├── gpt.hurl
├── renovate.json
├── models
├── web-developer
│ └── Modelfile
└── adr
│ └── Modelfile
└── README.md
/gpt.hurl:
--------------------------------------------------------------------------------
1 | POST http://localhost:11434/api/generate
2 | {"model": "mario", "prompt":"Who are you?"}
3 |
4 |
--------------------------------------------------------------------------------
/renovate.json:
--------------------------------------------------------------------------------
1 | {
2 | "$schema": "https://docs.renovatebot.com/renovate-schema.json",
3 | "extends": [
4 | "config:recommended"
5 | ]
6 | }
7 |
--------------------------------------------------------------------------------
/models/web-developer/Modelfile:
--------------------------------------------------------------------------------
1 | # Modelfile for creating a web developer assistant
2 | # Run `ollama create web-developer -f ./Modelfile` and then `ollama run web-developer` and enter a topic
3 |
4 | FROM llama2:13b
5 | PARAMETER temperature 1
6 | SYSTEM """
7 | You are a senior web developer, acting as an assistant. You offer help with web technologies like: React, AWS, NodeJs, Typescript, HTML, and TailwindCSS. You answer with code examples when possible """
8 |
--------------------------------------------------------------------------------
/models/adr/Modelfile:
--------------------------------------------------------------------------------
1 | # Modelfile for creating a software engineer assistant to write Architecture Decisions Record (ADR)
2 | # Run `ollama create adr f ./Modelfile` and then `ollama run adr` and enter a topic
3 |
4 | FROM llama2:13b
5 | PARAMETER temperature 1
6 | SYSTEM """
7 | You are a sensor software engineer, acting as an assistant. You offer help with architecture design like: business analysis, software design, architecture design. We will use Architecture Decision Records, as described by Michael Nygard. You answer with diagram in markdown with example data and code in TypeScript when possible """
8 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 |
2 |
👋 Welcome to llama2-demo
3 | Build your personal AI with the llama2 model 🤖. Easy to use, and perfect for your development needs!
4 |
5 |
6 | [![IT Man - Build Your Personal AI with Llama2 [Vietnamese]](https://i.ytimg.com/vi/2wCgPa4G9H0/hqdefault.jpg)](https://www.youtube.com/watch?v=2wCgPa4G9H0)
7 |
8 | ## 🛠 Requirements
9 |
10 | Make sure to have [ollama](https://github.com/jmorganca/ollama) installed on your machine.
11 |
12 | ## 🚀 Usage
13 |
14 | ### List All Models
15 |
16 | ```sh
17 | ❯ ollama ls
18 | ```
19 |
20 | ### Web Developer
21 |
22 | #### Create a Model
23 |
24 | ```sh
25 | ❯ ollama create web-developer -f ./models/web-developer/Modelfile
26 | ```
27 |
28 | #### Run Model
29 |
30 | ```sh
31 | ❯ ollama run web-developer
32 | ```
33 |
34 | ### ADR Writer
35 |
36 | #### Create a Model
37 |
38 | ```sh
39 | ❯ ollama create adr -f ./models/adr/Modelfile
40 | ```
41 |
42 | #### Run Model
43 |
44 | ```sh
45 | ❯ ollama run adr
46 | ```
47 |
48 | ## Resources
49 |
50 | - [Llama 2 - Meta AI](https://ai.meta.com/llama/)
51 | - [jmorganca/ollama: Get up and running with Llama 2 and other large language models locally](https://github.com/jmorganca/ollama)
52 | - [getumbrel/llama-gpt: A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device.](https://github.com/getumbrel/llama-gpt)
53 | - [NextJs Mini Course](https://www.youtube.com/playlist?list=PLOdXIcVPTyB_2IiS36upNkEw2fLhyb5D6)
54 | - [Architectural Decision Records - why you should write ADR](https://youtu.be/EhsBVGDWTxs)
55 |
56 | ## ❤️ Show Your Support
57 |
58 | Give this project a ⭐️ if it's helped you out! Feel free to contribute or raise any issues.
59 |
--------------------------------------------------------------------------------