Downloads · 30 days
8
32% of all-time downloads
pdw_final_dora
athul020/pdw_final_dora
pdw_final_dora is a machine learning model from athul020. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft.
A DoRA (Weight-Decomposed Low-Rank Adaptation) adapter for CogVideoX-2b, fine-tuned to generate physically accurate videos using NVIDIA Warp physics simulation data and TRD (Temporal Representation Distillation) with…
All-time downloads
25
Public
Repo size
30.5 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors30.5 MB · 100%
At a glance
- Library
- peft
- Access
- Public
- Created
- Mar 4, 2026
- Updated
- Mar 4, 2026
- SHA
- 12cfa0fd
Base models
Model card
From the Hugging Face model README
PDW — Physics-Corrected CogVideoX-2b World Model (DoRA Adapter)
A DoRA (Weight-Decomposed Low-Rank Adaptation) adapter for CogVideoX-2b, fine-tuned to generate physically accurate videos using NVIDIA Warp physics simulation data and TRD (Temporal Representation Distillation) with DINOv2-large as teacher.
Model Details
- Base model: THUDM/CogVideoX-2b (1.7B params)
- Adapter: DoRA (r=16, lora_alpha=32, use_dora=True)
- Target modules:
to_q,to_k,to_v,to_out.0 - Trainable params: 7.6M / 1.7B (0.45%)
- Physics engine: NVIDIA Warp (28-scenario 7×4 grid)
- TRD teacher: DINOv2-large
- Hardware: NVIDIA H100 NVL
- Training steps: 400
Evaluation Results
| Metric | Delta |
|---|---|
| Diffusion MSE | +94.1% |
| Motion score | +1.7% |
| Overall | +47.9% |
How to Use
from peft import PeftModel
from diffusers import CogVideoXTransformer3DModel
# Load base transformer
base_transformer = CogVideoXTransformer3DModel.from_pretrained(
"THUDM/CogVideoX-2b", subfolder="transformer"
)
# Load DoRA adapter
model = PeftModel.from_pretrained(base_transformer, "athul020/pdw_final_dora")
Framework versions
- PEFT 0.18.1
- Library
- peft
- Created
- Mar 4, 2026
- Updated
- Mar 4, 2026