the-jb/phi-1_5-tofu_full

The-jb/phi-1_5-tofu_full is a 1.4 billion parameter language model, fine-tuned from Microsoft's phi-1_5 architecture. It has been specifically adapted using the full TOFU dataset, making it suitable for tasks requiring factual recall and knowledge-based generation. This model is designed for efficient deployment in applications where a smaller, specialized model is preferred.

Cold
Public
1.4B
BF16
2048
License: mit
Hugging Face

No reviews yet. Be the first to review!