PA-RAG: RAG Alignment via Multi-Perspective Preference Optimization

πŸŽ‰πŸŽ‰πŸŽ‰ PA-RAG is accepted by NAACL 2025!

Paper Link: https://arxiv.org/pdf/2412.14510
Github Link: https://github.com/wujwyi/PA-RAG

This is a model fine-tuned on Llama-2-7b-chat-hf using PA-RAG. The training data for PA-RAG, available at Huggingface link or Google Drive link

Downloads last month
0
Safetensors
Model size
6.74B params
Tensor type
BF16
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for wuqiong1/PA-RAG_Llama-2-7b-chat-hf

Finetuned
(449)
this model
Quantizations
2 models

Dataset used to train wuqiong1/PA-RAG_Llama-2-7b-chat-hf

Collection including wuqiong1/PA-RAG_Llama-2-7b-chat-hf