Instructions to use anmol-unitmole/longformer-qasper-document-qa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anmol-unitmole/longformer-qasper-document-qa with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="anmol-unitmole/longformer-qasper-document-qa")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("anmol-unitmole/longformer-qasper-document-qa") model = AutoModelForQuestionAnswering.from_pretrained("anmol-unitmole/longformer-qasper-document-qa", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "status": "completed", | |
| "base_model_id": "valhalla/longformer-base-4096-finetuned-squadv1", | |
| "saved_model_path": "C:\\Users\\atripathi\\OneDrive - Veralto\\Desktop\\AI Codes\\GIT Projects\\transformer-projects\\04-long-document-question-answering-longformer\\models\\qasper-longformer", | |
| "profile": { | |
| "name": "high-vram", | |
| "train_examples": null, | |
| "validation_examples": null, | |
| "max_length": 3072, | |
| "stride": 384, | |
| "epochs": 2.0, | |
| "learning_rate": 1e-05, | |
| "train_batch_size": 1, | |
| "eval_batch_size": 1, | |
| "gradient_accumulation_steps": 8, | |
| "save_steps": 200, | |
| "logging_steps": 25 | |
| }, | |
| "seed": 42, | |
| "cuda_available": true, | |
| "gpu_name": "NVIDIA GeForce RTX 5090", | |
| "bf16": true, | |
| "fp16": false, | |
| "training_duration_seconds": 432.16304820001824, | |
| "training_loss": 4.296871501620453, | |
| "global_steps": 202, | |
| "best_model_checkpoint": "C:\\Users\\atripathi\\OneDrive - Veralto\\Desktop\\AI Codes\\GIT Projects\\transformer-projects\\04-long-document-question-answering-longformer\\models\\qasper-longformer\\checkpoint-202", | |
| "best_metric": 4.139431476593018, | |
| "train_features": { | |
| "source_examples": 803, | |
| "training_features": 803, | |
| "dropped_without_answer_window": 0, | |
| "max_length": 3072, | |
| "stride": 384 | |
| }, | |
| "validation_features": { | |
| "source_examples": 419, | |
| "training_features": 419, | |
| "dropped_without_answer_window": 0, | |
| "max_length": 3072, | |
| "stride": 384 | |
| }, | |
| "fine_tuned_by_this_project": true | |
| } |