Instructions to use Doohae/roberta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Doohae/roberta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Doohae/roberta")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Doohae/roberta") model = AutoModelForQuestionAnswering.from_pretrained("Doohae/roberta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| epoch = 10.0 | |
| init_mem_cpu_alloc_delta = 955506688 | |
| init_mem_cpu_peaked_delta = 1337384960 | |
| init_mem_gpu_alloc_delta = 1343489024 | |
| init_mem_gpu_peaked_delta = 0 | |
| train_mem_cpu_alloc_delta = 391798784 | |
| train_mem_cpu_peaked_delta = 448819200 | |
| train_mem_gpu_alloc_delta = 4055639040 | |
| train_mem_gpu_peaked_delta = 10974608384 | |
| train_runtime = 17438.5747 | |
| train_samples = 17427 | |
| train_samples_per_second = 1.25 | |