🌍 A minimalist repository for training video world models based on diffusion-forcing. • 20 items • Updated • 7
NanoWM-B/2 · rt1 · NanoWM-B/2 on RT-1
NanoWM-B/2 on RT-1 (300k steps)
Run identity
- wandb: https://wandb.ai/better_guidance/nano-world-model-phase2/runs/lho54iwn
- launcher:
src/scripts/phase2/rt1.sh - collection: https://huggingface.co/collections/knightnemo/nano-world-model
Training setup
| Key | Value |
|---|---|
| Architecture | NanoWM-B/2 |
| Dataset | rt1 |
| Prediction | v |
| Noise schedule | squaredcos_cap_v2 (ZTSNR=True) |
| Steps | 300000 |
| Batch | 8/GPU |
Loading
import sys
from omegaconf import OmegaConf
from safetensors.torch import load_file
sys.path.insert(0, "src")
from models import get_models
cfg = OmegaConf.load("ckpt/config.yaml")
cfg.experiment.infra.compile = False
model = get_models(cfg).eval()
state_dict = load_file("ckpt/model.safetensors")
model.load_state_dict(state_dict, strict=True)
- Downloads last month
- 35
Safetensors
Model size
0.2B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support