# Hugging Face — Accelerating Protein Language Model ProtST on Intel Gaudi 2

- Company: Hugging Face (huggingface.co)
- Announced: 2024-07-03T00:00:00+00:00
- Subject: Platform
- Models affected: ProtST, ProtST-ESM-1b, ProtST-ESM1b-for-sequential-classification
- Source: https://huggingface.co/blog/intel-protein-language-model-protst
- Record: https://forck.live/items/1862-accelerating-protein-language-model-protst-on-intel-gaudi-2

This blog post demonstrates how to run inference and fine-tuning of the ProtST protein language model on Intel Gaudi 2 accelerators using the Optimum for Intel Gaudi library, achieving 1.76x faster inference and 2.92x faster fine-tuning compared to NVIDIA A100.

## Evidence

Verbatim from https://huggingface.co/blog/intel-protein-language-model-protst:

> our results show competitive performance against A100, with a 1.76x speedup for inference and a 2.92x speedup for fine-tuning.

---

Record: https://forck.live/items/1862-accelerating-protein-language-model-protst-on-intel-gaudi-2
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md