Question Answering
Transformers
PyTorch
Graphcore
roberta
Generated from Trainer
Eval Results (legacy)
Instructions to use nbroad/rob-base-gc1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nbroad/rob-base-gc1 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="nbroad/rob-base-gc1")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("nbroad/rob-base-gc1") model = AutoModelForQuestionAnswering.from_pretrained("nbroad/rob-base-gc1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download train_results.json from nbroad/rob-base-gc1: direct link, hf CLI and curl.
- Browser
- Download file 197 Bytes
-
https://huggingface.co/nbroad/rob-base-gc1/resolve/main/train_results.json
- Command line
-
hf download hf://nbroad/rob-base-gc1/train_results.json
-
curl -L -o train_results.json https://huggingface.co/nbroad/rob-base-gc1/resolve/main/train_results.json
197 Bytes
| { | |
| "epoch": 2.0, | |
| "train_loss": 1.0671158636125415, | |
| "train_runtime": 2476.3519, | |
| "train_samples": 317774, | |
| "train_samples_per_second": 256.584, | |
| "train_steps_per_second": 1.002 | |
| } |