An Open-source assistant model trained on various data for Turkish by NeuroTürk !Ekrangörüntüsü2026-05-17_141827-removebg-preview — Base model: 4-stage Turkish continual pre-training (CPT) applied on top of a multilingual foundation. — Fine-tuning (SFT): 372,697 carefully curated Turkish instruction-response pairs. — Optimization: LoRA (r=64) + DoRA, bfloat16, flash-attention-2, AdamW. — Final training loss: 0.6707 New special tokens were added to the tokenizer for two purposes: — Language-structure tokens: To represent Turkish morphological features more efficiently. — Task and structure tokens: To support structural use cases such as chain-of-thought, code blocks, section markers, and language labels. The following 20 tokens have been added to the vocabulary but were not used during training; they are defined as infrastructure for future advanced capabilities: For faster inference and lower resource usage, GGUF quantized versions of HYZ-01-0.6B are available. These were kindly provided by mradermacher. 1. Download the GGUF file (e.g., hyz-01-0.6b-q4km.gguf) from the repository above. 2. Run with llama.cpp bibtex @misc{neuroturk2026hyz01, author = {NeuroTürk}, title …
Модальности:
Генерация текста
Области применения:
Следование инструкциям Диалог / чат Суммаризация Ответы на вопросы
Задача: Генерация текста
Автор: neuroturk
Теги: qwen3, turkish, turkish-llm, turkish-nlp, instruct, neuroturk, hyz01, sft
Лайков: 3 | Загрузок: 48
Описание основано на материалах HuggingFace. Перевод выполнен автоматически.
