Update README.md

README.md

@@ -43,7 +43,7 @@ model = AutoModelForMaskedLM.from_pretrained('Synthyra/ESMplusplus_small', trust
 ```
 
 ## Embed entire datasets with no new code
-To embed a list of protein sequences **fast**, just call embed_dataset. Sequences are sorted to reduce padding tokens, so the progress bar is usually much longer than the actual time.
+To embed a list of protein sequences **fast**, just call embed_dataset. Sequences are sorted to reduce padding tokens, so the initial progress bar estimation is usually much longer than the actual time.
 ```python
 embeddings = model.embed_dataset(
     sequences=sequences, # list of protein strings
@@ -92,7 +92,7 @@ The plot below showcases performance normalized between the negative control (ra
 ## 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. ESM++ small is even faster than ESM2-35M with long sequences!
 The most gains will be seen with PyTorch > 2.5 on linux machines.
-![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f2bd3bdb7cbd214b658c48/NNmbupdIxuieuyjc8vMuj.png)
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/62f2bd3bdb7cbd214b658c48/aqe1nozNdwaL0bgaUKBPp.png)
 
 ### Citation
 If you use any of this implementation or work please cite it (as well as the ESMC preprint). Bibtex for both coming soon.