Question Answering
Transformers
PyTorch
TensorFlow
JAX
Rust
Safetensors
English
roberta
Eval Results (legacy)
Instructions to use deepset/roberta-base-squad2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use deepset/roberta-base-squad2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="deepset/roberta-base-squad2")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("deepset/roberta-base-squad2") model = AutoModelForQuestionAnswering.from_pretrained("deepset/roberta-base-squad2") - Inference
- Notebooks
- Google Colab
- Kaggle
What is the word limit for context (question text)
#14
by Vikastp1 - opened
What is the word limit for context (question text)
Vikastp1 changed discussion status to closed
Vikastp1 changed discussion status to open
Vikastp1 changed discussion status to closed
Vikastp1 changed discussion status to open
Based on this max_query_length=64,
Looks like the number of average-sized 4-character words limited for "question text" will be somewhere near 60 words as 1 token = 4 characters implies a total of 250 characters.
Vikastp1 changed discussion status to closed