Zero-Shot Classification
Transformers
ONNX
Safetensors
English
watersheep
feature-extraction
decision-model
calibration
multi-label
custom_code
Instructions to use samratduttaofficial/WaterSheep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use samratduttaofficial/WaterSheep with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("zero-shot-classification", model="samratduttaofficial/WaterSheep", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("samratduttaofficial/WaterSheep", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download watersheep.json from samratduttaofficial/WaterSheep: direct link, hf CLI and curl.
- Browser
- Download file 661 Bytes
-
https://huggingface.co/samratduttaofficial/WaterSheep/resolve/main/watersheep.json
- Command line
-
hf download hf://samratduttaofficial/WaterSheep/watersheep.json
-
curl -L -o watersheep.json https://huggingface.co/samratduttaofficial/WaterSheep/resolve/main/watersheep.json
661 Bytes
| { | |
| "format": 2, | |
| "run_id": "run_20260928-070402", | |
| "encoder": "answerdotai/ModernBERT-base", | |
| "tokenizer": "hf", | |
| "max_len": 512, | |
| "max_question_tokens": 96, | |
| "max_option_tokens": 32, | |
| "max_options": 10, | |
| "head_layers": 1, | |
| "temperatures": { | |
| "binary": 1.0594, | |
| "choice": 1.0631, | |
| "score": 1.0022, | |
| "multi": 0.8276 | |
| }, | |
| "metrics": { | |
| "test_calibrated": { | |
| "acc": 0.7778176740474766, | |
| "ece": 0.025550670609045353 | |
| }, | |
| "zeroshot_calibrated": { | |
| "acc": 0.6121272507294855, | |
| "ece": 0.04295260971909359 | |
| } | |
| }, | |
| "multi_threshold": 0.5, | |
| "created": "20260928-125453", | |
| "name": "watersheep-20260928-125452" | |
| } | |