDPO-Qwen2.5-7B-Instruct is a text generation model from YijunLiao. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Research Preview checkpoint for the paper DZ-TDPO.
All-time downloads
211
Public
Parameters
7.6B
29.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors30.5 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- Dec 9, 2025
- Updated
- Dec 24, 2025
- SHA
- ba8e38f1
Try a prompt
Base models
Model card
From the Hugging Face model README
DZ-TDPO (Qwen2.5-7B)
Research Preview checkpoint for the paper DZ-TDPO.
⚠️ Research Note
This model corresponds to the Scaling Analysis (Section 4.3) of our paper.
Due to the strong 'Parametric Inertia' of larger models, this checkpoint prioritizes Language Stability (Low PPL) over aggressive state updates.
- Win Rate: 50.8% (MSC Dataset)
- Alignment Tax: Negligible (+1.95 PPL)
We release this model to facilitate research into the Capacity-Stability Trade-off in long-context alignment.
🚀 For maximum plasticity and SOTA conflict resolution (55.4% Win Rate), please use our flagship model: DZ-TDPO-Phi-3.5-mini-instruct.
- Task
- Text Generation
- Library
- transformers
- Type
- qwen2
- License
- apache-2.0
- Languages
- en
- Created
- Dec 9, 2025
- Updated
- Dec 24, 2025