Synthyra
/

ESMplusplus_large

Model card Files Files and versions Community

lhallee commited on Dec 12, 2024

Commit

0bae73f

·

verified ·

1 Parent(s): ab7f9c5

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -87,7 +87,7 @@ You can load the weights from the ESM package instead of transformers by replaci
 We employ linear probing techniques on various PLMs and standard datasets, similar our previous [paper](https://www.biorxiv.org/content/10.1101/2024.07.30.605924v1), to assess the intrinsic correlation between pooled hidden states and valuable properties. ESMC (and thus ESM++) perform very well.
 The plot below showcases performance normalized between the negative control (random vector embeddings) and the best performer. Classification task scores are averaged between MCC and F1 (or F1max for multilabel) and regression tasks are averaged between Spearman rho and R2.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f2bd3bdb7cbd214b658c48/dcvZhbtR_fJ6KSFYgI6l6.png)
 ## Inference speeds
 We look at various ESM models and their throughput on an H100. Adding efficient batching between ESMC and ESM++ significantly improves the throughput, although ESM++ is also faster than ESMC for batch size one. ESM++ small is even faster than ESM2-35M with long sequences! The most gains will be seen with PyTorch > 2.5 on linux machines.

 We employ linear probing techniques on various PLMs and standard datasets, similar our previous [paper](https://www.biorxiv.org/content/10.1101/2024.07.30.605924v1), to assess the intrinsic correlation between pooled hidden states and valuable properties. ESMC (and thus ESM++) perform very well.
 The plot below showcases performance normalized between the negative control (random vector embeddings) and the best performer. Classification task scores are averaged between MCC and F1 (or F1max for multilabel) and regression tasks are averaged between Spearman rho and R2.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f2bd3bdb7cbd214b658c48/uRAHYQcwkbgajylTIFbUb.png)
 ## Inference speeds
 We look at various ESM models and their throughput on an H100. Adding efficient batching between ESMC and ESM++ significantly improves the throughput, although ESM++ is also faster than ESMC for batch size one. ESM++ small is even faster than ESM2-35M with long sequences! The most gains will be seen with PyTorch > 2.5 on linux machines.