Instructions to use microsoft/deberta-large-mnli with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use microsoft/deberta-large-mnli with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="microsoft/deberta-large-mnli")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("microsoft/deberta-large-mnli") model = AutoModelForSequenceClassification.from_pretrained("microsoft/deberta-large-mnli") - Inference
- Notebooks
- Google Colab
- Kaggle
Maximum context length
#2
by Jackpot115 - opened
Hi!
The config.json file says that "max_position_embeddings: 512". Does this mean that the maximum length of the text input is 512 tokens? I'm more familiar with decoder-only LLMs where the context window is a lot longer, so I hope to check my understanding.
Thank you in advance!