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

Introducing Code Llama: a new code generation model from Meta AI. Based on Llama 2, it’s one of the best-performing and most powerful code generation models available. Join us as we unveil Llama Code’s unparalleled capabilities, its diverse applications; and how it can transform your development experience on AR, VR and MR projects. | Meta for Developers

37 reactions | You can now try Code Llama, Meta’s newest #LLM, directly from your browser with NVIDIA AI Playground. Code Llama is fine-tuned on LLama2 and can generate code in popular languages like Python, C++, Java, and more. https://nvda.ws/3rbQoJ4 | NVIDIA AI | Facebook