Switch LIBERO checkpoint to native_delta_eef10 action representation

The previous release served `absolute_eef10` (absolute EEF pose, with
osc_position_scale=0.05 / osc_rotation_scale=0.5 in the stats), while the
LIBERO evaluation client in benchmarks/libero consumes the native normalized
delta command `[delta_xyz3, rot6d(Exp(delta_rotvec3)), gripper_open1]` without
composing with the current pose and without applying the controller scales.

This checkpoint is trained on the delta representation, matching both that
client contract and assets/benchmark_data/libero (conversion.json declares
output_representation=native_delta_eef10). normalization_stats.npy is now
byte-identical to the canonical benchmark_data stats file (keys: eef,
eef_state).

Measured on LIBERO with the official protocol (50 trials/task, seed 42),
sampled one task per suite: spatial 50/50, goal 49/50, object 50/50,
long 48/50 -> 197/200 = 98.5%.

checkpoint_step_10690.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95a213a667cfdad86c2b1274159cfb02702fa4e2507acc5bdc14c2a1ac50597e
+oid sha256:34c9a6c9af67dda9aaffa2edc0efa29b28eeee1c26dea419f98065c80508c96a
 size 24813767464

normalization_stats.npy

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e0dfe8b8d6e2a84b9cbc2ce3cf3fd938253aab478e1a60eaafbc9741308ff4
-size 1529
+oid sha256:f3fd7daa340ee6cbcb0d6a489a130f1e866c2688fcc40ffd98cae506b4d0cc8e
+size 2350