Archive README

README.md

@@ -0,0 +1,36 @@
+---
+license: other
+license_name: nvidia-open-model-license
+base_model: GEAR-Dreams/DreamZero-AgiBot
+tags:
+  - robotics
+  - world-action-model
+  - dreamzero
+  - yam
+---
+
+# dreamzero-yam-molmoact2-checkpoints
+
+Training-run archive for
+[robocurve/dreamzero-yam-molmoact2](https://huggingface.co/robocurve/dreamzero-yam-molmoact2)
+(the merged release; start there). Training code, eval protocol, and model
+card: [robocurve/dreamzero-yam](https://github.com/robocurve/dreamzero-yam).
+
+Contents:
+
+- `checkpoints/step-N/` — all 26 raw LoRA training milestones, weights only
+  (steps 100, 200, 300, then every 500 from 1,000 to 12,000; DeepSpeed
+  optimizer shards are omitted). **Do not load these with stock
+  `load_lora`** — it rebuilds the frozen DiT on vanilla Wan2.1 instead of
+  the DreamZero-AgiBot base they were trained against. Use the explicit
+  reconstruction in
+  [`src/reconstruct.py`](https://github.com/robocurve/dreamzero-yam/blob/main/src/reconstruct.py).
+- `training-state/checkpoint-12000/` — the final checkpoint with full
+  DeepSpeed optimizer state, resumable for continued training (the val/loss
+  curve had plateaued but not risen at 12k steps). Earlier milestones can be
+  warm-started weights-only via the training repo's
+  `--allow-fresh-optimizer` path.
+- `training-state/` top level — trainer state, run config, per-step runtime
+  metrics, and loss logs of the main run.
+- `renders/` — imagined-vs-real rollout videos from the released checkpoint
+  (model's 2x2 camera-grid dream next to ground-truth frames).