Hackernews posts about Code Llama
- Reading the Llama Code (www.adrian.idv.hk)
- Llama 3.2 from-scratch implementation focused on code readability (huggingface.co)
- Show HN: I Developed AI Memory Booster: Self-Hosted AI with Long Term Memory (aimemorybooster.com)
- Show HN: Auto-Detect Cheating and AI Hiring Agents (ShivonAI Python Package) (www.shivonai.com)
- Show HN: A website/app to help manage your game library (gamenode.app)
- Show HN: An AI code assistant for Vim (github.com)
- Beating GPT-4 on HumanEval with a fine-tuned CodeLlama-34B (www.phind.com)
- Meta AI releases Code Llama 70B (twitter.com)
- Understanding Llama 2 and the New Code Llama LLMs (magazine.sebastianraschka.com)
- Show HN: Open Interpreter – CodeLlama in your terminal, executing code (openinterpreter.com)
- Workers AI Update: Stable Diffusion, Code Llama and Workers AI in 100 Cities (blog.cloudflare.com)
- Show HN: I built local copilot alternative using Codellama (marketplace.visualstudio.com)
- A complete guide to fine-tuning Code Llama (ragntune.com)
- Full F16 precision 34B Code Llama at >20T/s on M2 Ultra (twitter.com)
- Meta launches own AI code-writing tool: Code Llama (www.theverge.com)
- Run Code Llama Locally (ollama.ai)
- Code Llama (ai.meta.com)
- Prompting Code Llama (ollama.ai)
- Meta is releasing a new CodeLlama (www.facebook.com)
- OpenAI Lifeboat – Proxy OpenAI Code to Llama 70B on Replicate (lifeboat.replicate.dev)
- Comparing Code Llama Models Locally (about.xethub.com)
- Code Llama for VS Code (github.com)
- Meta releases Code Llama, a code-generating AI model (techcrunch.com)
- M2 Ultra runs codellama 34B F16 at 150 token per second (twitter.com)
- Run CodeLlama on a Serverless GPU (github.com)
- Fine-tuned CodeLlama beats GPT-4 on HumanEval (huggingface.co)