发简信
IP属地：浙江
-
直接偏好优化技术DPO基础理论及推导
论文标题：Direct Preference Optimization: Your Language Model is Secretly a R...
-
自适应视图增强的谣言检测图对比学习方法论文标题：Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning A...
-
生成式大模型的RLHF技术（一）：基础一、概述 大语言模型（LLMs）在预训练的过程中通常会捕捉数据的特征，而这些训练数据通常既包含高质量的也包含低质量的，因此模型有时会产生不被期望...
-
LoRA：大模型下游任务的低秩适应论文标题：LoRA: Low-Rank Adaptation of Large Language Models论文链接：https://arxi...
-
Megatron-LM：Transformer模型专用分布式张量模型并行方法论文标题：Megatron-LM: Training Multi-Billion Parameter Language Models Using...
-
思维树：大模型的复杂推理技术论文标题：Tree of Thoughts: Deliberate Problem Solving with Large Language Mo...
-
LIMA：小规模监督数据指令微调论文标题：LIMA: Less Is More for Alignment论文链接：https://arxiv.org/abs/2305.112...
-
语言模型的自洽性思维链推理技术论文标题：Self-Consistency Improves Chain of Thought Reasoning in Language Mo...
-
GPipe：微批量流水线并行论文标题：GPipe: Easy Scaling with Micro-Batch Pipeline Parallelism论文链接：https...