Instructions to use InstaDeepAI/NTv3_8M_pre with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use InstaDeepAI/NTv3_8M_pre with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="InstaDeepAI/NTv3_8M_pre", trust_remote_code=True)# Load model directly from transformers import AutoModelForMaskedLM model = AutoModelForMaskedLM.from_pretrained("InstaDeepAI/NTv3_8M_pre", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
tryin to get access to the project
#2
by noabotnet - opened
would like for help, this is my code:
print("loading torch")
import torch
def load_model():
from huggingface_hub import login
login(token="XXXXXXXXXXXXXXXXXXXXXXXXX")
print("loading transformets")
from transformers import AutoTokenizer, AutoModelForMaskedLM
print("create model and tokinzer")
model_name = "InstaDeepAI/NTv3_8M_pre"
device = "cuda" if torch.cuda.is_available() else "cpu"
repo = "InstaDeepAI/NTv3_8M_pre"
tok = AutoTokenizer.from_pretrained(repo, trust_remote_code=True)
model = AutoModelForMaskedLM.from_pretrained(repo, trust_remote_code=True)
model.eval()
return model, tok, device