Transformers
Safetensors
English
deberta-v2
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
Inference Endpoints
File size: 130 Bytes
e50d81e
 
 
 
 
 
 
1
2
3
4
5
6
7
8
{
  "<|candidate1|>": 128002,
  "<|candidate2|>": 128003,
  "<|candidate|>": 128004,
  "<|source|>": 128001,
  "[MASK]": 128000
}