# Llama2.cpp Chat

### llama.cpp

<figure><img src="/files/D0YElEPPNk40MRmqAFd4" alt=""><figcaption></figcaption></figure>

**This repository is a fork of** [**llama.cpp**](https://github.com/ggerganov/llama.cpp) **customized to facilitate Llama2 inference within Arkane Cloud.**

### Overview

Llama.cpp is a powerful tool for running Llama2 inference, and this fork is tailored specifically for seamless integration with Arkane Cloud environments.

### Features

* **Pre-Configured CI Pipeline**: The CI pipeline is set up to automatically fetch a pre-converted and quantized llama code instruct model from TheBloke on Hugging Face.
* **HTTP Server Example**: The repository includes an HTTP server example, allowing for easy deployment and testing. Configuration options can be found in the /examples/server directory.

### Usage

1. Clone this repository in a new workspace (at least Pro/GPU)
2. Start the `Prepare` stage in the `CI-Pipeline`
3. After the `Prepare` stage is done you can start the `run` stage
4. Click on `Open deployment` in the top right corner

### Documentation

For detailed configuration options and usage instructions, refer to the README file located in the /examples/server directory.

### Note

Please note that while this repository provides a convenient setup for running Llama2 inference in Arkane Cloud, further customization may be required to suit specific use cases or preferences.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.arkanecloud.com/docs/templates/llama2.cpp-chat.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.