Transformers
Safetensors
English
deberta-v2
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
Instructions to use mightbe/Better-PairRM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mightbe/Better-PairRM with Transformers:
# Load model directly from transformers import AutoTokenizer, DebertaV2PairRM tokenizer = AutoTokenizer.from_pretrained("mightbe/Better-PairRM") model = DebertaV2PairRM.from_pretrained("mightbe/Better-PairRM") - Notebooks
- Google Colab
- Kaggle
Ctrl+K