--- license: mit pipeline_tag: text-generation tags: - cortex.cpp --- ## Overview **Meta** developed and released the [Llama3.3](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct) model, a state-of-the-art multilingual large language model designed for instruction-tuned generative tasks. With 70 billion parameters, this model is optimized for multilingual dialogue use cases, providing high-quality text input and output. Llama3.3 has been fine-tuned through supervised learning and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. It sets a new standard in performance, outperforming many open-source and closed-source chat models on common industry benchmarks. The model’s capabilities make it a powerful tool for applications requiring conversational AI, multilingual support, and instruction adherence. ## Variants | No | Variant | Cortex CLI command | | --- | --- | --- | | 1 | [Llama3.3-70b](https://huggingface.co/cortexso/llama3.3/tree/70b) | `cortex run llama3.3:70b` | ## Use it with Jan (UI) 1. Install **Jan** using [Quickstart](https://jan.ai/docs/quickstart) 2. Use in Jan model Hub: ```bash cortexso/llama3.3 ``` ## Use it with Cortex (CLI) 1. Install **Cortex** using [Quickstart](https://cortex.jan.ai/docs/quickstart) 2. Run the model with command: ```bash cortex run llama3.3 ``` ## Credits - **Author:** Meta - **Converter:** [Homebrew](https://www.homebrew.ltd/) - **Original License:** [License](https://llama.meta.com/llama3/license/) - **Papers:** [Llama-3 Blog](https://llama.meta.com/llama3/)