Transformers
Safetensors
English
deberta-v2
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
Inference Endpoints
Better-PairRM / added_tokens.json
maywell's picture
Upload folder using huggingface_hub
e50d81e verified
raw history blame
No virus
130 Bytes
{
"<|candidate1|>": 128002,
"<|candidate2|>": 128003,
"<|candidate|>": 128004,
"<|source|>": 128001,
"[MASK]": 128000
}