Feature Extraction
Transformers
Safetensors
pivot
decision-making
classification
scoring
custom_code
Instructions to use Q1z/Pivot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Q1z/Pivot with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Q1z/Pivot", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Q1z/Pivot", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "schema_version": "pivot-native-v1", | |
| "contract": "context_in__closed_semantic_candidates_out", | |
| "closed_set": true, | |
| "probability_scope": "supplied_candidates_only", | |
| "selected": { | |
| "id": "billing", | |
| "text": "route to billing support", | |
| "kind": "candidate", | |
| "prob": 1.0 | |
| }, | |
| "index": 0, | |
| "relative_confidence": 1.0, | |
| "abstained": false, | |
| "candidates": [ | |
| { | |
| "id": "billing", | |
| "text": "route to billing support", | |
| "kind": "candidate", | |
| "prob": 1.0 | |
| }, | |
| { | |
| "id": "technical", | |
| "text": "route to technical support", | |
| "kind": "candidate", | |
| "prob": 1.4294558425831383e-08 | |
| }, | |
| { | |
| "id": "sales", | |
| "text": "route to sales", | |
| "kind": "candidate", | |
| "prob": 1.0551385321022622e-09 | |
| }, | |
| { | |
| "id": "none", | |
| "text": "none of these routes is appropriate", | |
| "kind": "abstain", | |
| "prob": 6.683787908984967e-15 | |
| } | |
| ], | |
| "prob_vector": [ | |
| 1.0, | |
| 1.4294558425831383e-08, | |
| 1.0551385321022622e-09, | |
| 6.683787908984967e-15 | |
| ] | |
| } |