mlfoundations-dev/qwen2-5_sky_t1_2-5k_base

The mlfoundations-dev/qwen2-5_sky_t1_2-5k_base model is a fine-tuned version of Qwen's Qwen2.5-7B-Instruct, developed by mlfoundations-dev. It was trained on the sky_t1_2-5k_base dataset, utilizing a learning rate of 1e-05 and a total batch size of 96 over 3 epochs. This model is based on the Qwen2.5 architecture, making it suitable for tasks requiring a robust base language model, though specific differentiators beyond its fine-tuning dataset are not detailed.