MolJEPA-World v2: multi-horizon displacement heads (11-21% better than the v1 Koopman operator, 100% win rate on 23 held-out domains)
5e2a55e verified Download example_inference.py from AdagioBiology/world-v2: direct link, hf CLI and curl.
- Browser
- Download file 2.42 kB
-
https://huggingface.co/AdagioBiology/world-v2/resolve/main/example_inference.py
- Command line
-
hf download hf://AdagioBiology/world-v2/example_inference.py
-
curl -L -o example_inference.py https://huggingface.co/AdagioBiology/world-v2/resolve/main/example_inference.py
2.42 kB
| """MolJEPA-World v2 -- minimal inference demo. | |
| Run from this folder (the model loads itself from the local files): | |
| pip install torch numpy safetensors huggingface_hub | |
| python example_inference.py | |
| """ | |
| import os | |
| import numpy as np | |
| import torch | |
| from modeling_moljepa import load_pretrained, prepare_coords, advance | |
| HERE = os.path.dirname(os.path.abspath(__file__)) | |
| demo = np.load(os.path.join(HERE, "examples", "demo_1a0hA01.npz")) | |
| device = "cuda" if torch.cuda.is_available() else "cpu" | |
| model = load_pretrained() # local folder; or "AdagioBiology/world-v2" | |
| x = prepare_coords(torch.from_numpy(demo["coords_angstrom"])) # (T,N,3) | |
| atom_types = torch.from_numpy(demo["atom_types"]).long() # (N,) | |
| esm = torch.from_numpy(demo["esm2_emb"]).float() # (N,480) | |
| temperature = torch.from_numpy(demo["temperature"]).float() # (T,) | |
| mask = torch.ones(1, x.shape[1]) | |
| with torch.no_grad(): | |
| def encode(frame): | |
| return model.encode(atom_types.unsqueeze(0).to(device), | |
| x[frame:frame + 1].to(device), | |
| atom_mask=mask.to(device), | |
| esm_emb=esm.unsqueeze(0).to(device), | |
| sim_temp=temperature[frame:frame + 1].to(device)) | |
| z0 = encode(0) | |
| z_true = encode(20) # 20 steps x 275 ps = 5.5 ns ahead | |
| for mode in ("direct", "rollout"): # rollout = free-running 1-step, drifts | |
| z_pred = advance(model, z0, frames=20, mode=mode) | |
| mse = float((z_pred - z_true).pow(2).mean()) | |
| per = float((z0 - z_true).pow(2).mean()) | |
| cos = float(torch.nn.functional.cosine_similarity(z_pred, z_true, dim=1)) | |
| print(" %-8s MSE %8.3f | vs persistence %5.2fx | cosine %.4f" | |
| % (mode, mse, mse / per, cos)) | |
| tau = model.koop.timescales(dt_ps=model.config["frame_dt_ps"]) | |
| print("\nKoopman timescales of the v1 encoder (ns):", | |
| np.round(tau[:6].detach().cpu().numpy() / 1000, 1)) | |
| # 3D decode of the rolled latent (distogram -> SMACOF). This path is the | |
| # known weak link of the release; the latent forecast is the measured part. | |
| coords = model.generate_3d(atom_types.unsqueeze(0).to(device), | |
| x[0:1].to(device), z=z0, atom_mask=mask.to(device)) | |
| print("\ndecoded CA trace:", np.asarray(coords).shape, | |
| "(multiply by model.coord_scale for angstrom)") | |