Text Classification
Transformers
Safetensors
English
roberta
reward model
alignment
preference model
RLHF
text-embeddings-inference
Instructions to use nicholasKluge/Harmless-RewardModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nicholasKluge/Harmless-RewardModel with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="nicholasKluge/Harmless-RewardModel")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("nicholasKluge/Harmless-RewardModel") model = AutoModelForSequenceClassification.from_pretrained("nicholasKluge/Harmless-RewardModel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md
Verified signature3cf2a1e -
Update config.json
Verified signaturececb795 -
Update README.md
Verified signaturef4f2060
-
Update README.md
Verified signature1ba5b15
-
Update config.json
Verified signature144ae68 -
Update README.md
Verified signaturefed22d0 -
Update README.md
Verified signature7a584f3 -
Upload hh_rlhf_eval.parquet
Verified signature5d2556a -
Upload LICENSE
Verified signaturecbccea9 -
Create README.md
Verified signaturec3ba6f1 -
Upload emissions.csv with huggingface_hub
Verified signature72aa516 -
Upload folder using huggingface_hub
Verified signature70e65be -
initial commit
Verified signature12aaab0