James-WYang
/

ICR_ANALYSIS_M0_Llama-3-Base-8B-SFT-DPO_en_es_ru_de_fr_wo_length_control

Model card Files Files and versions

No model card

Downloads last month: 1

Safetensors

Model size

8.03B params

Tensor type

BF16

·

Inference Providers NEW

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

Collection including James-WYang/ICR_ANALYSIS_M0_Llama-3-Base-8B-SFT-DPO_en_es_ru_de_fr_wo_length_control

Implicit Cross-lingual Reward

All checkpoints for "Implicit Cross-Lingual Rewarding for Efficient Multilingual Preference Alignment", https://arxiv.org/abs/2503.04647 • 10 items • Updated Aug 25