Cards: point links at rfd4-proteina.org docs and the new wordmark

README.md

@@ -13,9 +13,9 @@ tags:
 - annotated-cif
 - diffusers
 ---
-<p align="center"><img src="assets/wordmark.svg" width="560" alt="RFD4-Proteína"></p>
+<p align="center"><picture><source media="(prefers-color-scheme: dark)" srcset="assets/wordmark-dark.webp"><img src="assets/wordmark.webp" width="520" alt="RFD4-Proteína"></picture></p>
 <p align="center"><strong>Sequence and structure, designed together.</strong><br>Baker Lab × NVIDIA GenAIR</p>
-<p align="center"><a href="https://huggingface.co/nvidia/RFD4-Proteina">Original release</a> · <a href="https://github.com/RosettaCommons/RFD4-Proteina">Code</a> · <a href="https://huggingface.co/datasets/nvidia/RFD4-Proteina">Training data</a> · <a href="https://huggingface.co/docs/diffusers/api/pipelines/rfd4_proteina">Diffusers docs</a></p>
+<p align="center"><a href="https://rfd4-proteina.org/">Project page</a> · <a href="https://huggingface.co/nvidia/RFD4-Proteina">Original release</a> · <a href="https://github.com/RosettaCommons/RFD4-Proteina">Code</a> · <a href="https://huggingface.co/datasets/nvidia/RFD4-Proteina">Training data</a> · <a href="https://huggingface.co/docs/diffusers/api/pipelines/rfd4_proteina">Diffusers docs</a></p>
 
 # RFD4-Proteína for Diffusers
 
@@ -165,7 +165,7 @@ With FP32 weights, the Diffusers implementation and the original implementation
 
 ## Training data and limitations
 
-The companion [dataset card](https://huggingface.co/datasets/nvidia/RFD4-Proteina) describes the available training snapshot. Use the model for computational biomolecular design and follow designs with appropriate structural and experimental evaluation. Performance depends on the target, input annotations, sampling settings and training coverage. Generation-only runs omit external refolding and scoring. See the [original model card](https://huggingface.co/nvidia/RFD4-Proteina) for benchmark results and the [evaluation and metrics guide](https://github.com/RosettaCommons/RFD4-Proteina/blob/main/docs/workflow/metrics.md).
+The companion [dataset card](https://huggingface.co/datasets/nvidia/RFD4-Proteina) describes the available training snapshot. Use the model for computational biomolecular design and follow designs with appropriate structural and experimental evaluation. Performance depends on the target, input annotations, sampling settings and training coverage. Generation-only runs omit external refolding and scoring. See the [original model card](https://huggingface.co/nvidia/RFD4-Proteina) for benchmark results and the [evaluation and metrics guide](https://rfd4-proteina.org/latest/how-to/evaluate-with-metrics.html).
 
 ## Attribution and support