code Llama

Today, we’re releasing Code Llama, a large language model (LLM) that can use text prompts to generate and discuss code. Code Llama is state-of-the-art for publicly available LLMs on coding tasks. It has the potential to make workflows faster and more efficient for developers and lower the barrier to entry for people who are learning to code. Code Llama has the potential to be used as a productivity and educational tool to help programmers write more robust, well-documented software.

We believe an open approach to AI is best for developing new AI tools that are innovative, safe and responsible, so we’re releasing Code Llama for both research and commercial use under the same community license as Llama 2.

Code Llama is a code-specialized version of Llama 2 that was created by further training Llama 2 on its code-specific datasets, sampling more data from that same dataset for longer. Essentially, Code Llama features enhanced coding capabilities. It can generate code and natural language about code, from both code and natural language prompts (e.g., “Write me a function that outputs the fibonacci sequence”). It can also be used for code completion and debugging. It supports many of the most popular programming languages used today, including Python, C++, Java, PHP, Typescript (Javascript), C#, Bash and more.

Certainly! Here's a step-by-step guide for each of the five options mentioned:

Option 1: Accessing Code Llama Models and Tokenizers Directly from Meta

1. Prepare: Ensure you are an experienced researcher or developer with the necessary expertise.

2. Request Access: Visit Meta's platform or relevant channels where Code Llama models are hosted. Look for the option to request access to the model weights and tokenizers.

3. Submit Request: Follow the provided instructions to submit a request. This will grant you access to the required resources.

4. Download Code and Models: After approval, you will receive download links. Use these links to download the Code Llama model weights and tokenizers.

5. Sample Code: Explore the GitHub repository mentioned to find sample code for loading Code Llama models and running inference.

6. Handling Errors: If you encounter issues like "403: Forbidden" due to link expiration or download limits, you can request new links as needed.

Option 2: Perplexity Llama Chat

Perplexity AI is an AI-chat-based conversational search engine that delivers answers to questions using various language models. Within 6 hours of Code Llama's release, Perplexity integrated the 34b-instruct model into its Llama Chat offering. Simply navigate to the website to get going.

Option 3: Code Llama Playground

This is a demo to generate text and code with the Code Llama model (13B). Please note that this model is not designed for instruction purposes but for code completion. Infilling is currently not supported.

Option 4:  Faraday

Faraday has also added support for the 7b, 13b, and 34b Code Llama instruct models.

Faraday is an easy-to-use desktop app (Mac and Windows) that allows users to chat with AI "characters" offline. It features a one-click Desktop installer that "just works" out of the box (GPU & Metal acceleration included!). The AI models that power Faraday are stored 100% locally on your computer. Your chat data is saved to your computer and is never sent to a remote server. 

Option 5: Code Llama 13B Chat on Hugging Face

You can check out this Space on Hugging Face for a quick demo of CodeLlama-13b-Instruct. You can play with it as is, or duplicate to run generations without a queue! If you want to run your own service, you can also deploy the model on Inference Endpoints.

Additionally you can access the 34B Instruct model for free with super fast inference using Hugging Chat.