OpenPipe/Qwen3-14B-Instruct

OpenPipe/Qwen3-14B-Instruct is a 14.8 billion parameter causal language model, fine-tuned from the Qwen3-14B base model. It features a 32,768 token context window, extendable to 131,072 tokens with YaRN. This variant is specifically designed to be finetuning-friendly, addressing chat template inconsistencies by ensuring uniform message formatting with <think></think> tags for both training and inference. It retains the strong general capabilities of the Qwen3-14B base model while optimizing for consistent finetuning workflows.