ChocoLlama/Llama-3-ChocoLlama-8B-instruct

The ChocoLlama/Llama-3-ChocoLlama-8B-instruct is an 8 billion parameter instruction-tuned causal language model developed by Matthieu Meeus and Anthony Rathé. It is a Dutch language-adapted version of Meta's Llama-3-8B, fine-tuned on 32 billion Dutch tokens and further aligned using Supervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO). This model is specifically optimized for Dutch language generation in conversational settings, achieving state-of-the-art performance on Dutch benchmarks within its weight class.