mlx-community
/

Llama-2-7b-chat-mlx

Text Generation

Model card Files Files and versions

pcuenq HF Staff commited on Dec 6, 2023

Commit

7207004

·

1 Parent(s): 225ab0a

float16

Files changed (1) hide show

README.md +2 -0

README.md CHANGED Viewed

@@ -13,5 +13,7 @@ tags:
 Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, in `npz` format suitable for use in Apple's MLX framework.
 Please, refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b-chat/tree/main) for details on Llama 2.

 Llama 2 is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the repository for the 7B fine-tuned model, in `npz` format suitable for use in Apple's MLX framework.
+Weights have been converted to `float16` from the original `bfloat16` type, because `numpy` is not compatible with `bfloat16` out of the box.
 Please, refer to the [original model card](https://huggingface.co/meta-llama/Llama-2-7b-chat/tree/main) for details on Llama 2.