Text Classification
Transformers
Safetensors
English
deberta-v2
cross-encoder
reward-model
forecasting
text-embeddings-inference
Instructions to use HiddenSystemsAI/rem-matcher with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HiddenSystemsAI/rem-matcher with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="HiddenSystemsAI/rem-matcher")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("HiddenSystemsAI/rem-matcher") model = AutoModelForSequenceClassification.from_pretrained("HiddenSystemsAI/rem-matcher", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download calibration.json from HiddenSystemsAI/rem-matcher: direct link, hf CLI and curl.
- Browser
- Download file 287 Bytes
-
https://huggingface.co/HiddenSystemsAI/rem-matcher/resolve/main/calibration.json
- Command line
-
hf download hf://HiddenSystemsAI/rem-matcher/calibration.json
-
curl -L -o calibration.json https://huggingface.co/HiddenSystemsAI/rem-matcher/resolve/main/calibration.json
287 Bytes
| { | |
| "temperature": 1.7073526474706913, | |
| "bias": -0.4470148298452159, | |
| "decision_threshold": 0.5, | |
| "confidence_threshold": 0.8, | |
| "method": "platt_on_logit_margin", | |
| "positive_label": "yes", | |
| "probability_scope": "L2 matching on the held-out pair distribution", | |
| "max_length": 512 | |
| } |