Instructions to use Magolor/deepstruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Magolor/deepstruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Magolor/deepstruct")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("Magolor/deepstruct") model = AutoModel.from_pretrained("Magolor/deepstruct") - Notebooks
- Google Colab
- Kaggle
What is the difference between 10B and 10B_1?
#2
by minolee - opened
Hello,
As mentioned in title, I'm curious what is difference between 10B and 10B_1.
In github code, it downloads both 10B and 10B_1. According to scripts in src/tasks/mt, Some tasks(ADE, SNIPS, ...) use 10B model and some(ACE2005, CoNLL05, ...) use 10B_1.
I couldn't find any mention about this. Can you please explain the difference?
Thank you in advance.