The bennett-tan/phi-4-mini-instruct-merged is a 3.8 billion parameter instruction-tuned causal language model developed by bennett-tan. This model is a finetuned variant of the phi3 architecture, optimized for faster training using Unsloth and Huggingface's TRL library. It is designed for general instruction-following tasks, leveraging its efficient training methodology.
No reviews yet. Be the first to review!