Text Classification
Transformers
Safetensors
English
modernbert
encoder
decision-model
tool-routing
agentic
preview
text-embeddings-inference
Instructions to use MaziyarPanahi/ModernJEV-Decide-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MaziyarPanahi/ModernJEV-Decide-Preview with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="MaziyarPanahi/ModernJEV-Decide-Preview")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/ModernJEV-Decide-Preview") model = AutoModelForSequenceClassification.from_pretrained("MaziyarPanahi/ModernJEV-Decide-Preview", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download evaluation/per-task-baselines.json from MaziyarPanahi/ModernJEV-Decide-Preview: direct link, hf CLI and curl.
- Browser
- Download file 1.9 kB
-
https://huggingface.co/MaziyarPanahi/ModernJEV-Decide-Preview/resolve/main/evaluation/per-task-baselines.json
- Command line
-
hf download hf://MaziyarPanahi/ModernJEV-Decide-Preview/evaluation/per-task-baselines.json
-
curl -L -o per-task-baselines.json https://huggingface.co/MaziyarPanahi/ModernJEV-Decide-Preview/resolve/main/evaluation/per-task-baselines.json
1.9 kB
| { | |
| "dataset_revision": "f2fb14e4ec977c420f376c08785664cd38763d7e", | |
| "families": { | |
| "agent_next_action_type": { | |
| "n": 1158, | |
| "majority_correct": 616, | |
| "majority_accuracy": 0.531951640759931, | |
| "majority_labels": [ | |
| "text_response" | |
| ], | |
| "candidate_count": { | |
| "median": 3.0, | |
| "min": 3, | |
| "max": 3 | |
| }, | |
| "uniform_expected_accuracy": 0.3333333333333333, | |
| "reference_definition": "Descriptive test-set constant-label majority; no model fitting", | |
| "unseen_task_family": false, | |
| "training_fixed_majority": { | |
| "label": "text_response", | |
| "correct": 616, | |
| "n": 1158, | |
| "majority_label_absent_from_choices": 0 | |
| } | |
| }, | |
| "tool_selection": { | |
| "n": 542, | |
| "majority_correct": 79, | |
| "majority_accuracy": 0.14575645756457564, | |
| "majority_labels": [ | |
| "transfer_to_human_agent" | |
| ], | |
| "candidate_count": { | |
| "median": 20.0, | |
| "min": 11, | |
| "max": 32 | |
| }, | |
| "uniform_expected_accuracy": 0.051859254651728436, | |
| "reference_definition": "Descriptive test-set constant-label majority; no model fitting", | |
| "unseen_task_family": false, | |
| "training_fixed_majority": { | |
| "label": "transfer_to_human_agent", | |
| "correct": 79, | |
| "n": 542, | |
| "majority_label_absent_from_choices": 235 | |
| } | |
| }, | |
| "when_to_call_tool": { | |
| "n": 3652, | |
| "majority_correct": 1295, | |
| "majority_accuracy": 0.3546002190580504, | |
| "majority_labels": [ | |
| "cannot_answer", | |
| "tool_call" | |
| ], | |
| "candidate_count": { | |
| "median": 4.0, | |
| "min": 4, | |
| "max": 4 | |
| }, | |
| "uniform_expected_accuracy": 0.25, | |
| "reference_definition": "Descriptive test-set constant-label majority; no model fitting", | |
| "unseen_task_family": true | |
| } | |
| }, | |
| "when2call_training_rows": 0 | |
| } | |