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
Upload abacus_cheat_tell_meta.json with huggingface_hub
Browse files- abacus_cheat_tell_meta.json +40 -0
abacus_cheat_tell_meta.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_id": "answerdotai/ModernBERT-base",
|
| 3 |
+
"n_positives": 400,
|
| 4 |
+
"n_negatives": 400,
|
| 5 |
+
"n_train": 720,
|
| 6 |
+
"n_eval": 80,
|
| 7 |
+
"epochs": 3,
|
| 8 |
+
"batch_size": 8,
|
| 9 |
+
"grad_accumulation": 4,
|
| 10 |
+
"effective_batch": 32,
|
| 11 |
+
"lr": 2e-05,
|
| 12 |
+
"warmup_ratio": 0.1,
|
| 13 |
+
"label_map": {
|
| 14 |
+
"authentic": 0,
|
| 15 |
+
"anachronism": 1
|
| 16 |
+
},
|
| 17 |
+
"id_to_label": {
|
| 18 |
+
"0": "authentic",
|
| 19 |
+
"1": "anachronism"
|
| 20 |
+
},
|
| 21 |
+
"decision_ref": "Decision #53 \u2014 W7.2 Colab T4 production run",
|
| 22 |
+
"eval_results": {
|
| 23 |
+
"accuracy": 1.0,
|
| 24 |
+
"f1_anachronism": 1.0,
|
| 25 |
+
"precision": 1.0,
|
| 26 |
+
"recall": 1.0,
|
| 27 |
+
"post_1930_detection_rate": 1.0,
|
| 28 |
+
"pre_1930_detection_rate": 0.0,
|
| 29 |
+
"detection_delta": 1.0,
|
| 30 |
+
"baseline_delta": 0.1205,
|
| 31 |
+
"criterion_passed": true
|
| 32 |
+
},
|
| 33 |
+
"w71_baseline": {
|
| 34 |
+
"post_1930_rate": 0.5524,
|
| 35 |
+
"pre_1930_rate": 0.4319,
|
| 36 |
+
"delta": 0.1205
|
| 37 |
+
},
|
| 38 |
+
"hf_repo": "idirectships/abacus-cheat-tell-v1",
|
| 39 |
+
"output_dir": "/tmp/abacus-cheat-tell-w72"
|
| 40 |
+
}
|