base_model: unsloth/Llama-3.2-3B-Instruct tags: - text-generation-inference - transformers - unsloth - llama3 - dutch - fine-tuned license: apache-2.0 language: nl

🇳🇱 DUTCHGPT — Fine-Tuned Llama 3.2 3B Model

• Developed by: aacudad & AkramChakrouni
• License: apache-2.0
  
• Base model: unsloth/Llama-3.2-3B-Instruct

📚 Training Datasets

This model was fine-tuned on a diverse mix of high-quality Dutch datasets to support instruction following, legal reasoning, summarization, and conversational tasks:

• 🧾 BramVanroy/ultrachat_200k_dutch — Dutch UltraChat conversational dataset
  
• 🌐 aacudad/8K_DUTCH_NEMOTRON_TRANSLATION — 8K translated instruction-style samples from NVIDIA’s Nemotron dataset
  
• ⚖️ aacudad/5K_DUTCH_LEGAL_SUMMARY — Legal cases with Gemini-generated summaries
  
• 💬 aacudad/86k_DUTCH_conversational — Instructional and chat-style Dutch conversations

🚀 Powered by Unsloth

This Llama 3.2 model was trained 2x faster using Unsloth along with Hugging Face’s TRL library.

🔗 Resources

• 🧠 GitHub (DutchGPT): github.com/aacudad/DutchGPT
  
• 🤗 Hugging Face Profile: huggingface.co/aacudad

Feel free to use the model in your own projects. If you do, I’d really appreciate a reference or tag — thanks! 🙌