Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
ContextualAI
/
Contextual_KTO_Mistral_PairRM
like
32
Follow
ContextualAI
109
Text Generation
Transformers
Safetensors
snorkelai/Snorkel-Mistral-PairRM-DPO-Dataset
English
mistral
human feedback
rlhf
preferences
alignment
HALO
halos
dpo
rl
conversational
text-generation-inference
arxiv:
2402.01306
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
Deploy
Use this model
main
Contextual_KTO_Mistral_PairRM
/
.gitattributes
Commit History
initial commit
4564abd
verified
xwinxu
commited on
Mar 5, 2024