ESM2 Models
Collection
14 items • Updated • 1
How to use gabrielbianchin/esm2_t6_long with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("fill-mask", model="gabrielbianchin/esm2_t6_long") # Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("gabrielbianchin/esm2_t6_long")
model = AutoModelForMaskedLM.from_pretrained("gabrielbianchin/esm2_t6_long")ESM2 Long is an adapted version of the ESM2 architectures. It uses local attention instead of global attention, allowing for models with longer input sizes. ESM2 Long models have a context size of 2,050, double that of the standard ESM2 model. Several ESM2 Long models are available:
| Model | Num layers |
|---|---|
| gabrielbianchin/esm2_t33_long | 33 |
| gabrielbianchin/esm2_t30_long | 30 |
| gabrielbianchin/esm2_t12_long | 12 |
| gabrielbianchin/esm2_t6_long | 6 |
For detailed information, please refer to the paper.