Instructions to use idirectships/abacus-cheat-tell-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use idirectships/abacus-cheat-tell-v1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="idirectships/abacus-cheat-tell-v1")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("idirectships/abacus-cheat-tell-v1") model = AutoModelForSequenceClassification.from_pretrained("idirectships/abacus-cheat-tell-v1") - Notebooks
- Google Colab
- Kaggle
| { | |
| "base_model_id": "answerdotai/ModernBERT-base", | |
| "n_positives": 400, | |
| "n_negatives": 400, | |
| "n_train": 720, | |
| "n_eval": 80, | |
| "epochs": 3, | |
| "batch_size": 8, | |
| "grad_accumulation": 4, | |
| "effective_batch": 32, | |
| "lr": 2e-05, | |
| "warmup_ratio": 0.1, | |
| "label_map": { | |
| "authentic": 0, | |
| "anachronism": 1 | |
| }, | |
| "id_to_label": { | |
| "0": "authentic", | |
| "1": "anachronism" | |
| }, | |
| "decision_ref": "Decision #53 \u2014 W7.2 Colab T4 production run", | |
| "eval_results": { | |
| "accuracy": 1.0, | |
| "f1_anachronism": 1.0, | |
| "precision": 1.0, | |
| "recall": 1.0, | |
| "post_1930_detection_rate": 1.0, | |
| "pre_1930_detection_rate": 0.0, | |
| "detection_delta": 1.0, | |
| "baseline_delta": 0.1205, | |
| "criterion_passed": true | |
| }, | |
| "w71_baseline": { | |
| "post_1930_rate": 0.5524, | |
| "pre_1930_rate": 0.4319, | |
| "delta": 0.1205 | |
| }, | |
| "hf_repo": "idirectships/abacus-cheat-tell-v1", | |
| "output_dir": "/tmp/abacus-cheat-tell-w72" | |
| } |