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
216
Inference Examples
Inference API (serverless) is not available, repository is disabled.

Spaces using coreml-projects/Llama-2-7b-chat-coreml 4