Mac下使用ollama 本地部署LLM

Ollama

Get up and running with large language models.
Run Llama 3, Mistral, Gemma, and other models. Customize and create your own.

https://github.com/ollama/ollama

下载地址：

https://ollama.com/download/mac

下载后直接解压安装

安装好后，直接终端运行llama3 

ollama run llama3

文件比较大，下载时间稍长，耐心等待。

模型文件默认存储地址：

cd ~ .ollama/

默认端口号确认：

lsof -i:11434

浏览器访问验证：

开始交流：当问问题的时候，电脑风扇真的是嗡嗡响。。。

how to learn LLM?
Learning a Large Language Model (LLM) is a challenging but rewarding task. Here's a step-by-step guide to help you get started:

**Step 1: Understand the Basics of NLP**

* Learn about Natural Language Processing (NLP) and its applications.
* Study the fundamentals of text processing, including tokenization, stemming, lemmatization, and named entity recognition.

**Step 2: Familiarize yourself with Deep Learning**

* Learn the basics of deep learning, including neural networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers.
* Study popular deep learning frameworks like TensorFlow, PyTorch, or Keras.

**Step 3: Learn about Language Models**

* Study the history and evolution of language models, including bag-of-words models, n-gram models, and neural network-based models.
* Learn about the different types of language models, such as character-level models, word-level models, and sentence-level models.

**Step 4: Choose a Specific LLM to Learn**

* Research popular LLMs like BERT, RoBERTa, and XLNet.
* Study their architectures, training objectives, and applications.
* Experiment with pre-trained models and fine-tune them for specific tasks.

**Step 5: Practice and Build Projects**

* Start by building simple text-based projects, such as language translation or sentiment analysis.
* Gradually move on to more complex projects, like conversational AI or text generation.
* Join online communities and participate in hackathons to collaborate with others and learn from their experiences.

**Step 6: Read Research Papers and Books**

* Study research papers published in top NLP conferences like NAACL, ACL, and EMNLP.
* Read books on LLMs, such as "Natural Language Processing (almost) from Scratch" by Collobert et al. or "Deep Learning for Natural Language Processing" by Y.
Bengio.

**Step 7: Join Online Communities and Take Courses**

* Participate in online forums like Reddit's r/MachineLearning and r/NLP.
* Take online courses or attend workshops on LLMs, such as Andrew Ng's Machine Learning course on Coursera.
* Collaborate with others and learn from their experiences.

**Step 8: Stay Up-to-Date**

* Follow top researchers and NLP enthusiasts on social media platforms like Twitter.
* Subscribe to newsletters and podcasts focused on NLP and LLMs.
* Attend conferences and meetups to stay updated on the latest developments in the field.

Remember, learning an LLM is a long-term process that requires dedication, persistence, and practice. Start with the basics, build your way up, and don't be
afraid to ask for help when needed!