Edit model card

Core ML version of Llama 2

This is a Core ML version of meta-llama/Llama-2-7b-chat-hf. For license information, model details and acceptable use policy, please refer to the original model card.

This conversion was performed in float16 mode with a fixed sequence length of 64, and is intended for evaluation and test purposes. Please, open a conversation in the Community tab if you have questions or want to report an issue.

Downloads last month
Hosted inference API
This model can be loaded on the Inference API on-demand.

Space using coreml-projects/Llama-2-7b-chat-coreml 1