Instructions to use frett/chinese_extract_longbert with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use frett/chinese_extract_longbert with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="frett/chinese_extract_longbert", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("frett/chinese_extract_longbert", trust_remote_code=True) model = AutoModelForQuestionAnswering.from_pretrained("frett/chinese_extract_longbert", trust_remote_code=True) - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 5.0, | |
| "eval_exact_match": 0.0, | |
| "eval_f1": 0.0, | |
| "eval_runtime": 30.7516, | |
| "eval_samples": 3934, | |
| "eval_samples_per_second": 127.928, | |
| "eval_steps_per_second": 2.016, | |
| "total_flos": 3.611513123226624e+16, | |
| "train_loss": 3.3395631154378256, | |
| "train_runtime": 2548.4435, | |
| "train_samples": 27643, | |
| "train_samples_per_second": 54.235, | |
| "train_steps_per_second": 1.695 | |
| } |