Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,55 @@
+---
+license: apache-2.0
+tags:
+  - egowm
+  - wan2.1
+  - hand-pose
+  - camera-pose
+  - egocentric
+library_name: pytorch
+---
+
+# EgoWM Lane B — Wan2.1-T2V-1.3B + cam/hand heads (frozen trunk)
+
+Project: [github.com/geng-haoran/EgoWM](https://github.com/geng-haoran/EgoWM)
+
+This ckpt is Lane B's first real-finetune-at-scale on a single GH200:
+the Wan2.1-T2V-1.3B DiT trunk is **frozen** and 8.37 M trainable parameters
+on the camera + hand regression heads are tuned with rectified-flow latents
+cached from 1,873 ARCTIC clips.
+
+## Held-out evaluation (24-clip val pool, ARCTIC)
+
+| metric | this ckpt | predict-train-mean baseline | Δ |
+|---|---|---|---|
+| Hand 21-keypoint MPJPE (mm) | 195.8 | 207.3 | **-5.5 %** |
+| Hand wrist translation MAE (mm) | 181.8 | 178.1 | **+2.1 %** |
+| Camera translation MAE (cm) | 7.53 | 3.64 | +107.2 % |
+
+Training details: 2000 steps × 1 step/s on the cached-latent ARCTIC pool;
+lr 5e-4; AdamW. Loss curves + per-ckpt eval in the repo (`_viz/21_train_curve.png`,
+`_viz/30_final_summary.png`).
+
+## Loading
+
+```python
+import torch
+from egowm.models.egowm_toy import EgoWMToy
+from egowm.models.wan_load import load_pretrained_wan
+m = EgoWMToy(z_rgb=16, cond_ch=17, dim=1536, ffn_dim=8960, layers=30,
+             heads=12, model_type="t2v", cam_dim=7, hand_dim=61, n_hands=2)
+load_pretrained_wan(m.dit, "Wan2.1-T2V-1.3B/diffusion_pytorch_model.safetensors")
+sd = torch.load("ckpt_step001200.pt", weights_only=False)["state_dict"]
+m.load_state_dict(sd)
+```
+
+## Manifest
+
+Trained on: data_engine/manifests/train_egowm_arctic.jsonl (1873 ARCTIC clips with
+both DA3 metric geometry and Wan2.1-VAE latents cached on disk).
+
+## Lane B / Lane A handoff
+
+This was produced by **h200_1 (Lane B)** of the EgoWM multi-machine sprint. See
+`docs/WORK_CLAIMS.md` + `docs/17_lane_b_e2e_report.md` for the full pipeline,
+HaWoR auto-label outputs, dataset deep-dive PPT, and remaining steps.