mzhaoshuai/zephyr-7b-alpha-conf-refalign

Model

0

stars

4

commits

1

linked in READMEs

Oct 16, 2025

updated

mistral

peft

refalign

safetensors

Browse cluster: Large Language Model Fine-tuning & Quantization →

README

RefAlign: RL with Similarity-based Rewards

GitHub repository: https://github.com/mzhaoshuai/RefAlign

Paper: Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data.

RefAlign Training with https://huggingface.co/datasets/shuchangtao/CONQORD_dataset/tree/main/conqord_step3_data.

Framework versions

PEFT 0.11.1

Contributors

4 commits

Similar repos

mzhaoshuai/Mistral-7B-v0.1-conf-sft

0

mzhaoshuai/Mistral-7B-v0.1-conf-refalign

0

mzhaoshuai/Llama-2-13b-hf-conf-refalign

0

mzhaoshuai/zephyr-7b-alpha-conf-sft

0

mzhaoshuai/Llama-2-7b-hf-conf-sft

0

mzhaoshuai/Llama-2-7b-hf-conf-refalign

0

TJKlein/ContrastivePerplexity

1

mzhaoshuai/Llama-2-13b-hf-conf-sft

0

Linked in READMEs

mzhaoshuai/RefAlign

RL with Similarity-based Rewards for Versatile Language Model Alignment.

8

mzhaoshuai/zephyr-7b-alpha-conf-refalign

Model

0

stars

4

commits

1

linked in READMEs

Oct 16, 2025

updated

mistral

peft

refalign

safetensors

Browse cluster: Large Language Model Fine-tuning & Quantization →

README

RefAlign: RL with Similarity-based Rewards

GitHub repository: https://github.com/mzhaoshuai/RefAlign

Paper: Learning from Reference Answers: Versatile Language Model Alignment without Binary Human Preference Data.

RefAlign Training with https://huggingface.co/datasets/shuchangtao/CONQORD_dataset/tree/main/conqord_step3_data.

Framework versions

PEFT 0.11.1

Similar repos

mzhaoshuai/Mistral-7B-v0.1-conf-sft

0

mzhaoshuai/Mistral-7B-v0.1-conf-refalign

0

mzhaoshuai/Llama-2-13b-hf-conf-refalign

0

mzhaoshuai/zephyr-7b-alpha-conf-sft

0

mzhaoshuai/Llama-2-7b-hf-conf-sft

0

mzhaoshuai/Llama-2-7b-hf-conf-refalign

0

TJKlein/ContrastivePerplexity

1

mzhaoshuai/Llama-2-13b-hf-conf-sft

0

Linked in READMEs

mzhaoshuai/RefAlign

RL with Similarity-based Rewards for Versatile Language Model Alignment.

8

Contributors

4 commits