Link KineWorld source and mark checkpoint transfer in progress
Browse files
README.md
CHANGED
|
@@ -11,6 +11,8 @@ tags:
|
|
| 11 |
|
| 12 |
# KineWorld step-500 checkpoint
|
| 13 |
|
|
|
|
|
|
|
| 14 |
This repository contains the complete `step-500.safetensors` checkpoint from a KineWorld training run and its paired `action_norm_stats.npz`. The run completed 500 optimizer steps on 24 accelerators. This release includes a public training configuration with machine-specific paths removed.
|
| 15 |
|
| 16 |
KineWorld uses a Wan2.2-TI2V-5B video backbone with an RGB/optical-flow dual-stream model and an action-prediction module. The run used RoboTwin head-camera data, 14-dimensional actions, and robot-only optical flow. It was initialized from an earlier action/world-model checkpoint rather than trained from scratch. The warm-start checkpoint SHA-256 is `21940bd45e95dc39bc3b166c6ecd2a777efa01c8068124958778173cd01ddf66`.
|
|
@@ -36,4 +38,4 @@ The checkpoint file is complete and its local SHA-256 was verified before upload
|
|
| 36 |
- Warm-start checkpoint SHA-256: `21940bd45e95dc39bc3b166c6ecd2a777efa01c8068124958778173cd01ddf66`.
|
| 37 |
- Hyperparameters and model modes: `training_config_public.json`.
|
| 38 |
|
| 39 |
-
For source-code setup and inference commands, see the KineWorld GitHub repository
|
|
|
|
| 11 |
|
| 12 |
# KineWorld step-500 checkpoint
|
| 13 |
|
| 14 |
+
**Release status:** the checkpoint file is uploading. The model card, public configuration, checksums, and paired action-normalization statistics are available.
|
| 15 |
+
|
| 16 |
This repository contains the complete `step-500.safetensors` checkpoint from a KineWorld training run and its paired `action_norm_stats.npz`. The run completed 500 optimizer steps on 24 accelerators. This release includes a public training configuration with machine-specific paths removed.
|
| 17 |
|
| 18 |
KineWorld uses a Wan2.2-TI2V-5B video backbone with an RGB/optical-flow dual-stream model and an action-prediction module. The run used RoboTwin head-camera data, 14-dimensional actions, and robot-only optical flow. It was initialized from an earlier action/world-model checkpoint rather than trained from scratch. The warm-start checkpoint SHA-256 is `21940bd45e95dc39bc3b166c6ecd2a777efa01c8068124958778173cd01ddf66`.
|
|
|
|
| 38 |
- Warm-start checkpoint SHA-256: `21940bd45e95dc39bc3b166c6ecd2a777efa01c8068124958778173cd01ddf66`.
|
| 39 |
- Hyperparameters and model modes: `training_config_public.json`.
|
| 40 |
|
| 41 |
+
For source-code setup and inference commands, see the [KineWorld GitHub repository](https://github.com/pumpkin601/KineWorld).
|