meta-llama/Llama-3.2-1B-Instruct

The Llama 3.2-1B-Instruct model by Meta is a 1.23 billion parameter instruction-tuned generative language model, part of the Llama 3.2 collection. Optimized for multilingual dialogue, it excels in agentic retrieval and summarization tasks across officially supported languages like English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. This model utilizes an optimized transformer architecture with supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) for alignment, and features a 32768 token context length.