Transformers
Safetensors
t5
text2text-generation
protein-language-model
fastplms
custom_code
text-generation-inference
Instructions to use Synthyra/ANKH_large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Synthyra/ANKH_large with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Synthyra/ANKH_large", trust_remote_code=True) model = AutoModelForSeq2SeqLM.from_pretrained("Synthyra/ANKH_large", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
metadata
{}
Encoder only version of the ANKH large model (paper). The encoder only version is ideal for protein representation tasks.
To download
from transformers import T5EncoderModel, AutoTokenizer
model_path = 'Synthyra/ANKH_large'
model = T5EncoderModel.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
We are working on implementing a version of T5 based PLMs with Flex attention once learned relative position bias is supported (used in T5). Stay tuned.