Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
LemiSt
/
PairRM-mdeberta-v3-base
like
0
Text Generation
Safetensors
6 datasets
16 languages
deberta
reward_model
reward-model
RLHF
evaluation
llm
instruction
reranking
License:
mit
Model card
Files
Files and versions
Community
5506b8d
PairRM-mdeberta-v3-base
/
added_tokens.json
LemiSt
added model
ec35be6
2 months ago
raw
Copy download link
history
blame
Safe
130 Bytes
{
"<|candidate1|>"
:
250103
,
"<|candidate2|>"
:
250104
,
"<|candidate|>"
:
250105
,
"<|source|>"
:
250102
,
"[MASK]"
:
250101
}