大模型【学术】

教程

• mlabonne/llm-course: Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks. (github.com)

框架

• 【收集了很多工具、框架】SylphAI-Inc/LLM-engineer-handbook: A curated list of Large Language Model resources, covering model training, serving, fine-tuning, and building LLM applications. (github.com)

推理

• Flash-Decoding for Long-Context Inference | Princeton NLP Group (princeton-nlp.github.io)

• LLM Inference Provider Leaderboard (withmartian.com)，各个模型推理价格/推理成本，

多模态

GPT-4V

• LMMs 多模态大模型的曙光：初探 GPT-4V(ision) (weibo.com)

论文

• [2309.16583] GPT-Fathom: Benchmarking Large Language Models to Decipher the Evolutionary Path towards GPT-4 and Beyond (arxiv.org)

可视化

• Dodrio (poloclub.github.io)Exploring transformer models in your browser!

• lutzroeder/netron: Visualizer for neural network, deep learning and machine learning models (github.com), 将模型可视化

• Transformer Explainer (poloclub.github.io)
• 一个很详细的可视化 https://bbycroft.net/llm 中文版 http://llm-viz-cn.iiiai.com/llm