通过裁剪(Pruning)和知识蒸馏(Knowledge Distillation)实现紧凑的语言模型
论文《通过裁剪和知识蒸馏实现紧凑的语言模型》(Compact Language Models via Prun […]
通过裁剪(Pruning)和知识蒸馏(Knowledge Distillation)实现紧凑的语言模型 Read More »
论文《通过裁剪和知识蒸馏实现紧凑的语言模型》(Compact Language Models via Prun […]
通过裁剪(Pruning)和知识蒸馏(Knowledge Distillation)实现紧凑的语言模型 Read More »
论文Mitigating Object Hallucination via Data Augmented Co
通过数据增强对比微调缓解“对象幻觉”(object hallucination) Read More »
论文Meta-Rewarding Language Models: Self-Improving Alignm
元奖励(Meta-Rewarding)模型:角色扮演(演员actor、评审judge和元评审meta-judge)的大语言模型 Read More »