發簡信
IP屬地：浙江
-
直接偏好優化技術DPO基礎理論及推導
論文標題：Direct Preference Optimization: Your Language Model is Secretly a R...
-
自適應視圖增強的謠言檢測圖對比學習方法論文標題：Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning A...
-
生成式大模型的RLHF技術（一）：基礎一、概述 大語言模型（LLMs）在預訓練的過程中通常會捕捉數據的特征，而這些訓練數據通常既包含高質量的也包含低質量的，因此模型有時會產生不被期望...
-
LoRA：大模型下游任務的低秩適應論文標題：LoRA: Low-Rank Adaptation of Large Language Models論文鏈接：https://arxi...
-
Megatron-LM：Transformer模型專用分布式張量模型并行方法論文標題：Megatron-LM: Training Multi-Billion Parameter Language Models Using...
-
思維樹：大模型的復雜推理技術論文標題：Tree of Thoughts: Deliberate Problem Solving with Large Language Mo...
-
LIMA：小規模監督數據指令微調論文標題：LIMA: Less Is More for Alignment論文鏈接：https://arxiv.org/abs/2305.112...
-
語言模型的自洽性思維鏈推理技術論文標題：Self-Consistency Improves Chain of Thought Reasoning in Language Mo...
-
GPipe：微批量流水線并行論文標題：GPipe: Easy Scaling with Micro-Batch Pipeline Parallelism論文鏈接：https...