2.5K views · 21 reactions | ACL 2024: You can Unified Efficiently fine-tune 100+ open-source models without writing code. LLaMA-Factory gives you a unified interface for training LLMs and VLMs. It supports LLaMA, Mistral, Qwen, DeepSeek, Gemma, Phi, Yi, and 90+ others. -/github.com/hiyouga/LlamaFactory | Md Ismail Sojal | Facebook

3.4K views · 289 reactions | Code Llama is built on top of Llama 2 and free for both research and commercial use. We've made three different models available: - Code Llama: The foundational code model. - Code Llama - Python: Specialized for Python. - Code Llama - Instruct: Fine-tuned for understanding natural language instructions. More details on these models and how you can access them ➡️ https://bit.ly/3OU18Ue | AI at Meta | Facebook

META JUST MADE YOUR LIFE EASIER 🦙Meta just launched Code Llama 3, a free AI that helps you build workflows and automations — without hiring a developer. 💡It writes better backend logic, fixes broken code, and connects with tools like Zapier or Make. Example: Want to send every new IG DM lead to your email list? 🧠Code Llama can write that workflow — and even explain how it works. ❌No more paying for tools you don’t understand. ❌No more tech overwhelm. ✨This is how you simplify your backend wit