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:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, DebertaV2PairRM tokenizer = AutoTokenizer.from_pretrained("mightbe/Better-PairRM") model = DebertaV2PairRM.from_pretrained("mightbe/Better-PairRM", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update README.md (#3)
Verified signature- Update README.md (24ffc354f15ff6116a8093df021e62ac234f7ba7) Co-authored-by: Jeonghwan Park <maywell@users.noreply.huggingface.co>c260584
-
Update README.md (#2)
Verified signature- Update README.md (790e282bc02182cfeae4f2ed26eb864da05adc35) Co-authored-by: Jeonghwan Park <maywell@users.noreply.huggingface.co>5fca838
-
Update README.md
Verified signature69f3ec1 -
Update README.md
Verified signature2fc8ad5 -
Update README.md
Verified signature0319c87 -
Update README.md
Verified signaturec9f7a5d -
Update README.md
Verified signaturea775416 -
Update README.md
Verified signature4c4f60b -
Upload folder using huggingface_hub
Verified signaturee50d81e
-
Update README.md
Verified signature90d89ed -
Update README.md
Verified signature1b901ae -
initial commit
Verified signature7fc0cce