knightnemo/nanowm-b2-rt1-300k

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)