Update model card

README.md

@@ -73,7 +73,7 @@ them locally with `build/jepa-quantize lewm-pusht-f16.gguf out.gguf q6_k -t 32`.
 
 ## Measured
 
-Every figure below is read from a committed artifact of jepa.cpp [`d53ab48`](https://github.com/aselimc/jepa.cpp/commit/d53ab48) by `scripts/hf_publish.py` — [parity](https://aselimc.github.io/jepa.cpp/parity/), [quantization](https://aselimc.github.io/jepa.cpp/quantization/), [accuracy](https://aselimc.github.io/jepa.cpp/accuracy/), [performance](https://aselimc.github.io/jepa.cpp/performance/) and `tests/results/*.json`.
+Every figure below is read from a committed artifact of jepa.cpp [`00bfd4e`](https://github.com/aselimc/jepa.cpp/commit/00bfd4e) by `scripts/hf_publish.py` — [parity](https://aselimc.github.io/jepa.cpp/parity/), [quantization](https://aselimc.github.io/jepa.cpp/quantization/), [accuracy](https://aselimc.github.io/jepa.cpp/accuracy/), [performance](https://aselimc.github.io/jepa.cpp/performance/) and `tests/results/*.json`.
 
 **Imagenette k-NN** — 1000 queries against a gallery of 2000 (`train2000`), the frozen `emb` feature, k = 20 cosine vote. Nothing is trained.
 
@@ -106,7 +106,7 @@ The licence travels inside every GGUF as `general.license` and the origin as `ge
 
 ## Conversion
 
-Produced by jepa.cpp [`d53ab48`](https://github.com/aselimc/jepa.cpp/commit/d53ab48):
+Produced by jepa.cpp [`00bfd4e`](https://github.com/aselimc/jepa.cpp/commit/00bfd4e):
 
 ```bash
 scripts/download_models.sh --convert lewm