aloobun/Reyna-Mini-1.8B-v0.1

Reyna-Mini-1.8B-v0.1 by aloobun is a 1.8 billion parameter causal language model, fine-tuned from Qwen/Qwen1.5-1.8B-Chat with a 32768 token context length. This model utilizes SFT on the OpenHermes-2.5 dataset, establishing the foundation for aloobun's Qwen1.5 LLM series. It is designed for chat-based applications, formatted for ChatML, and demonstrates an average benchmark score of 41.46 across various tasks including ARC, HellaSwag, MMLU, TruthfulQA, Winogrande, and GSM8K.