The trl-lib/qwen1.5-1.8b-sft model is a 1.8 billion parameter language model, fine-tuned from the Qwen/Qwen1.5-1.8B architecture. Developed by trl-lib, this model has been instruction fine-tuned on the HuggingFaceH4/deita-6k-v0-sft dataset. It is designed for general language generation tasks, leveraging its compact size and fine-tuning for efficient deployment.
No reviews yet. Be the first to review!