chaoweihuang
/

FactAlign-gemma-2b-sft

Model card Files Files and versions

Metrics Training metrics Community

YAML Metadata Warning: empty or missing yaml metadata in repo card (https://huggingface.co/docs/hub/model-cards#model-card-metadata)

This model is aligned with our FactAlign framework for improved long-form factuality, from Columbia-NLP/gemma-2b-zephyr-sft.

For more information, please refer to our paper: FactAlign: Long-form Factuality Alignment of Large Language Models.

Downloads last month: 4

Safetensors

Model size

3.03B params

Tensor type

F16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including chaoweihuang/FactAlign-gemma-2b-sft

FactAlign

Models and datasets of our EMNLP 2024 paper "FactAlign: Long-form Factuality Alignment of Large Language Models" • 7 items • Updated Oct 7, 2024 • 1