You can deploy this model and start earning money today!

athul020/
pdw_final_dora

Name: pdw_final_dora
Availability: InStock

Views

No views yet

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

python

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