Instructions to use eevoire/json-extractor-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use eevoire/json-extractor-demo with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir json-extractor-demo eevoire/json-extractor-demo
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "promote": true, | |
| "reasons": [ | |
| "field_accuracy: 0.1667 -> 1.0 (+0.8333) meets min improvement 0.05", | |
| "json_validity: 1.0 -> 1.0 (no meaningful regression)", | |
| "exact_match: 0.0 -> 1.0 (no meaningful regression)" | |
| ], | |
| "gate": { | |
| "primary_metric": "field_accuracy", | |
| "min_improvement": 0.05, | |
| "no_regression": [ | |
| "json_validity", | |
| "exact_match" | |
| ], | |
| "regression_tolerance": 0.02 | |
| }, | |
| "base_report": "runs/json-extractor-demo/eval_base.json", | |
| "tuned_report": "runs/json-extractor-demo/eval_tuned.json" | |
| } | |