https://github.com/sollimann/chatty-llama

A fullstack Rust + React chat app using open-source Llama language models
https://github.com/sollimann/chatty-llama

artificial-intelligence chatbot fullstack llama2 llm meta react rust

Last synced: 3 months ago
JSON representation

A fullstack Rust + React chat app using open-source Llama language models

• Host: GitHub
• URL: https://github.com/sollimann/chatty-llama
• Owner: Sollimann
• License: mit
• Created: 2023-08-25T16:48:50.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-09-08T12:55:07.000Z (over 1 year ago)
• Last Synced: 2024-10-18T22:02:17.633Z (3 months ago)
• Topics: artificial-intelligence, chatbot, fullstack, llama2, llm, meta, react, rust
• Language: Rust
• Homepage:
• Size: 598 KB
• Stars: 31
• Watchers: 1
• Forks: 4
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
 Chatty Llama 



  





    A fullstack chat app utilizing Llama LLMs





    

    

    

    

    

    



## How to run

#### 1. Install huggingface-cli

```sh

$ make install-huggingface-cli

```

#### 2. Export huggingface token

Create a huggingface token: https://huggingface.co/settings/tokens

, then set the token as env variable on your machine:

```sh

$ export HF_TOKEN=

```

#### 3. Download the [Llama-2-7B-Chat-GGML](https://huggingface.co/TheBloke/Llama-2-7B-Chat-GGML) model

```sh

$ make download-model

```

#### 4. Run the chat app

```sh

$ make chatty-llama

```

**PS!** If you're having issues connecting to the `backend`, try running `make chatty-llama-host` instead.

In your browser, open http://localhost:80

**Enjoy!**