Text Classification
Transformers
Safetensors
English
deberta-v2
reward-model
scpo
cultural-alignment
canada
text-embeddings-inference
Instructions to use MulticulturalAlignment/scpo-reward-model-canada with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MulticulturalAlignment/scpo-reward-model-canada with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="MulticulturalAlignment/scpo-reward-model-canada")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("MulticulturalAlignment/scpo-reward-model-canada") model = AutoModelForSequenceClassification.from_pretrained("MulticulturalAlignment/scpo-reward-model-canada", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download provenance.json from MulticulturalAlignment/scpo-reward-model-canada: direct link, hf CLI and curl.
- Browser
- Download file 1.14 kB
-
https://huggingface.co/MulticulturalAlignment/scpo-reward-model-canada/resolve/main/provenance.json
- Command line
-
hf download hf://MulticulturalAlignment/scpo-reward-model-canada/provenance.json
-
curl -L -o provenance.json https://huggingface.co/MulticulturalAlignment/scpo-reward-model-canada/resolve/main/provenance.json
1.14 kB
| { | |
| "country": "Canada", | |
| "protocol": "original-source-v1", | |
| "source_revision": "94f8430054835aa919b226b4344b8f0e8424f29b", | |
| "original_sha256": { | |
| "preferences.py": "df4c9e3991b8238c5a50a3d672d67ca3d6350f06a28a99bc6959e8edd817cd8e", | |
| "our_reward_trainer.py": "35aea8a2f4b30f51e5427b61418698d69528b868fd7b35abad7132508d092ab3", | |
| "our_inverse_reward_trainer.py": "b41fc006ae62dfdd5553217cdb231c35d45c80dd5437f3f7c70ce006f59835a1", | |
| "our_data_collator.py": "67c1b081e7886ed8a5747abe7612ff255f0043d8c3d59ef64bb774db12518c79" | |
| }, | |
| "generated_sha256": "16642fdfa0c817ca2b0ce33600d6478535f2994bef5c4f00d0d7b7227026b72e", | |
| "base_model_revision": "7dab4156e63944834c3aae169c3fe83955672cff", | |
| "dataset_revision": "18ab5cfb37456f4ec8cbc00212ce54cf7b1239f6", | |
| "experiment_metrics": { | |
| "overall": 66.1849710982659, | |
| "global_overall": 60.40462427745664, | |
| "misranked": 27.73722627737226, | |
| "global_misranked": 0.0 | |
| }, | |
| "weight_sha256": "aa23ee2ae72319bcc6351cd800c413a320856483208fc09f7e447351ba868583", | |
| "selection": "Per-country exploratory fixed-test selections; Israel accepted by user below prior matching threshold" | |
| } | |