Move updated checkpoints under checkpoints

README.md

@@ -26,8 +26,8 @@ The updated checkpoints were trained with diffusion loss only on the omni-modal
 
 | Model | Training step | Status | File |
 |---|---:|---|---|
-| OMG 100M | 158,000 | Recommended | `updated/100m/sstep=158000.ckpt` |
-| OMG 300M | 154,000 | Experimental | `updated/300m/sstep=154000.ckpt` |
+| OMG 100M | 158,000 | Recommended | `checkpoints/updated/100m/sstep=158000.ckpt` |
+| OMG 300M | 154,000 | Experimental | `checkpoints/updated/300m/sstep=154000.ckpt` |
 
 The updated models improve the principal fixed-manifest text, audio-distribution, and HumanRef fidelity metrics over the paper 100M checkpoint. The 300M checkpoint remains experimental because simple-command rollout quality is not uniformly better than the updated 100M checkpoint.
 

SHA256SUMS

@@ -2,6 +2,6 @@
 df4ce9aeced84fd96a39583c7f6e2c5773b76f942cb43012c6c51dd9eb806806  checkpoints/paper/300m/sstep=055000.ckpt
 f13bc58f07f104fcff67e35e79650def0fec5a6eb62a193fa1ae9f979fb911cf  checkpoints/paper/500m/sstep=050000.ckpt
 389fae1aa2ba31234e0ef621706362a19387ac485dce1f929408e06a3b012b2c  checkpoints/paper/50m/sstep=090000.ckpt
-d45c93fb749bfe9d6e2875c60d40a6762c4777dca4f4f63eb59c6f1cdf106f52  updated/100m/sstep=158000.ckpt
-6c2520b76be7a4c76f7d2231d9832cb2c7b4130eb2e271115a52ce77b497ff7c  updated/300m/sstep=154000.ckpt
+d45c93fb749bfe9d6e2875c60d40a6762c4777dca4f4f63eb59c6f1cdf106f52  checkpoints/updated/100m/sstep=158000.ckpt
+6c2520b76be7a4c76f7d2231d9832cb2c7b4130eb2e271115a52ce77b497ff7c  checkpoints/updated/300m/sstep=154000.ckpt
 e346790c5ce33c42840aa19f7fcc2891a4cab27e0d92e23bfaff7d48cb339c40  evaluator/step_004000.pt