1106ps. 论文感觉没什么时间整理了，面向毕设和面向实习吧
论文阅读工具：
小绿鲸英文文献阅读器——专注提高SCI阅读效率 (xljsci.com)
chatgpt
newbing
code llama
摘要
We release Code Llama, a family of large language models for code based on Llama 2
providing state-of-the-art performance among open models, infilling capabilities, support
for large input contexts, and zero-shot instruction following ability for programming tasks.
模型表现有以下评估角度：
infilling capabilities：根据上下文，基于语义或语法进行代码填充
support for large input contexts：模型能够处理较长输入文本，比如包含多个函数、类、变量等的源代码文件或项目
zero-shot instruction following ability for programming tasks：表示模型可以根据指令或要求生成代码，而无需在训练阶段事先接触到类似的任务示例
介绍
上图为specialization pipeline