Add teacher cache README

teacher_caches/README.md

@@ -0,0 +1,42 @@
+# Teacher Reference Caches
+
+Ready-made teacher reference artifacts for the teacher-normalized
+distribution evaluation of DistillAlign. They replace the
+`teacher-sample` + `extract` stage entirely: pass the `.npz` file to
+`--teacher-features` and only the student side needs to be generated.
+
+## Contents
+
+```text
+wan2.1_t2v_1.3b_reference_vjepa2.npz        V-JEPA2 features, 256 x 2560
+wan2.1_t2v_1.3b_reference_vjepa2.meta.json  extraction + sampling protocol
+wan2.1_t2v_14b_reference_vjepa2.npz
+wan2.1_t2v_14b_reference_vjepa2.meta.json
+```
+
+## Protocol
+
+Both caches follow the paper protocol:
+
+- Teacher: Wan2.1-T2V-1.3B / Wan2.1-T2V-14B, 25-step UniPC, timestep
+  shift 8.0, classifier-free guidance 5.0, official negative prompt.
+- Grid: 16 prompts (`prompts/distribution_eval_16.txt`) x 16 seeds
+  (`11,22,33,42,44,55,66,77,88,123,456,789,2024,3407,7777,9999`),
+  256 samples per teacher.
+- Features: `facebook/vjepa2-vith-fpc64-256`, 8 uniform frames from the
+  first 81 frames, token mean/std concat pooling, L2-normalized, 2560-D.
+
+The exact extractor fingerprint and prompt/seed hash are embedded in each
+`.npz` and validated by the metric CLI, which rejects incompatible student
+caches instead of producing incomparable numbers.
+
+## Usage
+
+```bash
+python evaluate_distribution.py run \
+  --checkpoint checkpoints/distillalign_distill_14b_teacher.pt \
+  --jobs outputs/eval_jobs.jsonl \
+  --teacher-model Wan2.1-T2V-14B \
+  --teacher-features teacher_caches/wan2.1_t2v_14b_reference_vjepa2.npz \
+  --output-dir outputs/my_eval
+```