InternLM学习笔记

入门岛

1. Linux基础知识

2. Python 基础知识

from collections import Counter


text = """
Got this panda plush toy for my daughter's birthday,
who loves it and takes it everywhere. It's soft and
super cute, and its face has a friendly look. It's
a bit small for what I paid though. I think there
might be other options that are bigger for the
same price. It arrived a day earlier than expected,
so I got to play with it myself before I gave it
to her.
"""


def wordcount(text: str):
    text = text.lower().replace('.', '').replace(',', '').replace('\n', ' ')
    words = [word[:-2] if word.endswith("'s") else word for word in text.split(' ') if word]
    return dict(Counter(words))


if __name__ == '__main__':
    res = wordcount(text)
    print(res)

基础岛

1. 书生大模型全链路开源体系

书生浦语大模型（InternLM）目前已开源InternLM、InternLM2、InternLM2.5三代大模型，包含1.8B、7B、20B等多种参数版本。其中InternLM2.5具有如下优势：

同时书生浦语大模型也开源了大模型全链路生态：

开源数据处理工具箱：

高效微调框架XTuner

加速推理框架LMDeploy
轻量级智能体框架Lagent

智能体MindSearch（详细规划、并且可视化每一步的思考思路，解决可解释性？）

企业级知识库构建工具

2. 8G 显存玩转书生大模型 Demo

部署 InternLM2-Chat-1.8B 模型

LMDeploy 部署 InternVL2-2B 模型

3. 浦语提示词工程实践