Instructions to use Synthyra/ESMFold2-300 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synthyra/ESMFold2-300 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Synthyra/ESMFold2-300", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Synthyra/ESMFold2-300", trust_remote_code=True) model = AutoModel.from_pretrained("Synthyra/ESMFold2-300", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
12 days ago
-
Update FastPLMs files from Synthyra/FastPLMs 32d9951 (PR 52: ESMFold2 noise cap, DPLM2 parity)
Verified signatureb76d9e3
22 days ago
-
Accept huggingface_hub's shared Xet blob store in the CCD loader (FastPLMs PR 51)
Verified signatureece09aa
28 days ago
-
Sync current FastPLMs source, model cards and dependencies
Verified signature52eec95 -
Embed evaluated confidence head and publish current training metrics
Verified signature960fd25 -
Update FastPLMs files
Verified signaturedcc20cf
29 days ago
-
Support verified live v2 confidence heads
Verified signature33e9b8d -
Apply coding standards from 1cb5747 (files only)
Verified signature809b15a -
Update FastPLMs runtime and cards from 328deef (files only)
Verified signaturee83f063
-
Document the separately trained confidence head results
Verified signature8aedd8b
-
Update FastPLMs runtime and model cards
Verified signaturec5ab962 -
Record published checkpoint pins and validation status
Verified signatured28d60c -
Publish ESMFold2 small backbone checkpoint with FastPLMs runtime
Verified signaturea38a62a