LLMSurvey
LLMSurvey copied to clipboard
RUCAIBox
The official GitHub page for the survey paper "A Survey of Large Language Models".
Typos
Version: arXiv:2303.18223v11 [cs.CL] 29 Jun 2023 section 2.2 decoder-onlly -> decoder-only And another issue: Figure 3 seems not be cited in the content. Other figures may also have this problem.
基于基座模型比如LLaMA系列进行指令微调，训练的损失函数是什么？在验证集上计算损失跟训练集上是否一致，谢谢！
Ingredient : Task Description Prompt content: Make your prompt as detailed as possible, e.g., "Summarize the article into a short paragraph within 50 words. The major storyline and conclusion should...
We welcome everyone to provide us with more relevant tips in the form of issues. After selection, we will regularly update them on GitHub and indicate the source. If you...
First - nicely done. This must have been a herculean effort to review all of these papers. Here are some ideas: 1. It would be nice to include more information...
The largest scale of RWKV is 14B, which achieve the criteria of this survey. GitHub Repo: https://github.com/BlinkDL/RWKV-LM Online Demo: https://huggingface.co/spaces/BlinkDL/ChatRWKV-gradio I hope my suggestion could improve your survey.
Good evening! could you please add new Google AI models like Genesis awesome job! thx
How u get Ratios of various data sources in the pre-training data for existing LLMs in Fig2? As for me, the data in the Fig2 differs from the paper I...
As we mention in the survey, we only include LLMs (larger than 10B) with publicly reported evaluation results in Figure 1. Excluding models with papers (because formal evaluation results are...